Data valuation using reinforcement learning.

Data valuation using reinforcement learning

Номер патента: US12106223B2
Опубликовано: 01-10-2024
Автор(ы): Jinsung YOON, Sercan Omer Arik, Tomas Pfister
Принадлежит: Google LLC
Получить PDF файл: Открыть в новом окне

Рисунок 1. Взаимосвязь патентов (ближайшие 20).

Distributional reinforcement learning

Номер патента: US12056593B2. Автор: William Clinton Dabney,Marc GENDRON-BELLEMARE. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-08-06.

Distributional reinforcement learning

Номер патента: US20210064970A1. Автор: William Clinton Dabney,Marc GENDRON-BELLEMARE. Владелец: DeepMind Technologies Ltd. Дата публикации: 2021-03-04.

Distributional reinforcement learning

Номер патента: US20240370707A1. Автор: William Clinton Dabney,Marc GENDRON-BELLEMARE. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-11-07.

Reinforcement learning systems comprising a relational network for generating data encoding relationships between entities in an environment

Номер патента: EP3794513A1. Автор: Adam Anthony SANTORO,Yujia LI,David Nunes RAPOSO,Victor Constant Bapst,Vinicius Zambaldi. Владелец: DeepMind Technologies Ltd. Дата публикации: 2021-03-24.

Data valuation using reinforcement learning

Номер патента: US20230325675A1. Автор: Jinsung YOON,Sercan Omer Arik,Tomas Pfister. Владелец: Google LLC. Дата публикации: 2023-10-12.

Data valuation using reinforcement learning

Номер патента: US11823058B2. Автор: Jinsung YOON,Tomas Jon Pfister,Sercan Omer Arik. Владелец: Google LLC. Дата публикации: 2023-11-21.

Natural question generation via reinforcement learning based graph-to-sequence model

Номер патента: US11816136B2. Автор: YU Chen,Lingfei Wu,Mohammed J. Zaki. Владелец: International Business Machines Corp. Дата публикации: 2023-11-14.

Attention-based deep reinforcement learning for autonomous agents

Номер патента: US20230419113A1. Автор: Tao Sun,Sahika Genc,Sunil Mallya KASARAGOD,Sravan Babu Bodapati. Владелец: Amazon Technologies Inc. Дата публикации: 2023-12-28.

Deep reinforcement learning with fast updating recurrent neural networks and slow updating recurrent neural networks

Номер патента: US11842261B2. Автор: Iain Robert Dunning,Maxwell Elliot Jaderberg,Wojciech CZARNECKI. Владелец: DeepMind Technologies Ltd. Дата публикации: 2023-12-12.

Attention-based deep reinforcement learning for autonomous agents

Номер патента: US11900244B1. Автор: Tao Sun,Sahika Genc,Sunil Mallya KASARAGOD,Sravan Babu Bodapati. Владелец: Amazon Technologies Inc. Дата публикации: 2024-02-13.

Deep reinforcement learning with fast updating recurrent neural networks and slow updating recurrent neural

Номер патента: EP4357976A1. Автор: Iain Robert Dunning,Maxwell Elliot Jaderberg,Wojciech CZARNECKI. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-04-24.

Deep reinforcement learning with fast updating recurrent neural networks and slow updating recurrent neural networks

Номер патента: US20240220774A1. Автор: Iain Robert Dunning,Maxwell Elliot Jaderberg,Wojciech CZARNECKI. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-07-04.

Programmable reinforcement learning systems

Номер патента: EP3610423A1. Автор: Serkan CABI,Joao Ferdinando FREITAS,Sergio Gomez COLMENAREJO,Misha Man DENIL,David William SAXTON. Владелец: DeepMind Technologies Ltd. Дата публикации: 2020-02-19.

Training an environment generator of a generative adversarial network (GAN) to generate realistic environments that incorporate reinforcement learning (RL) algorithm feedback

Номер патента: US12124537B2. Автор: Samuel Mathew Jawaharlal,Sathya Santhar,Sridevi Kannan,Kothagorla Lakshmana Rao. Владелец: International Business Machines Corp. Дата публикации: 2024-10-22.

Interactive reinforcement learning with dynamic reuse of prior knowledge

Номер патента: US11308401B2. Автор: Zhaodong WANG,Matthew Edmund TAYLOR. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2022-04-19.

Deep reinforcement learning based method for surreptitiously generating signals to fool a recurrent neural network

Номер патента: US20210089891A1. Автор: Michael A. Warren,Christopher SERRANO,Pape Sylla. Владелец: HRL LABORATORIES LLC. Дата публикации: 2021-03-25.

Reverse reinforcement learning to train training data for natural language processing neural network

Номер патента: US20230419077A1. Автор: Tong Liu,Wen Wang,Xiang Yu Yang,Zhong Fang Yuan,Hai Bo Zou. Владелец: International Business Machines Corp. Дата публикации: 2023-12-28.

Programmable reinforcement learning systems

Номер патента: WO2018211146A1. Автор: Serkan CABI,Joao Ferdinando FREITAS,Sergio Gomez COLMENAREJO,Misha Man DENIL,David William SAXTON. Владелец: DeepMind Technologies Limited. Дата публикации: 2018-11-22.

Programmable reinforcement learning systems

Номер патента: US20200167633A1. Автор: Serkan CABI,Joao Ferdinando GOMES DE FREITAS,Sergio Gomez COLMENAREJO,Misha Man Ray DENIL,David William SAXTON. Владелец: DeepMind Technologies Ltd. Дата публикации: 2020-05-28.

System reinforcement learning method and apparatus, and computer storage medium

Номер патента: US11669711B2. Автор: CHAO Xu,Zitian CHEN,Shuqin Xie,Cewu LU. Владелец: Shanghai Sensetime Intelligent Technology Co Ltd. Дата публикации: 2023-06-06.

DATA VALUATION USING REINFORCEMENT LEARNING

Номер патента: US20210089870A1. Автор: Arik Sercan Omer,Pfister Tomas Jon,Yoon Jinsung. Владелец: Google LLC. Дата публикации: 2021-03-25.

Routing connections in integrated circuits based on reinforcement learning

Номер патента: US20210342516A1. Автор: Haoxing Ren,Matthew Fojtik. Владелец: Nvidia Corp. Дата публикации: 2021-11-04.

Routing connections in integrated circuits based on reinforcement learning

Номер патента: US12019967B2. Автор: Haoxing Ren,Matthew Fojtik. Владелец: Nvidia Corp. Дата публикации: 2024-06-25.

Code generation with reinforcement learning

Номер патента: WO2022265745A1. Автор: Neelakantan Sundaresan,Miltiadis Allamanis,Alexey Svyatkovskiy,Daya Guo. Владелец: Microsoft Technology Licensing, LLC. Дата публикации: 2022-12-22.

Code generation with reinforcement learning

Номер патента: US20220398071A1. Автор: Neelakantan Sundaresan,Miltiadis Allamanis,Alexey Svyatkovskiy,Daya Guo. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2022-12-15.

Reinforcement learning neural networks grounded in learned visual entities

Номер патента: US10748039B2. Автор: Tejas Dattatraya KULKARNI,Catalin-Dumitru IONESCU. Владелец: DeepMind Technologies Ltd. Дата публикации: 2020-08-18.

Method of neural architecture search using continuous action reinforcement learning

Номер патента: US11914672B2. Автор: Mohammad SALAMEH,Keith George MILLS,Di NIU. Владелец: Huawei Technologies Co Ltd. Дата публикации: 2024-02-27.

Reinforcement learning neural networks grounded in learned visual entities

Номер патента: US20200104645A1. Автор: Tejas Dattatraya KULKARNI,Catalin-Dumitru IONESCU. Владелец: DeepMind Technologies Ltd. Дата публикации: 2020-04-02.

Code generation with reinforcement learning

Номер патента: US20240061655A1. Автор: Neelakantan Sundaresan,Miltiadis Allamanis,Alexey Svyatkovskiy,Daya Guo. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2024-02-22.

Code generation with reinforcement learning

Номер патента: US11836467B2. Автор: Neelakantan Sundaresan,Miltiadis Allamanis,Alexey Svyatkovskiy,Daya Guo. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2023-12-05.

Synthetic data generation using deep reinforcement learning

Номер патента: WO2023200504A1. Автор: Kiran Rama. Владелец: Microsoft Technology Licensing, LLC. Дата публикации: 2023-10-19.

Large-scale retrieval augmented reinforcement learning

Номер патента: WO2023222885A1. Автор: Arthur Clément Guez,Peter Conway HUMPHREYS. Владелец: DeepMind Technologies Limited. Дата публикации: 2023-11-23.

System reinforcement learning method and apparatus, and computer storage medium

Номер патента: US20200349431A1. Автор: CHAO Xu,Zitian CHEN,Shuqin Xie,Cewu LU. Владелец: Shanghai Sensetime Intelligent Technology Co Ltd. Дата публикации: 2020-11-05.

Synthetic data generation using deep reinforcement learning

Номер патента: US20230334290A1. Автор: Kiran Rama. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2023-10-19.

Method, system, and computer program product for implementing reinforcement learning

Номер патента: US11978246B2. Автор: Hao Yang,Wei Zhang,Liang Gou. Владелец: VISA INTERNATIONAL SERVICE ASSOCIATION. Дата публикации: 2024-05-07.

Training an environment generator of a generative adversarial network (gan) to generate realistic environments that incorporate reinforcement learning (rl) algorithm feedback

Номер патента: US20230214453A1. Автор: Samuel Mathew Jawaharlal,Sathya Santhar,Sridevi Kannan,Kothagorla Lakshmana Rao. Владелец: International Business Machines Corp. Дата публикации: 2023-07-06.

De novo drug design using reinforcement learning

Номер патента: WO2024127035A1. Автор: Marco CAROBENE,Aleksandra Dominika KALISZ,Marius URBONAS. Владелец: Exscientia Ai Limited. Дата публикации: 2024-06-20.

Reinforcement Learning Techniques for Dialogue Management

Номер патента: US20220108080A1. Автор: Rajesh Virupaksha Munavalli. Владелец: PayPal Inc. Дата публикации: 2022-04-07.

Data path circuit design using reinforcement learning

Номер патента: US20230139623A1. Автор: Ilyas Elkin,Robert Kirby,Ming Y. Siu,Stuart Oberman,Bryan Catanzaro,Jonathan RAIMAN,Rajarshi Roy,Saad Godil,Neel Kant. Владелец: Nvidia Corp. Дата публикации: 2023-05-04.

Reinforcement learning with inductive logic programming

Номер патента: US20230143937A1. Автор: Songtao Lu,Akifumi Wachi. Владелец: International Business Machines Corp. Дата публикации: 2023-05-11.

System for preserving image and acoustic sensitivity using reinforcement learning

Номер патента: US20230048759A1. Автор: Madhusudhanan Krishnamoorthy. Владелец: Bank of America Corp. Дата публикации: 2023-02-16.

System for preserving image and acoustic sensitivity using reinforcement learning

Номер патента: US11756299B2. Автор: Madhusudhanan Krishnamoorthy. Владелец: Bank of America Corp. Дата публикации: 2023-09-12.

Identification and clustering of lane lines on roadways using reinforcement learning

Номер патента: US11836992B2. Автор: Orhan BULAN,Mason D. Gemar,David H. Clifford,Mohammed H. Al Qizwini. Владелец: GENERAL MOTORS LLC. Дата публикации: 2023-12-05.

Selecting action slates using reinforcement learning

Номер патента: US20170154261A1. Автор: Peter Goran Sunehag. Владелец: Google LLC. Дата публикации: 2017-06-01.

System for preserving image and acoustic sensitivity using reinforcement learning

Номер патента: US20220108110A1. Автор: Madhusudhanan Krishnamoorthy. Владелец: Bank of America Corp. Дата публикации: 2022-04-07.

Semantic graphing of heterogeneous documents for automated decision making and resource allocation using reinforcement learning

Номер патента: US20230244990A1. Автор: Tobias Jacobs,Julia Gastinger. Владелец: NEC Laboratories Europe GmbH. Дата публикации: 2023-08-03.

Identification and clustering of lane lines on roadways using reinforcement learning

Номер патента: US20220245386A1. Автор: Orhan BULAN,Mason D. Gemar,David H. Clifford,Mohammed H. Al Qizwini. Владелец: GENERAL MOTORS LLC. Дата публикации: 2022-08-04.

Attention-lstm-based method for knowledge reasoning of reinforcement learning agent

Номер патента: NL2028258A. Автор: Chen Chao,Liu Hui,Liu Hao,WANG Yinglong,Shu Minglei. Владелец: Shandong Artificial Intelligence Inst. Дата публикации: 2021-08-17.

Attention-lstm-based method for knowledge reasoning of reinforcement learning agent

Номер патента: NL2028258B1. Автор: Chen Chao,Liu Hui,Liu Hao,WANG Yinglong,Shu Minglei. Владелец: Shandong Artificial Intelligence Inst. Дата публикации: 2022-04-06.

Code generation through reinforcement learning using code-quality rewards

Номер патента: US20240192927A1. Автор: Neelakantan Sundaresan,Shao Kun DENG,Alexey Svyatkovskiy,Michele Tufano. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2024-06-13.

Code generation through reinforcement learning using code-quality rewards

Номер патента: WO2023113891A1. Автор: Neelakantan Sundaresan,Shao Kun DENG,Alexey Svyatkovskiy,Michele Tufano. Владелец: Microsoft Technology Licensing, LLC.. Дата публикации: 2023-06-22.

Unsupervised detection of intermediate reinforcement learning goals

Номер патента: US20230196058A1. Автор: Pierre SERMANET. Владелец: Google LLC. Дата публикации: 2023-06-22.

Unsupervised detection of intermediate reinforcement learning goals

Номер патента: WO2018085778A1. Автор: Pierre SERMANET. Владелец: Google LLC. Дата публикации: 2018-05-11.

Unsupervised detection of intermediate reinforcement learning goals

Номер патента: US12106200B2. Автор: Pierre SERMANET. Владелец: Google LLC. Дата публикации: 2024-10-01.

Reinforcement learning approach to approximate a mental map of formal logic

Номер патента: WO2020068877A1. Автор: Archuleta Michelle. Владелец: Michelle Archuleta. Дата публикации: 2020-04-02.

Code generation through reinforcement learning using code-quality rewards

Номер патента: US11941373B2. Автор: Neelakantan Sundaresan,Shao Kun DENG,Alexey Svyatkovskiy,Michele Tufano. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2024-03-26.

Unsupervised detection of intermediate reinforcement learning goals

Номер патента: EP3535702A1. Автор: Pierre SERMANET. Владелец: Google LLC. Дата публикации: 2019-09-11.

Contrastive learning by dynamically selecting dropout ratios and locations based on reinforcement learning

Номер патента: US20240119275A1. Автор: Tong Liu,Zhong Fang Yuan,Yi Chen Zhong,Si Tong Zhao,Hai Bo Zou,Yuan Yuan Ding. Владелец: International Business Machines Corp. Дата публикации: 2024-04-11.

Asynchronous deep reinforcement learning

Номер патента: EP4398159A2. Автор: Adria Puigdomenech BADIA,David Silver,Volodymyr Mnih,Koray Kavukcuoglu,Timothy James Alexander Harley,Alexander Benjamin GRAVES. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-07-10.

Reinforcement learning in combinatorial action spaces

Номер патента: WO2019222746A1. Автор: Jing Wang,Tze Way Eugene Ie,Ritesh Agarwal,Craig Edgar Boutilier,Vihan JAIN. Владелец: Google LLC. Дата публикации: 2019-11-21.

Methods, systems and computer program products for protecting a deep reinforcement learning agent

Номер патента: US12039062B2. Автор: Peter Ashwood-Smith,Omar Ahmad Mohammad ALHUSSEIN. Владелец: Huawei Technologies Co Ltd. Дата публикации: 2024-07-16.

Asynchronous deep reinforcement learning

Номер патента: EP4398159A3. Автор: Adria Puigdomenech BADIA,David Silver,Volodymyr Mnih,Koray Kavukcuoglu,Timothy James Alexander Harley,Alexander Benjamin GRAVES. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-10-02.

Reinforcement learning using baseline and policy neural networks

Номер патента: US20240362481A1. Автор: Adria Puigdomenech BADIA,David Silver,Volodymyr Mnih,Koray Kavukcuoglu,Timothy James Alexander Harley,Alexander Benjamin GRAVES. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-10-31.

Meta-Agent for Reinforcement Learning

Номер патента: US20230401482A1. Автор: Victor Kostyuk. Владелец: Offerfit Inc. Дата публикации: 2023-12-14.

Methods and systems that safely update control policies within reinforcement-learning-based management-system agents

Номер патента: US20240037193A1. Автор: Gagandeep Singh,Marius VILCU,Asmitha Rathis,Nina Narodytska,Arnav CHAKRAVARTHY. Владелец: VMware LLC. Дата публикации: 2024-02-01.

Intelligent agent reinforcement learning method and apparatus, device and medium

Номер патента: US20210117738A1. Автор: Yang Xue,Wei Zhang,Jing Lin,Chunxiao Liu. Владелец: Shenzhen Sensetime Technology Co Ltd. Дата публикации: 2021-04-22.

Asynchronous deep reinforcement learning

Номер патента: US11783182B2. Автор: Adria Puigdomenech BADIA,David Silver,Volodymyr Mnih,Koray Kavukcuoglu,Timothy James Alexander Harley,Alexander Benjamin GRAVES. Владелец: DeepMind Technologies Ltd. Дата публикации: 2023-10-10.

Methods, systems and computer program products for protecting a deep reinforcement learning agent

Номер патента: US20230185932A1. Автор: Peter Ashwood-Smith,Omar Ahmad Mohammad ALHUSSEIN. Владелец: Huawei Technologies Co Ltd. Дата публикации: 2023-06-15.

Managing aleatoric and epistemic uncertainty in reinforcement learning, with applications to autonomous vehicle control

Номер патента: EP4086813A1. Автор: Leo Laine,Carl-Johan HOEL. Владелец: VOLVO AUTONOMOUS SOLUTIONS AB. Дата публикации: 2022-11-09.

Method of RF Analog Circuits Electronic Design Automation Based on GCN and Deep Reinforcement Learning

Номер патента: US20230267250A1. Автор: Rui Ma,Weidong Cao,Mouhacine Benosman. Владелец: Mitsubishi Electric Research Laboratories Inc. Дата публикации: 2023-08-24.

Safe reinforcement learning by logical neural network

Номер патента: US20220164668A1. Автор: Michiaki Tatsubori,Asim Munawar,Daiki Kimura,Ryosuke Kohita,Akifumi Wachi,Subhajit CHAUDHURY. Владелец: International Business Machines Corp. Дата публикации: 2022-05-26.

Data-efficient reinforcement learning for continuous control tasks

Номер патента: US20240062035A1. Автор: Thomas Lampe,Ivaylo Popov,Timothy Paul Lillicrap,Nicolas Manfred Otto Heess,Martin RIEDMILLER,Roland Hafner,Gabriel BARTH-MARON,Mel Vecerik. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-02-22.

Methods, systems and computer program products for protecting a deep reinforcement learning agent

Номер патента: WO2023103763A1. Автор: Peter Ashwood-Smith,Omar Ahmad Mohammad ALHUSSEIN. Владелец: Huawei Technologies Co., Ltd.. Дата публикации: 2023-06-15.

Method of rf analog circuits electronic design automation based on gcn and deep reinforcement learning

Номер патента: EP4338087A1. Автор: Rui Ma,Weidong Cao,Mouhacine Benosman. Владелец: Mitsubishi Electric Corp. Дата публикации: 2024-03-20.

Reinforcement learning using baseline and policy neural networks

Номер патента: US12020155B2. Автор: Adria Puigdomenech BADIA,David Silver,Volodymyr Mnih,Koray Kavukcuoglu,Timothy James Alexander Harley,Alexander Benjamin GRAVES. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-06-25.

Using Reinforcement Learning to Dynamically Tune Cache Policy Parameters

Номер патента: US20210374523A1. Автор: Vinicius Michel Gottin,Alex Laier Bordignon,Daniel Sadoc Menasché,Tiago Salviano Calmon,Jonas Furtado Dias. Владелец: EMC IP Holding Co LLC. Дата публикации: 2021-12-02.

Using reinforcement learning to dynamically tune cache policy parameters

Номер патента: US11403525B2. Автор: Vinicius Michel Gottin,Alex Laier Bordignon,Daniel Sadoc Menasché,Tiago Salviano Calmon,Jonas Furtado Dias. Владелец: Dell Products LP. Дата публикации: 2022-08-02.

Temporal difference scaling when controlling agents using reinforcement learning

Номер патента: US20240104388A1. Автор: Tom Schaul. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-03-28.

Temporal difference scaling when controlling agents using reinforcement learning

Номер патента: EP4268134A1. Автор: Tom Schaul. Владелец: DeepMind Technologies Ltd. Дата публикации: 2023-11-01.

Environment navigation using reinforcement learning

Номер патента: EP4386624A3. Автор: Laurent Sifre,Hubert Josef Soyer,Koray Kavukcuoglu,Razvan PASCANU,Raia Thais HADSELL,Misha Man Ray DENIL,Andrew James Ballard,Andrea Banino,Sudarshan Kumaran,Piotr Wojciech Mirowski,Fabio VIOLA,Rostislav GOROSHIN. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-08-07.

Method for optimizing program using reinforcement learning

Номер патента: US12026487B2. Автор: Jaejin Lee,Wookeun JUNG. Владелец: Moreh Corp. Дата публикации: 2024-07-02.

Configuring a power management system using reinforcement learning

Номер патента: US20220100254A1. Автор: Robert Szurtei. Владелец: ATI TECHNOLOGIES ULC. Дата публикации: 2022-03-31.

System and method for actor based simulation of complex system using reinforcement learning

Номер патента: EP3966669A1. Автор: Prashant Kumar,Vinay Kulkarni,Vinita BANIWAL,Hardik MEISHERI,Souvik Barat,Harshad KHADILKAR,Monika Gajrani. Владелец: Tata Consultancy Services Ltd. Дата публикации: 2022-03-16.

Environment navigation using reinforcement learning

Номер патента: EP4386624A2. Автор: Laurent Sifre,Hubert Josef Soyer,Koray Kavukcuoglu,Razvan PASCANU,Raia Thais HADSELL,Misha Man Ray DENIL,Andrew James Ballard,Andrea Banino,Sudarshan Kumaran,Piotr Wojciech Mirowski,Fabio VIOLA,Rostislav GOROSHIN. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-06-19.

Training data generation via reinforcement learning fault-injection

Номер патента: US20230087837A1. Автор: Larisa Shwartz,Jinho Hwang,Frank Bagehorn,Jesus Maria Rios Aliaga,Stephen James Hussey. Владелец: International Business Machines Corp. Дата публикации: 2023-03-23.

Distributed cache or replay service for massively scalable distributed reinforcement learning

Номер патента: EP4143744A1. Автор: Yu Zheng,Junchao CHEN,Amir Yazdanbakhsh. Владелец: Google LLC. Дата публикации: 2023-03-08.

Cloud architecture for reinforcement learning

Номер патента: WO2023219675A1. Автор: Xiaoyan Liu,Timothy James Chapman,Steve K. LIM,Taylor Paul SPANGLER,Kashyap Maheshkumar PATEL,Marc Mas MEZQUITA,Levent OZGUR. Владелец: Microsoft Technology Licensing, LLC. Дата публикации: 2023-11-16.

Distributed Cache or Replay Service for Massively Scalable Distributed Reinforcement Learning

Номер патента: US20230229929A1. Автор: Yu Zheng,Junchao CHEN,Amir Yazdanbakhsh. Владелец: Google LLC. Дата публикации: 2023-07-20.

Distributed cache or replay service for massively scalable distributed reinforcement learning

Номер патента: WO2022039781A1. Автор: Yu Zheng,Junchao CHEN,Amir Yazdanbakhsh. Владелец: Google LLC. Дата публикации: 2022-02-24.

Method for self-supervised reinforcement learning by analogy-making cross-reference to related application

Номер патента: US20230215133A1. Автор: Shin Young Joo,Sang Wan Lee. Владелец: Korea Advanced Institute of Science and Technology KAIST. Дата публикации: 2023-07-06.

Meta-gradient updates for training return functions for reinforcement learning systems

Номер патента: US11836620B2. Автор: David Silver,Hado Philip VAN HASSELT,Zhongwen XU. Владелец: DeepMind Technologies Ltd. Дата публикации: 2023-12-05.

Transferable training for automated reinforcement-learning-based application-managers

Номер патента: US20200065670A1. Автор: Gregory T. Burk,Dongni Wang,Dev Nag,Yanislav Yankov,Nicholas Mark Grant Stephen. Владелец: VMware LLC. Дата публикации: 2020-02-27.

State-augmented reinforcement learning

Номер патента: US20220121921A1. Автор: Bo Li,Yada Zhu,JinJun Xiong,Pin-Yu Chen,Kumar Bhaskaran,Yunan Ye. Владелец: University of Illinois at Urbana Champaign. Дата публикации: 2022-04-21.

State-augmented reinforcement learning

Номер патента: US11880765B2. Автор: Bo Li,Yada Zhu,JinJun Xiong,Pin-Yu Chen,Kumar Bhaskaran,Yunan Ye. Владелец: University of Illinois at Urbana Champaign. Дата публикации: 2024-01-23.

Memory-based reinforcement learning method for storing optional information in streaming data and system therefore

Номер патента: US20210263859A1. Автор: Sung Ju Hwang,Minki KANG,Hyunwoo Jung,Moonsu Han. Владелец: Korea Advanced Institute of Science and Technology KAIST. Дата публикации: 2021-08-26.

Deep reinforcement learning-based intelligent job batching method and apparatus, and electronic device

Номер патента: US20230067605A1. Автор: LIANG Liu,Xiaolong ZHENG,Huadong Ma,Chengling Jiang,Zihui Luo. Владелец: BEIJING UNIVERSITY OF POSTS AND TELECOMMUNICATIONS. Дата публикации: 2023-03-02.

Offline meta reinforcement learning for online adaptation for robotic control tasks

Номер патента: US20230095351A1. Автор: Stefan Schaal,Sergey Vladimir Levine,Zihao ZHAO,Jianlan LUO. Владелец: Intrinsic Innovation LLC. Дата публикации: 2023-03-30.

Knowledge graph reasoning systems using self-supervised reinforcement learning and methods thereof

Номер патента: US20240249154A1. Автор: Ying Ma,Owen Burns,Mingqiu Wang. Владелец: University of Central Florida Research Foundation Inc UCFRF. Дата публикации: 2024-07-25.

Retrieval augmented reinforcement learning

Номер патента: US20240320506A1. Автор: Adria Puigdomenech BADIA,Charles BLUNDELL,Timothy Paul Lillicrap,Simon Osindero,Nan KE,Theophane Guillaume Weber,Andrea Banino,Anirudh GOYAL,Abram Luke FRIESEN. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-09-26.

Meta-gradient updates for training return functions for reinforcement learning systems

Номер патента: US20210089915A1. Автор: David Silver,Hado Philip VAN HASSELT,Zhongwen XU. Владелец: DeepMind Technologies Ltd. Дата публикации: 2021-03-25.

Meta-gradient updates for training return functions for reinforcement learning systems

Номер патента: EP3769264A1. Автор: David Silver,Hado Philip VAN HASSELT,Zhongwen XU. Владелец: DeepMind Technologies Ltd. Дата публикации: 2021-01-27.

Computationally efficient reinforcement-learning-based application manager

Номер патента: US20200065156A1. Автор: Gregory T. Burk,Dongni Wang,Dev Nag,Yanislav Yankov,Nicholas Mark Grant Stephen. Владелец: VMware LLC. Дата публикации: 2020-02-27.

Intelligently modifying digital calendars utilizing a graph neural network and reinforcement learning

Номер патента: US20220343155A1. Автор: Gang Wu,Richard Whitehead,Georgios Theocharous,Viswanathan Swaminathan,Saayan Mitra,Zahraa Parekh,Ben Tepfer. Владелец: Adobe Inc. Дата публикации: 2022-10-27.

User intent classification using a multi-agent reinforcement learning framework

Номер патента: US11836590B2. Автор: Shobhit Agrawal,Puneet Mehta,Nishant Pandey. Владелец: Ai Netomi Inc. Дата публикации: 2023-12-05.

Explainable deep reinforcement learning using a factorized function

Номер патента: US20220188623A1. Автор: Robert Price. Владелец: Palo Alto Research Center Inc. Дата публикации: 2022-06-16.

Reinforcement learning through a double actor critic algorithm

Номер патента: US11816591B2. Автор: James MACGLASHAN. Владелец: Sony Corp of America. Дата публикации: 2023-11-14.

Learning options for action selection with meta-gradients in multi-task reinforcement learning

Номер патента: EP4111383A1. Автор: David Silver,Hado Philip VAN HASSELT,Matteo HESSEL,Zhongwen XU,Vivek Veeriah Jeya Veeraiah,Tom Ben Zion Zahavy,Junhyuk Oh,Iurii Kemaev,Satinder Singh Baveja. Владелец: DeepMind Technologies Ltd. Дата публикации: 2023-01-04.

Reinforcement learning using meta-learned intrinsic rewards

Номер патента: US20210089910A1. Автор: Junhyuk Oh,Satinder Singh Baveja,Zeyu Zheng. Владелец: DeepMind Technologies Ltd. Дата публикации: 2021-03-25.

Reinforcement learning through a double actor critic algorithm

Номер патента: US20200302323A1. Автор: James MACGLASHAN. Владелец: Sony Corp of America. Дата публикации: 2020-09-24.

Reinforcement learning through a double actor critic algorithm

Номер патента: EP3921785A1. Автор: James MACGLASHAN. Владелец: Sony Corp of America. Дата публикации: 2021-12-15.

Multi-agent reinforcement learning system and operating method thereof

Номер патента: US20230334329A1. Автор: Joo-Young Kim,Je YANG. Владелец: Korea Advanced Institute of Science and Technology KAIST. Дата публикации: 2023-10-19.

Distributed training using actor-critic reinforcement learning with off-policy correction factors

Номер патента: US20240127060A1. Автор: Thomas Ward,Karen SIMONYAN,Hubert Josef Soyer,Lasse ESPEHOLT,Yotam Doron,Vlad Firoiu,Volodymyr Mnih,Koray Kavukcuoglu,Remi MUNOS,Timothy James Alexander Harley,Iain Robert Dunning. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-04-18.

Training technologies for deep reinforcement learning technologies for detecting malware

Номер патента: EP3782067A1. Автор: Yu Wang,Jack Wilson Stokes, Iii,Adrian Mihail Marinescu. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2021-02-24.

Training technologies for deep reinforcement learning technologies for detecting malware

Номер патента: WO2019226402A1. Автор: Yu Wang,Jack Wilson Stokes, Iii,Adrian Mihail Marinescu. Владелец: Microsoft Technology Licensing, LLC. Дата публикации: 2019-11-28.

Distributed training using actor-critic reinforcement learning with off-policy correction factors

Номер патента: US11868894B2. Автор: Thomas Ward,Karen SIMONYAN,Hubert Josef Soyer,Lasse ESPEHOLT,Yotam Doron,Vlad Firoiu,Volodymyr Mnih,Koray Kavukcuoglu,Remi MUNOS,Timothy James Alexander Harley,Iain Robert Dunning. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-01-09.

Reinforcement Learning-Based Semantic Method and System

Номер патента: US20240185103A1. Автор: Steven Dennis Flinn. Владелец: ManyWorlds Inc. Дата публикации: 2024-06-06.

Multi-agent reinforcement learning with matchmaking policies

Номер патента: US20230244936A1. Автор: Oriol Vinyals,David Silver,Maxwell Elliot Jaderberg. Владелец: DeepMind Technologies Ltd. Дата публикации: 2023-08-03.

Multi-agent reinforcement learning with matchmaking policies

Номер патента: US12067491B2. Автор: Oriol Vinyals,David Silver,Maxwell Elliot Jaderberg. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-08-20.

Reinforcement learning using agent curricula

Номер патента: EP3776363A1. Автор: Wojciech CZARNECKI,Siddhant JAYAKUMAR. Владелец: DeepMind Technologies Ltd. Дата публикации: 2021-02-17.

Distributional reinforcement learning using quantile function neural networks

Номер патента: US20230196108A1. Автор: William Clinton Dabney,Georg Ostrovski. Владелец: DeepMind Technologies Ltd. Дата публикации: 2023-06-22.

Quantum computation through reinforcement learning

Номер патента: AU2018406532A1. Автор: Hartmut Neven,Vadim SMELYANSKIY,Sergio Boixo CASTRILLO,Yuezhen Niu. Владелец: Google LLC. Дата публикации: 2020-07-09.

Quantum computation through reinforcement learning

Номер патента: EP3746953A1. Автор: Hartmut Neven,Vadim SMELYANSKIY,Sergio Boixo CASTRILLO,Yuezhen Niu. Владелец: Google LLC. Дата публикации: 2020-12-09.

Quantum computation through reinforcement learning

Номер патента: AU2022204185A1. Автор: Hartmut Neven,Vadim SMELYANSKIY,Sergio Boixo CASTRILLO,Yuezhen Niu. Владелец: Google LLC. Дата публикации: 2022-07-07.

Quantum computation through reinforcement learning

Номер патента: EP4209971A1. Автор: Hartmut Neven,Vadim SMELYANSKIY,Sergio Boixo CASTRILLO,Yuezhen Niu. Владелец: Google LLC. Дата публикации: 2023-07-12.

Quantum computation through reinforcement learning

Номер патента: WO2019152020A1. Автор: Hartmut Neven,Vadim SMELYANSKIY,Sergio Boixo CASTRILLO,Yuezhen Niu. Владелец: Hartmut Neven. Дата публикации: 2019-08-08.

Distributional reinforcement learning using quantile function neural networks

Номер патента: WO2019155061A1. Автор: William Clinton Dabney,Georg Ostrovski. Владелец: DeepMind Technologies Limited. Дата публикации: 2019-08-15.

Exploration method based on reward decomposition in multi-agent reinforcement learning

Номер патента: US20240256885A1. Автор: Hyun Woo Kim,Ran HAN,Sungwon Yi,Euisok Chung,Jeongmin YANG,Hwajeon SONG,Byunghyun YOO. Владелец: Electronics and Telecommunications Research Institute ETRI. Дата публикации: 2024-08-01.

Model-based reinforcement learning

Номер патента: US20240320505A1. Автор: Devesh Upadhyay,Kaushik Balakrishnan,Neeloy Chakraborty. Владелец: FORD GLOBAL TECHNOLOGIES LLC. Дата публикации: 2024-09-26.

Multi-agent reinforcement learning with matchmaking policies

Номер патента: US20240370725A1. Автор: Oriol Vinyals,David Silver,Maxwell Elliot Jaderberg. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-11-07.

Quantum computation through reinforcement learning

Номер патента: AU2021203130A1. Автор: Hartmut Neven,Vadim SMELYANSKIY,Sergio Boixo CASTRILLO,Yuezhen Niu. Владелец: Google LLC. Дата публикации: 2021-06-10.

Reinforcement learning using an ensemble of discriminator models

Номер патента: US20240311639A1. Автор: Daniel Joseph Strouse,Steven Stenberg HANSEN. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-09-19.

A deep reinforcement learning method for generation of environmental features for vulnerability analysis and improved performance of computer vision systems

Номер патента: WO2021206761A1. Автор: Michael A. Warren,Christopher SERRANO. Владелец: HRL LABORATORIES, LLC. Дата публикации: 2021-10-14.

Deep Reinforcement Learning for Workflow Optimization

Номер патента: US20190325304A1. Автор: Vinicius Michel Gottin,Alex Laier Bordignon,Daniel Sadoc Menasché,Jonas F. Dias,Angelo Ernani Maia Ciarlini. Владелец: EMC IP Holding Co LLC. Дата публикации: 2019-10-24.

Weakly supervised reinforcement learning

Номер патента: US11809977B2. Автор: Bin Cheng,Jonathan Fuerst,Mauricio Fadel Argerich. Владелец: NEC Laboratories Europe GmbH. Дата публикации: 2023-11-07.

Deep reinforcement learning method for generation of environmental features for vulnerability analysis and improved performance of computer vision systems

Номер патента: US20210319313A1. Автор: Michael A. Warren,Christopher SERRANO. Владелец: HRL LABORATORIES LLC. Дата публикации: 2021-10-14.

Invertible-reasoning policy and reverse dynamics for causal reinforcement learning

Номер патента: WO2023167576A2. Автор: Jun Ho Park. Владелец: Jun Ho Park. Дата публикации: 2023-09-07.

Merkmalsextraktor für ein neuronales Netzwerk für Actor-Critic-Reinforcement-Learning-Modelle

Номер патента: DE102023210854A1. Автор: Christoph KROENER,Jeffrey Keating Thompson,Jared Evans. Владелец: ROBERT BOSCH GMBH. Дата публикации: 2024-05-02.

Reinforcement learning method and apparatus using task decomposition

Номер патента: US20230177348A1. Автор: Min Jong Yoo,Gwang Pyo YOO,Hong Uk WOO. Владелец: Sungkyunkwan University Research and Business Foundation. Дата публикации: 2023-06-08.

Neural network feature extractor for actor-critic reinforcement learning models

Номер патента: US20240143975A1. Автор: Christoph KROENER,Jared Evans. Владелец: ROBERT BOSCH GMBH. Дата публикации: 2024-05-02.

Training neural networks through reinforcement learning using standardized absolute deviations

Номер патента: US20240169211A1. Автор: Lei Yu,WANG Ling,Christopher James Dyer,Domenic Joseph Donato. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-05-23.

Systems and methods for end-to-end multi-agent reinforcement learning on a graphics processing unit

Номер патента: US20230237352A1. Автор: TIAN Lan,Sunil Srinivasa,Stephan Tao Zheng. Владелец: Salesforce com Inc. Дата публикации: 2023-07-27.

Memory-based reinforcement learning method for storing optional information in streaming data and system therefore

Номер патента: US11875119B2. Автор: Sung Ju Hwang,Minki KANG,Hyunwoo Jung,Moonsu Han. Владелец: Korea Advanced Institute of Science and Technology KAIST. Дата публикации: 2024-01-16.

Invertible-reasoning policy and reverse dynamics for causal reinforcement learning

Номер патента: WO2023167576A3. Автор: Jun Ho Park. Владелец: Jun Ho Park. Дата публикации: 2024-02-01.

Physical database design and tuning with deep reinforcement learning

Номер патента: US20210034588A1. Автор: Sanjay Nair,Douglas P. Brown,Frank Roderic Vandervort,Louis Martin Burger,Emiran Curtmola. Владелец: Teradata US Inc. Дата публикации: 2021-02-04.

Retrieval augmented reinforcement learning

Номер патента: EP4384953A1. Автор: Adria Puigdomenech BADIA,Charles BLUNDELL,Timothy Paul Lillicrap,Simon Osindero,Nan KE,Theophane Guillaume Weber,Andrea Banino,Anirudh GOYAL,Abram Luke FRIESEN. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-06-19.

Smoothed reward system transfer for actor-critic reinforcement learning models

Номер патента: US20240144023A1. Автор: Christoph KROENER,Jared Evans. Владелец: ROBERT BOSCH GMBH. Дата публикации: 2024-05-02.

Reinforcement learning using an ensemble of discriminator models

Номер патента: EP4305556A1. Автор: Daniel Joseph Strouse,Steven Stenberg HANSEN. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-01-17.

Removing unnecessary history from reinforcement learning state

Номер патента: US11928556B2. Автор: Boaz Carmeli,George Kour,Guy Hadash. Владелец: International Business Machines Corp. Дата публикации: 2024-03-12.

Distributional reinforcement learning using quantile function neural networks

Номер патента: US11887000B2. Автор: William Clinton Dabney,Georg Ostrovski. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-01-30.

Controlling reinforcement learning agents using geometric policy composition

Номер патента: WO2023144395A1. Автор: Remi MUNOS,William Clinton Dabney,Mark Daniel ROWLAND,Shantanu Yogeshraj THAKOOR,Andre da Motta Salles Barreto,Diana Luiza Borsa. Владелец: DeepMind Technologies Limited. Дата публикации: 2023-08-03.

Reinforcement learning with auxiliary tasks

Номер патента: US11842281B2. Автор: David Silver,Volodymyr Mnih,Koray Kavukcuoglu,Maxwell Elliot Jaderberg,Wojciech CZARNECKI,Tom Schaul. Владелец: DeepMind Technologies Ltd. Дата публикации: 2023-12-12.

Data-efficient reinforcement learning with adaptive return computation schemes

Номер патента: WO2024056891A1. Автор: Adria Puigdomenech BADIA,Steven James KAPTUROWSKI,Ray Jiang,Víctor CAMPOS CAMÚÑEZ,Nemanja RAKICEVIC. Владелец: DeepMind Technologies Limited. Дата публикации: 2024-03-21.

Method and system for operating a device by using hierarchical reinforcement learning

Номер патента: EP3992856A1. Автор: Martin Ringsquandl. Владелец: SIEMENS AG. Дата публикации: 2022-05-04.

Modeling bounded rationality in multi-agent simulations using rationally inattentive reinforcement learning

Номер патента: US20230107271A1. Автор: Tong Mu,Alexander Richard Trott,Stephan ZHENG. Владелец: Salesforce com Inc. Дата публикации: 2023-04-06.

Quantum computation through reinforcement learning

Номер патента: AU2022204185B2. Автор: Hartmut Neven,Vadim SMELYANSKIY,Sergio Boixo CASTRILLO,Yuezhen Niu. Владелец: Google LLC. Дата публикации: 2024-01-18.

Quantum computation through reinforcement learning

Номер патента: US11928586B2. Автор: Hartmut Neven,Vadim SMELYANSKIY,Sergio Boixo CASTRILLO,Yuezhen Niu. Владелец: Google LLC. Дата публикации: 2024-03-12.

Distributional reinforcement learning using quantile function neural networks

Номер патента: US20240135182A1. Автор: William Clinton Dabney,Georg Ostrovski. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-04-25.

Reinforcement learning with auxiliary tasks

Номер патента: US20210182688A1. Автор: David Silver,Volodymyr Mnih,Koray Kavukcuoglu,Maxwell Elliot Jaderberg,Wojciech CZARNECKI,Tom Schaul. Владелец: DeepMind Technologies Ltd. Дата публикации: 2021-06-17.

System and method for reinforcement learning based controlled natural language generation

Номер патента: US20210383074A1. Автор: Arjun Maheswaran,Akhilesh Sudhakar,Bhargav UPADHYAY. Владелец: PM Labs Inc. Дата публикации: 2021-12-09.

Reinforcement learning with auxiliary tasks

Номер патента: EP3535705A1. Автор: David Silver,Volodymyr Mnih,Koray Kavukcuoglu,Maxwell Elliot Jaderberg,Wojciech CZARNECKI,Tom Schaul. Владелец: DeepMind Technologies Ltd. Дата публикации: 2019-09-11.

Reinforcement learning with auxiliary tasks

Номер патента: US20240144015A1. Автор: David Silver,Volodymyr Mnih,Koray Kavukcuoglu,Maxwell Elliot Jaderberg,Wojciech CZARNECKI,Tom Schaul. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-05-02.

Distributed training of reinforcement learning systems

Номер патента: EP3254239A1. Автор: Mustafa SULEYMAN,David Silver,Samuel Blackwell,Volodymyr Mnih,Koray Kavukcuoglu,Vedavyas Panneershelvam,Praveen Deepak SRINIVASAN,Rory FEARON,Cagdas ALCICEK,Arun Sarath NAIR,Alessandro DE MARIA. Владелец: Google LLC. Дата публикации: 2017-12-13.

Apparatus for determining the number of layers of graph neural network by using reinforcement learning model, method for determining the number of layers of graph neural network by using reinforcement learning model, and recording medium storing instructions to perform method for determining the number of layers of graph neural network by using reinforcement learning model

Номер патента: US20240119299A1. Автор: Hee Soo JUNG,Hogun PARK. Владелец: Sungkyunkwan University Research and Business Foundation. Дата публикации: 2024-04-11.

Human skill learning by inverse reinforcement learning

Номер патента: US20240201677A1. Автор: Yu Zhao,Kaimeng Wang. Владелец: FANUC Corp. Дата публикации: 2024-06-20.

A method and system for implementing reinforcement learning agent using reinforcement learning processor

Номер патента: WO2018164740A1. Автор: Nagendra Nagaraja. Владелец: Alphaics Corporation. Дата публикации: 2018-09-13.

Training conditional computation neural networks using reinforcement learning

Номер патента: EP4384951A1. Автор: ARTHUR Mensch,Aidan Clark. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-06-19.

System and method for reinforcement learning of steering geometry

Номер патента: EP4263327A1. Автор: Chidambaram Subramanian. Владелец: Volvo Truck Corp. Дата публикации: 2023-10-25.

System and method for reinforcement learning of steering geometry

Номер патента: US20240017766A1. Автор: Chidambaram Subramanian. Владелец: Volvo Truck Corp. Дата публикации: 2024-01-18.

Training conditional computation neural networks using reinforcement learning

Номер патента: US20230177309A1. Автор: ARTHUR Mensch,Aidan Clark. Владелец: DeepMind Technologies Ltd. Дата публикации: 2023-06-08.

Training conditional computation neural networks using reinforcement learning

Номер патента: WO2023104879A1. Автор: ARTHUR Mensch,Aidan Clark. Владелец: DeepMind Technologies Limited. Дата публикации: 2023-06-15.

Method and system for generating synthetically accessible molecules with chemical reaction trajectories using reinforcement learning

Номер патента: WO2021044365A1. Автор: Julien HORWOOD,Emmanuel NOUTAHI. Владелец: 10736406 Canada Inc.. Дата публикации: 2021-03-11.

Multi-agent reinforcement learning pipeline ensemble

Номер патента: US20230237385A1. Автор: Long Vu,Lan Ngoc Hoang. Владелец: International Business Machines Corp. Дата публикации: 2023-07-27.

Processor for implementing reinforcement learning operations

Номер патента: US09754221B1. Автор: Nagendra Nagaraja. Владелец: Alphaics Corp. Дата публикации: 2017-09-05.

Training system and training method of reinforcement learning

Номер патента: US20220215288A1. Автор: Chieh-Lin CHUANG,Chi-Hsuan Lee,Chin-Feng Lai,Yen-I Ouyang,Cheng-Ping TSENG,Wei-Zhong HSU. Владелец: INSTITUTE FOR INFORMATION INDUSTRY. Дата публикации: 2022-07-07.

Method for combating stop-and-go wave problem using deep reinforcement learning based autonomous vehicles, recording medium and device for performing the method

Номер патента: US12091025B2. Автор: Dongsu LEE,Minhae KWON. Владелец: FOUNDATION OF SOONGSIL UNIVERSITY INDUSTRY COOPERATION. Дата публикации: 2024-09-17.

Optimizing deep learning recommender model data pipelines with reinforcement learning

Номер патента: WO2024220707A1. Автор: Lingyi Liu,Prasanna Padmanabhan,Kabir Nagrecha,Pablo A. Delgado Aqueveque. Владелец: NETFLIX, Inc.. Дата публикации: 2024-10-24.

System and method for uncertainty-based advice for deep reinforcement learning agents

Номер патента: CA3092161A1. Автор: Matthew Edmund TAYLOR,Bilal KARTAL,Pablo Francisco HERNANDEZ LEAL,Felipe Leno DA SILVA. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2021-03-05.

Systems and methods for reinforcement learning with local state and reward data

Номер патента: EP4392903A1. Автор: Hasham BURHANI,Xiao Qi SHI. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2024-07-03.

Reinforcement learning-based techniques for training a natural media agent

Номер патента: US20240037398A1. Автор: Chen Fang,Byungmoon Kim,Jonathan Brandt,Biao Jia. Владелец: Adobe Inc. Дата публикации: 2024-02-01.

Systems and methods for reinforcement learning with local state and reward data

Номер патента: CA3129295A1. Автор: Hasham BURHANI,Xiao Qi SHI. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-02-25.

Method for parameter adjustment of reinforcement learning algorithm

Номер патента: US20240265265A1. Автор: Taeho Lee,Minseop KIM,Songsub LEE. Владелец: MakinaRocks Co Ltd. Дата публикации: 2024-08-08.

Deep reinforcement learning with short-term adjustments

Номер патента: US20220012585A1. Автор: Chi Zhang,Chetan GUPTA,Susumu Serita,Hamed KHORASGANI. Владелец: HITACHI LTD. Дата публикации: 2022-01-13.

Erlernen einer menschlichen fähigkeit durch inverse reinforcement learning

Номер патента: DE102023131746A1. Автор: Yu Zhao,Kaimeng Wang. Владелец: FANUC Corp. Дата публикации: 2024-06-20.

Processor for implementing reinforcement learning operations

Номер патента: WO2018164716A1. Автор: Nagendra Nagaraja. Владелец: Alphaics Corporation. Дата публикации: 2018-09-13.

Learning method for learning action of agent using model-based reinforcement learning

Номер патента: US11651282B2. Автор: Masashi Okada. Владелец: Panasonic Intellectual Property Corp of America. Дата публикации: 2023-05-16.

Architecture for explainable reinforcement learning

Номер патента: US20220147876A1. Автор: Angelo Dalli,Mauro PIRRONE,Matthew GRECH. Владелец: Umnai Ltd. Дата публикации: 2022-05-12.

Architecture for explainable reinforcement learning

Номер патента: EP4244770A1. Автор: Angelo Dalli,Mauro PIRRONE,Matthew GRECH. Владелец: Umnai Ltd. Дата публикации: 2023-09-20.

Architecture for explainable reinforcement learning

Номер патента: WO2022101452A1. Автор: Angelo Dalli,Mauro PIRRONE,Matthew GRECH. Владелец: UMNAI Limited. Дата публикации: 2022-05-19.

Upside-down reinforcement learning

Номер патента: US20210089966A1. Автор: Juergen Schmidhuber,Rupesh Kumar SRIVASTAVA. Владелец: Nnaisense SA. Дата публикации: 2021-03-25.

Realistic safety verification for deep reinforcement learning

Номер патента: US20240211746A1. Автор: Taesung Lee,Jiyong Jang,Kevin Eykholt,Wenbo Guo. Владелец: International Business Machines Corp. Дата публикации: 2024-06-27.

Reinforcement learning and accumulators map-based pipeline for workload placement

Номер патента: US20220343150A1. Автор: Eduardo Vera Sousa,Ana Cristina Bernardo de Oliveira. Владелец: Credit Suisse AG Cayman Islands Branch. Дата публикации: 2022-10-27.

Reinforcement learning system

Номер патента: EP3839828A1. Автор: Marcin TOMCZAK,Peter VRANCX. Владелец: Secondmind Ltd. Дата публикации: 2021-06-23.

Deep reinforcement learning based method for surreptitiously generating signals to fool a recurrent neural network

Номер патента: US12073318B2. Автор: Michael A. Warren,Christopher SERRANO,Pape Sylla. Владелец: HRL LABORATORIES LLC. Дата публикации: 2024-08-27.

Reinforcement learning system

Номер патента: WO2021123235A1. Автор: Marcin TOMCZAK,Peter VRANCX. Владелец: SECONDMIND LIMITED. Дата публикации: 2021-06-24.

Reinforcement learning-based techniques for training a natural media agent

Номер патента: US11775817B2. Автор: Chen Fang,Byungmoon Kim,Jonathan Brandt,Biao Jia. Владелец: Adobe Inc. Дата публикации: 2023-10-03.

Sequential learning of constraints for hierarchical reinforcement learning

Номер патента: US20200034704A1. Автор: Ryuki Tachibana,Don Joven Ravoy Agravante,Tu-Hoa Pham,Giovanni De De Magistris. Владелец: International Business Machines Corp. Дата публикации: 2020-01-30.

System and method for deep reinforcement learning using clustered experience replay memory

Номер патента: US20200104714A1. Автор: Yong Jin Lee. Владелец: Electronics and Telecommunications Research Institute ETRI. Дата публикации: 2020-04-02.

System and method for uncertainty-based advice for deep reinforcement learning agents

Номер патента: US20210073912A1. Автор: Matthew Edmund TAYLOR,Bilal KARTAL,Pablo Francisco HERNANDEZ LEAL,Felipe Leno DA SILVA. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2021-03-11.

Reinforcement learning for active sequence processing

Номер патента: EP4042330A1. Автор: Bilal PIOT,Simon Osindero,Volodymyr Mnih,Viorica Patraucean,Joao CARREIRA. Владелец: DeepMind Technologies Ltd. Дата публикации: 2022-08-17.

Reinforcement learning for active sequence processing

Номер патента: WO2021094522A1. Автор: Bilal PIOT,Simon Osindero,Volodymyr Mnih,Viorica Patraucean,Joao CARREIRA. Владелец: DeepMind Technologies Limited. Дата публикации: 2021-05-20.

Systems and methods for reinforcement learning with local state and reward data

Номер патента: WO2023023844A1. Автор: Hasham BURHANI,Xiao Qi SHI. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-03-02.

Method for a state engineering for a reinforcement learning system, computer program product, and reinforcement learning system

Номер патента: US20240028873A1. Автор: Danielle TURNER,Sebastian Pol,Schirin BÄR. Владелец: Individual. Дата публикации: 2024-01-25.

Systems and Methods for Providing Reinforcement Learning in a Deep Learning System

Номер патента: US20200065672A1. Автор: Benjamin Van Roy,Ian David Moffat Osband. Владелец: Leland Stanford Junior University. Дата публикации: 2020-02-27.

Method for a state engineering for a reinforcement learning (rl) system, computer program product and rl system

Номер патента: EP4179468A1. Автор: Danielle TURNER,Sebastian Pol,Schirin BÄR. Владелец: SIEMENS AG. Дата публикации: 2023-05-17.

Apparatus and method for training reinforcement learning model for use in combinatorial optimization

Номер патента: US20210374604A1. Автор: Byoung Jip Kim,Jin Ho CHOO,Il Joo Yoon,Yeong Dae Kwon. Владелец: Samsung SDS Co Ltd. Дата публикации: 2021-12-02.

Unsupervised reinforcement learning method and apparatus based on Wasserstein distance

Номер патента: US11823062B1. Автор: Yuhang JIANG,Xiangyang Ji,Shuncheng He. Владелец: TSINGHUA UNIVERSITY. Дата публикации: 2023-11-21.

Reinforcement learning method and apparatus

Номер патента: US20230037632A1. Автор: Zhitang Chen,Furui LIU,Wenjing CUN. Владелец: Huawei Technologies Co Ltd. Дата публикации: 2023-02-09.

Reinforcement learning using epistemic value estimation

Номер патента: EP4398158A1. Автор: Simon Schmitt,Hado van Hasselt. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-07-10.

Tactical decision-making through reinforcement learning with uncertainty estimation

Номер патента: WO2021213616A1. Автор: Leo Laine,Carl-Johan HOEL. Владелец: VOLVO TRUCK CORPORATION. Дата публикации: 2021-10-28.

Methods and apparatuses for training a model based reinforcement learning model

Номер патента: WO2022248064A1. Автор: Vincent Huang,Jieqiang WEI,Doumitrou Daniil NIMARA,Mohammadreza MALEK MOHAMMADI. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2022-12-01.

Distributional reinforcement learning for continuous control tasks

Номер патента: US11948085B2. Автор: Gabriel BARTH-MARON,David BUDDEN,Matthew William HOFFMAN. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-04-02.

Verifying an action proposed by a reinforcement learning model

Номер патента: US20240249199A1. Автор: Wenfeng Hu,Jaeseong JEONG,Burak Demirel,Harshit TATED. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2024-07-25.

Value-based action selection algorithm in reinforcement learning

Номер патента: CA3241929A1. Автор: Hongyi Zhang,Jingya Li,Xingqin LIN,Zhiqiang Qi,Anders Aronsson,Jan Bosch,Helena Holmstroem OLSSON. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2023-07-20.

Method and device with reinforcement learning transferal

Номер патента: US20240273376A1. Автор: Gun Hee Kim,Minsu KO,Sungjoo Suh,Jae Kyeom KIM,Seo Hong PARK. Владелец: SAMSUNG ELECTRONICS CO LTD. Дата публикации: 2024-08-15.

Reinforcement learning using epistemic value estimation

Номер патента: US20240232642A1. Автор: Simon Schmitt,Hado Philip VAN HASSELT. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-07-11.

Uncertainty-directed training of a reinforcement learning agent for tactical decision-making

Номер патента: WO2021213617A1. Автор: Leo Laine,Carl-Johan HOEL. Владелец: VOLVO TRUCK CORPORATION. Дата публикации: 2021-10-28.

Precision landing for rockets using deep reinforcement learning

Номер патента: US11613384B2. Автор: Brian Haney. Владелец: Individual. Дата публикации: 2023-03-28.

Precision Landing for Rockets using Deep Reinforcement Learning

Номер патента: US20220234765A1. Автор: Brian Haney. Владелец: Individual. Дата публикации: 2022-07-28.

Systems and Methods for Simulating a Complex Reinforcement Learning Environment

Номер патента: US20230117499A1. Автор: Tze Way Eugene Ie,Sanmit Santosh Narvekar,Craig Edgar Boutilier. Владелец: Google LLC. Дата публикации: 2023-04-20.

Rank selection in tensor decomposition based on reinforcement learning for deep neural networks

Номер патента: US20210241094A1. Автор: Zhiyu Cheng,Baopu Li,Yingze Bao,Yanwen FAN. Владелец: Baidu com Times Technology Beijing Co Ltd. Дата публикации: 2021-08-05.

Systems and Methods for Simulating a Complex Reinforcement Learning Environment

Номер патента: US20200250575A1. Автор: Tze Way Eugene Ie,Sanmit Santosh Narvekar,Craig Edgar Boutilier. Владелец: Google LLC. Дата публикации: 2020-08-06.

Deep reinforcement learning for skill recommendation

Номер патента: US20230334308A1. Автор: Xiao Yan,Yiming Wang,Jaewon Yang,Yanen Li,Sufeng Niu,Chujie Zheng,Qidu He. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2023-10-19.

Hybrid reward architecture for reinforcement learning

Номер патента: EP3625731A1. Автор: Harm Hendrik VAN SEIJEN,Seyed Mehdi Fatemi Booshehri,Romain Michel Henri Laroche,Joshua Samuel Romoff. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2020-03-25.

A deep reinforcement learning based method for surreptitiously generating signals to fool a recurrent neural network

Номер патента: WO2021061266A1. Автор: Michael A. Warren,Christopher SERRANO,Pape Sylla. Владелец: HRL LABORATORIES, LLC. Дата публикации: 2021-04-01.

Deep reinforcement learning for skill recommendation

Номер патента: WO2023200546A1. Автор: Xiao Yan,Yiming Wang,Jaewon Yang,Yanen Li,Sufeng Niu,Chujie Zheng,Qidu He. Владелец: Microsoft Technology Licensing, LLC. Дата публикации: 2023-10-19.

Methods and systems that safely implement control policies within reinforcement-learning-based management-system agents

Номер патента: US20240046069A1. Автор: Marius VILCU,Asmitha Rathis,Peter Rudy,Aiswaryaa Venugopalan. Владелец: VMware LLC. Дата публикации: 2024-02-08.

Training server and method for generating a predictive model of a neural network through distributed reinforcement learning

Номер патента: EP3805996A1. Автор: Francois Gervais,Steve Lupien. Владелец: Distech Controls Inc. Дата публикации: 2021-04-14.

Training server and method for generating a predictive model of a neural network through distributed reinforcement learning

Номер патента: US20240086686A1. Автор: Francois Gervais,Steve Lupien. Владелец: Distech Controls Inc. Дата публикации: 2024-03-14.

Method for adaptive exploration to accelerate deep reinforcement learning

Номер патента: US11886988B2. Автор: Sakyasingha Dasgupta. Владелец: International Business Machines Corp. Дата публикации: 2024-01-30.

Distributional reinforcement learning for continuous control tasks

Номер патента: EP3688675A1. Автор: Gabriel BARTH-MARON,David BUDDEN,Matthew William HOFFMAN. Владелец: DeepMind Technologies Ltd. Дата публикации: 2020-08-05.

Neural model for reinforcement learning

Номер патента: EP2939187A1. Автор: Narayan Srinivasa,Corey M. THIBEAULT. Владелец: HRL LABORATORIES LLC. Дата публикации: 2015-11-04.

Reinforcement learning with scheduled auxiliary control

Номер патента: US11893480B1. Автор: Martin RIEDMILLER,Roland Hafner. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-02-06.

Training server and method for generating a predictive model of a neural network through distributed reinforcement learning

Номер патента: US11861482B2. Автор: Francois Gervais,Steve Lupien. Владелец: Distech Controls Inc. Дата публикации: 2024-01-02.

Agent control through in-context reinforcement learning

Номер патента: US20240104379A1. Автор: LUYU Wang,Volodymyr Mnih,Satinder Singh Baveja,Michael Laskin. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-03-28.

Method and apparatus for end-to-end task-oriented latent compression with deep reinforcement learning

Номер патента: WO2022146523A1. Автор: Wei Wang,Wei Jiang,Sheng Lin,Shan Liu. Владелец: Tencent America LLC. Дата публикации: 2022-07-07.

Method and apparatus for end-to-end task-oriented latent compression with deep reinforcement learning

Номер патента: US20220215265A1. Автор: Wei Wang,Wei Jiang,Sheng Lin,Shan Liu. Владелец: Tencent America LLC. Дата публикации: 2022-07-07.

Reinforcement learning with centralized inference and training

Номер патента: WO2021062226A1. Автор: Ke Wang,Lasse ESPEHOLT,Raphael Marinier,Marcin M. MICHALSKI,Piotr Michal STANCZYK. Владелец: Google LLC. Дата публикации: 2021-04-01.

Verifying an action proposed by a reinforcement learning model

Номер патента: EP4348504A1. Автор: Wenfeng Hu,Jaeseong JEONG,Burak Demirel,Harshit TATED. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2024-04-10.

Distributional reinforcement learning for continuous control tasks

Номер патента: US20230020071A1. Автор: Gabriel BARTH-MARON,David BUDDEN,Matthew William HOFFMAN. Владелец: DeepMind Technologies Ltd. Дата публикации: 2023-01-19.

Distributional reinforcement learning for continuous control tasks

Номер патента: US20230409907A1. Автор: Gabriel BARTH-MARON,David BUDDEN,Matthew William HOFFMAN. Владелец: DeepMind Technologies Ltd. Дата публикации: 2023-12-21.

Verifying an action proposed by a reinforcement learning model

Номер патента: WO2022248040A1. Автор: Wenfeng Hu,Jaeseong JEONG,Burak Demirel,Harshit TATED. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2022-12-01.

Value-based action selection algorithm in reinforcement learning

Номер патента: WO2023133816A1. Автор: Hongyi Zhang,Jingya Li,Xingqin LIN,Zhiqiang Qi,Anders Aronsson,Jan Bosch,Helena Holmstroem OLSSON. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2023-07-20.

Agent control through in-context reinforcement learning

Номер патента: WO2024068843A1. Автор: LUYU Wang,Volodymyr Mnih,Satinder Singh Baveja,Michael Laskin. Владелец: DeepMind Technologies Limited. Дата публикации: 2024-04-04.

Methods and apparatuses for training a model based reinforcement learning model

Номер патента: EP4348502A1. Автор: Vincent Huang,Jieqiang WEI,Doumitrou Daniil NIMARA,Mohammadreza MALEK MOHAMMADI. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2024-04-10.

Uncertainty-directed training of a reinforcement learning agent for tactical decision-making

Номер патента: US20230242144A1. Автор: Leo Laine,Carl-Johan HOEL. Владелец: VOLVO AUTONOMOUS SOLUTIONS AB. Дата публикации: 2023-08-03.

Tactical decision-making through reinforcement learning with uncertainty estimation

Номер патента: US20230142461A1. Автор: Leo Laine,Carl-Johan HOEL. Владелец: VOLVO AUTONOMOUS SOLUTIONS AB. Дата публикации: 2023-05-11.

Uncertainty-directed training of a reinforcement learning agent for tactical decision-making

Номер патента: EP4139845A1. Автор: Leo Laine,Carl-Johan HOEL. Владелец: VOLVO AUTONOMOUS SOLUTIONS AB. Дата публикации: 2023-03-01.

Process controller with meta-reinforcement learning

Номер патента: CA3151239A1. Автор: Daniel George Mcclement,Nathan Peron Lawrence,Philip Daniel Loewen,Ratna Bhushan Gopaluni,Michael Gregory Forbes. Владелец: Honeywell Ltd Canada. Дата публикации: 2022-09-15.

Readable and editable NPC behavior creation using reinforcement learning

Номер патента: US11534690B2. Автор: Yunqi Zhao,Navid Aghdaie,Meng Wu,Harold Chaput,Kazi Zaman,Qilian Yu. Владелец: Electronic Arts Inc. Дата публикации: 2022-12-27.

Method and system for performing negotiation task using reinforcement learning agents

Номер патента: US11521281B2. Автор: Arnab Chatterjee,Gautam Shroff,Lovekesh VIG,Vishal Sunder. Владелец: Tata Consultancy Services Ltd. Дата публикации: 2022-12-06.

Automated policy function adjustment using reinforcement learning algorithm

Номер патента: US20230298080A1. Автор: Changyao Chen,Amin Akbari,Tilman Drerup,Jonathan Gu,Nour Alkhatib. Владелец: Maplebear Inc. Дата публикации: 2023-09-21.

Adaptive learning system utilizing reinforcement learning to tune hyperparameters in machine learning techniques

Номер патента: WO2021118949A2. Автор: Thomas Triplet. Владелец: Ciena Corporation. Дата публикации: 2021-06-17.

Training strategy search using reinforcement learning

Номер патента: WO2021050600A3. Автор: DONG Yang,Ling Zhang,Daguang Xu,Te-Chung Isaac Yang,Holger Reinhard Roth,Ziyue Xu,Fausto Milletari. Владелец: NVIDIA CORPORATION. Дата публикации: 2021-04-15.

Training strategy search using reinforcement learning

Номер патента: WO2021050600A2. Автор: DONG Yang,Ling Zhang,Daguang Xu,Te-Chung Isaac Yang,Holger Reinhard Roth,Ziyue Xu,Fausto Milletari. Владелец: NVIDIA CORPORATION. Дата публикации: 2021-03-18.

Method and system for performing negotiation task using reinforcement learning agents

Номер патента: CA3049235A1. Автор: Arnab Chatterjee,Gautam Shroff,Lovekesh VIG,Vishal Sunder. Владелец: Tata Consultancy Services Ltd. Дата публикации: 2019-09-17.

Apparatus and method for accelerating deep neural network learning for deep reinforcement learning

Номер патента: US20230072432A1. Автор: Juhyoung Lee,Hoi Jun Yoo. Владелец: Korea Advanced Institute of Science and Technology KAIST. Дата публикации: 2023-03-09.

Reinforcement Learning Based Machine Retirement Planning and Management Apparatuses, Processes and Systems

Номер патента: US20230260034A1. Автор: Xiao Zhang,Jiayu LIU,Igor Halperin,Michael G. Caplan,Scott Kuldell. Владелец: FMR LLC. Дата публикации: 2023-08-17.

Method for determining an uncertainty level of deep reinforcement learning network and device implementing such method

Номер патента: US12036391B2. Автор: Maxime Louis. Владелец: Diabeloop SA. Дата публикации: 2024-07-16.

Reinforcement Learning Based Machine Asset Planning and Management Apparatuses, Processes and Systems

Номер патента: US20230222581A1. Автор: Xiao Zhang,Lisa L. Huang,Jiayu LIU,Igor Halperin. Владелец: FMR LLC. Дата публикации: 2023-07-13.

Reinforcement learning of interference-aware beam pattern design

Номер патента: WO2023219654A9. Автор: Yu Zhang,Ahmed ALKHATEEB. Владелец: Arizona Board of Regents on behalf of Arizona State University. Дата публикации: 2024-03-14.

Reinforcement learning of interference-aware beam pattern design

Номер патента: WO2023219654A2. Автор: Yu Zhang,Ahmed ALKHATEEB. Владелец: Arizona Board of Regents on behalf of Arizona State University. Дата публикации: 2023-11-16.

Understanding reinforcement learning policies by identifying strategic states

Номер патента: US20230419097A1. Автор: Miao Liu,Ronny Luss,Amit Dhurandhar. Владелец: International Business Machines Corp. Дата публикации: 2023-12-28.

Reinforcement learning of interference-aware beam pattern design

Номер патента: WO2023219654A3. Автор: Yu Zhang,Ahmed ALKHATEEB. Владелец: Arizona Board of Regents on behalf of Arizona State University. Дата публикации: 2024-04-18.

Method for determining an uncertainty level of deep reinforcement learning network and device implementing such method

Номер патента: US20240165330A1. Автор: Maxime Louis. Владелец: Diabeloop SA. Дата публикации: 2024-05-23.

Reinforcement learning-based label-free six-dimensional object pose prediction method and apparatus

Номер патента: US20230005181A1. Автор: Xiangyang Ji,Jianzhun SHAO. Владелец: TSINGHUA UNIVERSITY. Дата публикации: 2023-01-05.

Model-based reinforcement learning for behavior prediction in autonomous systems and applications

Номер патента: WO2022094624A1. Автор: David Nister,Julia NG,Rotem Aviv,Nikolai Smolyanskiy,Alexey Kamenev,Ollin BOER BOHAN,Ishwar Kulkarni,Fangkai YANG,Alperen DEGIRMENCI,Ruchi Bhargava,Lirui WANG. Владелец: NVIDIA CORPORATION. Дата публикации: 2022-05-05.

Method and apparatus for renewable energy allocation based on reinforcement learning

Номер патента: US11861702B2. Автор: Yu-Chieh Chuang,Wei-Yu Chiu. Владелец: National Tsing Hua University NTHU. Дата публикации: 2024-01-02.

Method and apparatus for renewable energy allocation based on reinforcement learning

Номер патента: US20220230243A1. Автор: Yu-Chieh Chuang,Wei-Yu Chiu. Владелец: National Tsing Hua University NTHU. Дата публикации: 2022-07-21.

Method for determining an uncertainty level of deep reinforcement learning network and device implementing such method

Номер патента: EP4376016A1. Автор: Maxime Louis. Владелец: Diabeloop SA. Дата публикации: 2024-05-29.

Method and apparatus for adaptive anti-jamming communications based on deep double-q reinforcement learning

Номер патента: US20220209885A1. Автор: Viet Hung Nguyen,Truong Xuan Do,Phan Khanh Ha Nguyen,Van Long Do. Владелец: VIETTEL GROUP. Дата публикации: 2022-06-30.

Training rate control neural networks through reinforcement learning

Номер патента: US20240267532A1. Автор: Julian SCHRITTWIESER,Miaosen Wang,Thomas Keisuke HUBERT,Chenjie Gu,Anton Zhernov,Daniel J. Mankowitz,Amol Balkishan MANDHANE,Mary Elizabeth RAUH. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-08-08.

Training rate control neural networks through reinforcement learning

Номер патента: AU2022279597B2. Автор: Julian SCHRITTWIESER,Miaosen Wang,Thomas Keisuke HUBERT,Chenjie Gu,Anton Zhernov,Daniel J. Mankowitz,Amol Balkishan MANDHANE,Mary Elizabeth RAUH. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-07-11.

Methods and apparatus for reinforcement learning

Номер патента: US09679258B2. Автор: Volodymyr Mnih,Koray Kavukcuoglu. Владелец: Google LLC. Дата публикации: 2017-06-13.

Artificial neural network compression via iterative hybrid reinforcement learning approach

Номер патента: WO2020176297A1. Автор: Gopal B. Avinash,Ravi Soni,Venkata Ratnam Saripalli,Jiahui Guan. Владелец: GE Precision Healthcare LLC. Дата публикации: 2020-09-03.

Graph convolutional reinforcement learning with heterogeneous agent groups

Номер патента: US20230185253A1. Автор: Arquimedes Martinez Canedo,Dmitriy Fradkin,Anton Kocheturov,Nikolay Borodinov. Владелец: Siemens Corp. Дата публикации: 2023-06-15.

Safe and fast exploration for reinforcement learning using constrained action manifolds

Номер патента: US11823039B2. Автор: Ryuki Tachibana,Asim Munawar,Tu-Hoa Pham,Giovanni De Magistris. Владелец: International Business Machines Corp. Дата публикации: 2023-11-21.

Active reinforcement learning for drilling optimization and automation

Номер патента: US11982171B2. Автор: Keshava Rangarajan,Srinath MADASU,Shashi DANDE,Raja Vikram R Pandya,Yashas Malur Saidutta. Владелец: Landmark Graphics Corp. Дата публикации: 2024-05-14.

Reinforcement learning based rate control

Номер патента: AU2020456664A1. Автор: BIN Li,Yan Lu,Ming-Chieh Lee,Jiahao Li,Mei-Hsuan Lu,W. Tom HOLCOMB,Andrey MEZENTSEV. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2023-01-05.

Reinforcement learning based rate control

Номер патента: US20230319292A1. Автор: BIN Li,Yan Lu,Ming-Chieh Lee,Jiahao Li,Mei-Hsuan Lu,Andrey MEZENTSEV,Tom W. HOLCOMB. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2023-10-05.

Graph convolutional reinforcement learning with heterogeneous agent groups

Номер патента: WO2021225879A3. Автор: Arquimedes Martinez Canedo,Dmitriy Fradkin,Anton Kocheturov,Nikolay Borodinov. Владелец: Siemens Corporation. Дата публикации: 2022-02-10.

Graph convolutional reinforcement learning with heterogeneous agent groups

Номер патента: EP4128049A2. Автор: Arquimedes Martinez Canedo,Dmitriy Fradkin,Anton Kocheturov,Nikolay Borodinov. Владелец: Siemens Corp. Дата публикации: 2023-02-08.

Reinforcement learning-enabled low-density parity check decoder

Номер патента: US11984910B1. Автор: Nedeljko Varnica,Di Fan,Xuanxuan Lu. Владелец: Marvell Asia Pte Ltd. Дата публикации: 2024-05-14.

Reinforcement learning based rate control

Номер патента: EP4173291A1. Автор: BIN Li,Yan Lu,Ming-Chieh Lee,Jiahao Li,Mei-Hsuan Lu,W. Tom HOLCOMB,Andrey MEZENTSEV. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2023-05-03.

Reinforcement learning based rate control

Номер патента: ZA202211950B. Автор: Li Bin,Lu Yan,Lu Mei-Hsuan,Lee Ming-Chieh,LI Jiahao,Tom Holcomb W,Mezentsev Andrey. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2024-04-24.

Method and apparatus for end-to-end neural compression with deep reinforcement learning

Номер патента: WO2022146508A1. Автор: Wei Wang,Wei Jiang,Sheng Lin,Shan Liu. Владелец: Tencent America LLC. Дата публикации: 2022-07-07.

End-to-end neural compression with deep reinforcement learning

Номер патента: US11917154B2. Автор: Wei Wang,Wei Jiang,Sheng Lin,Shan Liu. Владелец: Tencent America LLC. Дата публикации: 2024-02-27.

Neural model for reinforcement learning

Номер патента: US20140344202A1. Автор: Narayan Srinivasa,Corey M. THIBEAULT. Владелец: HRL LABORATORIES LLC. Дата публикации: 2014-11-20.

Adversarial reinforcement learning for procedural content generation and improved generalization

Номер патента: US11883746B2. Автор: Linus Mathias Gisslén,Andrew John Eakins. Владелец: Electronic Arts Inc. Дата публикации: 2024-01-30.

Deep reinforcement learning for field development planning optimization

Номер патента: US20220164657A1. Автор: Kainan WANG,Xian-Huan Wen,Chaoshun Hu,Meng Tang,Jincong He,Shusei TANAKA. Владелец: Chevron USA Inc. Дата публикации: 2022-05-26.

Training rate control neural networks through reinforcement learning

Номер патента: WO2022248736A1. Автор: Julian SCHRITTWIESER,Miaosen Wang,Thomas Keisuke HUBERT,Chenjie Gu,Anton Zhernov,Daniel J. Mankowitz,Amol Balkishan MANDHANE,Mary Elizabeth RAUH. Владелец: DeepMind Technologies Limited. Дата публикации: 2022-12-01.

End-to-end neural compression with deep reinforcement learning

Номер патента: US20240171743A1. Автор: Wei Wang,Wei Jiang,Sheng Lin,Shan Liu. Владелец: Tencent America LLC. Дата публикации: 2024-05-23.

Neural network reinforcement learning

Номер патента: US20180197079A1. Автор: Takayuki Osogami,Sakyasingha Dasgupta. Владелец: International Business Machines Corp. Дата публикации: 2018-07-12.

Training rate control neural networks through reinforcement learning

Номер патента: EP4289138A1. Автор: Julian SCHRITTWIESER,Miaosen Wang,Thomas Keisuke HUBERT,Chenjie Gu,Anton Zhernov,Daniel J. Mankowitz,Amol Balkishan MANDHANE,Mary Elizabeth RAUH. Владелец: DeepMind Technologies Ltd. Дата публикации: 2023-12-13.

Adversarial Reinforcement Learning for Procedural Content Generation and Improved Generalization

Номер патента: US20240017175A1. Автор: Linus Mathias Gisslén,Andrew John Eakins. Владелец: Electronic Arts Inc. Дата публикации: 2024-01-18.

Training rate control neural networks through reinforcement learning

Номер патента: CA3214193A1. Автор: Julian SCHRITTWIESER,Miaosen Wang,Thomas Keisuke HUBERT,Chenjie Gu,Anton Zhernov,Daniel J. Mankowitz,Amol Balkishan MANDHANE,Mary Elizabeth RAUH. Владелец: DeepMind Technologies Ltd. Дата публикации: 2022-12-01.

Training rate control neural networks through reinforcement learning

Номер патента: AU2022279597A1. Автор: Julian SCHRITTWIESER,Miaosen Wang,Thomas Keisuke HUBERT,Chenjie Gu,Anton Zhernov,Daniel J. Mankowitz,Amol Balkishan MANDHANE,Mary Elizabeth RAUH. Владелец: DeepMind Technologies Ltd. Дата публикации: 2023-10-05.

System and method of validating multi-vendor internet-of-things (iot) devices using reinforcement learning

Номер патента: US20210256318A1. Автор: Manjunath Ramachandra Iyer,Chandrashekar Bangalore Nagaraj,Shashidhar Soppin. Владелец: Wipro Ltd. Дата публикации: 2021-08-19.

Systems and methods for reinforcement learning with supplemented state data

Номер патента: EP4384950A1. Автор: Hasham BURHANI,Xiao Qi SHI. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2024-06-19.

Systems and methods for reinforcement learning with supplemented state data

Номер патента: US20230038434A1. Автор: Hasham BURHANI,Xiao Qi SHI. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-02-09.

Systems and methods for reinforcement learning with supplemented state data

Номер патента: WO2023015388A1. Автор: Hasham BURHANI,Xiao Qi SHI. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-02-16.

Systems and methods for reinforcement learning with supplemented state data

Номер патента: CA3129288A1. Автор: Hasham BURHANI,Xiao Qi SHI. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-02-09.

Mapping Workloads to Circuit Units in a Computing Device via Reinforcement Learning

Номер патента: US20230306272A1. Автор: Skyler Arron Windh,Patrick Alan Estep,Eugenio Culurciello,Andre Xian Ming Chang,Abhishek Chaurasia,Bashar Romanous,Parth Khopkar,Sheik Dawood Beer Mohideen. Владелец: Micron Technology Inc. Дата публикации: 2023-09-28.

Mapping workloads to circuit units in a computing device via reinforcement learning

Номер патента: WO2023183329A1. Автор: Skyler Arron Windh,Patrick Alan Estep,Eugenio Culurciello,Andre Xian Ming Chang,Abhishek Chaurasia,Bashar Romanous,Parth Khopkar,Sheik Dawood Beer Mohideen. Владелец: MICRON TECHNOLOGY, INC.. Дата публикации: 2023-09-28.

Method of rf analog circuits electronic design automation based on gcn and deep reinforcement learning

Номер патента: WO2023162449A1. Автор: Rui Ma,Weidong Cao,Mouhacine Benosman. Владелец: Mitsubishi Electric Corporation. Дата публикации: 2023-08-31.

Identification of molecular inhibitors using reinforcement learning and realtime docking of 3d structures

Номер патента: WO2023077124A1. Автор: Jie Li,Teresa HEAD-GORDON. Владелец: The Regents of the University of California. Дата публикации: 2023-05-04.

Automated software testing with reinforcement learning

Номер патента: WO2023219713A1. Автор: Xiaoyan Liu,Timothy James Chapman,Steve K. LIM,Taylor Paul SPANGLER,Kashyap Maheshkumar PATEL,Marc Mas MEZQUITA,Levent OZGUR. Владелец: Microsoft Technology Licensing, LLC. Дата публикации: 2023-11-16.

Systems and methods for unit test generation using reinforcement learning augmented transformer architectures

Номер патента: US20240078435A1. Автор: Georgios Papadopoulos,Sean Moran,Fanny SILAVONG,Rohan SAPHAL. Владелец: JPMorgan Chase Bank NA. Дата публикации: 2024-03-07.

Reinforcement learning based correction of timing failures

Номер патента: US20240232503A9. Автор: Manuel Beck,Simon Hermann Friedmann,Marvin von der Ehe,Gregor Boronowsky,Jan Niklas Stegmaier. Владелец: International Business Machines Corp. Дата публикации: 2024-07-11.

Reinforcement learning based group testing

Номер патента: US12066910B2. Автор: Caiming Xiong,Yingbo Zhou,Lav Raj Varshney,Govardana Sachithanandam Ramachandran. Владелец: Salesforce Inc. Дата публикации: 2024-08-20.

First node, computer system, second node and method performed thereby, for handling reinforcement learning in a computer system

Номер патента: WO2024100675A1. Автор: Saravanan M,Kaushik Dey,Perepu SATHEESH KUMAR. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2024-05-16.

Simulated training for reinforcement learning

Номер патента: WO2023219676A1. Автор: Xiaoyan Liu,Timothy James Chapman,Steve K. LIM,Taylor Paul SPANGLER,Kashyap Maheshkumar PATEL,Marc Mas MEZQUITA,Levent OZGUR. Владелец: Microsoft Technology Licensing, LLC. Дата публикации: 2023-11-16.

Reinforcement learning based correction of timing failures

Номер патента: US20240135083A1. Автор: Manuel Beck,Simon Hermann Friedmann,Marvin von der Ehe,Gregor Boronowsky,Jan Niklas Stegmaier. Владелец: International Business Machines Corp. Дата публикации: 2024-04-25.

Reinforcement learning based group testing

Номер патента: US20230113750A1. Автор: Caiming Xiong,Yingbo Zhou,Lav Raj Varshney,Govardana Sachithanandam Ramachandran. Владелец: Salesforce com Inc. Дата публикации: 2023-04-13.

Stepwise uncertainty-aware offline reinforcement learning under constraints

Номер патента: US20230185881A1. Автор: Takayuki Osogami,Akifumi Wachi. Владелец: International Business Machines Corp. Дата публикации: 2023-06-15.

Reinforcement learning under constraints

Номер патента: GB2627895A. Автор: Osogami Takayuki,Wachi Akifumi. Владелец: International Business Machines Corp. Дата публикации: 2024-09-04.

Reinforcement learning under constraints

Номер патента: WO2023111700A1. Автор: Takayuki Osogami,Akifumi Wachi. Владелец: Ibm Israel Science And Technology Ltd.. Дата публикации: 2023-06-22.

System and methods for coverage optimization of test generation program for cpu random verification using reinforcement learning

Номер патента: WO2022183143A3. Автор: Ning Yan,Robert Chu,Masood Seyed Mortazavi,Noah Lewis SHERRILL. Владелец: Huawei Technologies Co., Ltd.. Дата публикации: 2023-04-20.

Systems and methods for joint inter- and intra-slice orchestration using reinforcement learning

Номер патента: WO2024151189A1. Автор: Milad GANJALIZADEH,Marina Petrova,Johan HARALDSON,Hossein SHOKRI GHADIKOLAEI. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2024-07-18.

Dynamic intent-based network computing job assignment using reinforcement learning

Номер патента: US20230376783A1. Автор: Ting Wang,Philip JI,Zilong Ye. Владелец: NEC Laboratories America Inc. Дата публикации: 2023-11-23.

Training policy using distributional reinforcement learning and conditional value at risk

Номер патента: US20240330696A1. Автор: Takayuki Osogami,Lan Ngoc Hoang. Владелец: International Business Machines Corp. Дата публикации: 2024-10-03.

Dynamic intent-based network computing job assignment using reinforcement learning

Номер патента: WO2023225322A1. Автор: Ting Wang,Philip JI,Zilong Ye. Владелец: NEC Laboratories America, Inc.. Дата публикации: 2023-11-23.

Reinforcement Learning Method, Non-Transitory Computer Readable Recording Medium, Reinforcement Learning Device and Molding Machine

Номер патента: US20240227266A9. Автор: Takayuki Hirano. Владелец: Japan Steel Works Ltd. Дата публикации: 2024-07-11.

Distributed reinforcement learning system and distributed reinforcement learning method

Номер патента: US20230125834A1. Автор: Yasuhiro Fujita,Kota Uenishi. Владелец: Preferred Networks Inc. Дата публикации: 2023-04-27.

Reinforcement learning simulation of supply chain graph

Номер патента: WO2023069223A1. Автор: Ranveer Chandra,Vishal Jain,Peeyush Kumar,Hui Qing LI,Vaishnavi NATTAR RANGANATHAN,Lillian Jane RATLIFF,Michael McNab BASSANI,Jeremy Randall REYNOLDS. Владелец: Microsoft Technology Licensing, LLC.. Дата публикации: 2023-04-27.

Method for Training a Multi-Task Model Through Multi-Task Reinforcement Learning, Apparatus, Electronic Device, and Storage Medium

Номер патента: US20230347510A1. Автор: Wei Xu,Haichao Zhang,Lingfeng Sun. Владелец: Horizon Robotics Inc. Дата публикации: 2023-11-02.

Reinforcement learning simulation of supply chain graph

Номер патента: EP4420037A1. Автор: Ranveer Chandra,Vishal Jain,Peeyush Kumar,Hui Qing LI,Vaishnavi NATTAR RANGANATHAN,Lillian Jane RATLIFF,Michael McNab BASSANI,Jeremy Randall REYNOLDS. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2024-08-28.

T-cell receptor optimization with reinforcement learning and mutation policies for precision immunotherapy

Номер патента: US20230253068A1. Автор: Hans Peter Graf,Ziqi CHEN,Renqiang Min. Владелец: NEC Laboratories America Inc. Дата публикации: 2023-08-10.

Using inverse reinforcement learning in objective-aware traffic flow prediction

Номер патента: WO2024147107A1. Автор: Akram Bin SEDIQ,Hamza SOKUN,Raviraj ADVE,Hossein SHAFIEIRAD. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2024-07-11.

T-cell receptor optimization with reinforcement learning and mutation policies for precision immunotherapy

Номер патента: WO2023154162A1. Автор: Hans Peter Graf,Ziqi CHEN,Renqiang Min. Владелец: NEC Laboratories America, Inc.. Дата публикации: 2023-08-17.

Demonstration-driven reinforcement learning

Номер патента: EP4384949A1. Автор: Jonathan Karl Scholz,Oleg O. Sushkov,Todor Bozhinov DAVCHEV. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-06-19.

T-cell receptor optimization with reinforcement learning and mutation policies for precision immunotherapy

Номер патента: US20240177798A1. Автор: Hans Peter Graf,Ziqi CHEN,Renqiang Min. Владелец: NEC Laboratories America Inc. Дата публикации: 2024-05-30.

T-cell receptor optimization with reinforcement learning and mutation policies for precision immunotherapy

Номер патента: US20240177799A1. Автор: Hans Peter Graf,Ziqi CHEN,Renqiang Min. Владелец: NEC Laboratories America Inc. Дата публикации: 2024-05-30.

Reinforcement Learning Method, Non-Transitory Computer Readable Recording Medium, Reinforcement Learning Device and Molding Machine

Номер патента: US20240131765A1. Автор: Takayuki Hirano. Владелец: Japan Steel Works Ltd. Дата публикации: 2024-04-25.

Method for calibrating parameters of hydrology forecasting model based on deep reinforcement learning

Номер патента: US20230281459A1. Автор: Ye Zhang,Qiang Hu,Hexuan HU,Zhenyun HU. Владелец: Hohai University HHU. Дата публикации: 2023-09-07.

Method and apparatus for multiple reinforcement learning agents in a shared environment

Номер патента: US20230214725A1. Автор: Baochun Li,Fei Wang,Zhenhua Hu,Timothy James ZEYL,Salma Shukry Hussien Mohamed EMARA. Владелец: Huawei Cloud Computing Technologies Co Ltd. Дата публикации: 2023-07-06.

Multi-task offline reinforcement learning model based on skill regularized task decomposition and multi-task offline reinforcement learning method using the same

Номер патента: US20240185134A1. Автор: Sang Woo CHO,Min Jong Yoo,Hong Uk WOO. Владелец: Sungkyunkwan University Research and Business Foundation. Дата публикации: 2024-06-06.

Cavity filter tuning using imitation and reinforcement learning

Номер патента: WO2020242367A1. Автор: Xiaoyu LAN,Simon LINDSTÅHL. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2020-12-03.

System and method for robust optimization for trajectory-centric model-based reinforcement learning

Номер патента: EP3924884A1. Автор: Devesh Jha,Diego Romeres,Mouhacine Benosman,Arvind Raghunathan,Patrik KOLARIC. Владелец: Mitsubishi Electric Corp. Дата публикации: 2021-12-22.

Cavity filter tuning using imitation and reinforcement learning

Номер патента: US20220343141A1. Автор: Xiaoyu LAN,Simon LINDSTÅHL. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2022-10-27.

System and method for robust optimization for trajectory-centric model-based reinforcement learning

Номер патента: WO2021117845A1. Автор: Devesh Jha,Diego Romeres,Mouhacine Benosman,Arvind Raghunathan,Patrik KOLARIC. Владелец: Mitsubishi Electric Corporation. Дата публикации: 2021-06-17.

Cavity filter tuning using imitation and reinforcement learning

Номер патента: EP3977617A1. Автор: Xiaoyu LAN,Simon LINDSTÅHL. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2022-04-06.

Boosting deep reinforcement learning performance by combining off-line data and simulators

Номер патента: US20230107725A1. Автор: Haiyan Wang,Chetan GUPTA,Maria Teresa Gonzalez Diaz,Hamed KHORASGANI. Владелец: HITACHI LTD. Дата публикации: 2023-04-06.

Neural network reinforcement learning with diverse policies

Номер патента: EP4288905A1. Автор: Volodymyr Mnih,Tom Ben Zion Zahavy,Satinder Singh Baveja,Andre da Motta Salles Barreto,Brendan Timothy O'DONOGHUE,Johan Sebastian Flennerhag. Владелец: DeepMind Technologies Ltd. Дата публикации: 2023-12-13.

Reinforcement learning-based rate control for end-to-end neural network bsed video compression

Номер патента: WO2024064329A1. Автор: Fabien Racape,Hyomin CHOI,Ujwal DINESHA,Syed Mateen UL HAQ. Владелец: InterDigital VC Holdings, Inc.. Дата публикации: 2024-03-28.

T-cell receptor optimization with reinforcement learning and mutation policies for precision immunotherapy

Номер патента: US20240185948A1. Автор: Hans Peter Graf,Ziqi CHEN,Renqiang Min. Владелец: NEC Laboratories America Inc. Дата публикации: 2024-06-06.

Multi-task offline reinforcement learning model based on skill regularized task decomposition and multi-task offline reinforcement learning method using the same

Номер патента: EP4375885A1. Автор: Sang Woo CHO,Min Jong Yoo,Hong Uk WOO. Владелец: Sungkyunkwan University Research and Business Foundation. Дата публикации: 2024-05-29.

Methods and apparatuses of determining for controlling a multi-agent reinforcement learning environment

Номер патента: EP4268142A1. Автор: Kaushik Dey,Perepu SATHEESH KUMAR. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2023-11-01.

Methods and apparatuses of determining for controlling a multi-agent reinforcement learning environment

Номер патента: WO2022137244A1. Автор: SATHEESH KUMAR Perepu,DEY Kaushik. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2022-06-30.

Computing robust policies in offline reinforcement learning

Номер патента: US20230409957A1. Автор: Parikshit Ram,Radu Marinescu,Paulito Palmes,Tejaswini Pedapati,Djallel Bouneffouf. Владелец: International Business Machines Corp. Дата публикации: 2023-12-21.

Process controller with meta-reinforcement learning

Номер патента: EP4075337A1. Автор: Daniel George Mcclement,Nathan Peron Lawrence,Philip Daniel Loewen,Ratna Bhushan Gopaluni,Michael Gregory Forbes,Ulf Johan BACKSTRÖM. Владелец: Honeywell Ltd Canada. Дата публикации: 2022-10-19.

Neural network reinforcement learning with diverse policies

Номер патента: US20240104389A1. Автор: Volodymyr Mnih,Tom Ben Zion Zahavy,Satinder Singh Baveja,Andre da Motta Salles Barreto,Brendan Timothy O'DONOGHUE,Johan Sebastian Flennerhag. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-03-28.

Methods and apparatuses of determining for controlling a multi-agent reinforcement learning environment

Номер патента: US20240046111A1. Автор: Kaushik Dey,Perepu SATHEESH KUMAR. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2024-02-08.

Model-free reinforcement learning with regularized nash dynamics

Номер патента: WO2024003058A1. Автор: Bart DE VYLDER,Julien Perolat,Karl Paul TUYLS. Владелец: DeepMind Technologies Limited. Дата публикации: 2024-01-04.

Uncertainty-aware continuous control system based on reinforcement learning

Номер патента: US20240013090A1. Автор: Haiyan Wang,Chetan GUPTA,Takuya Kanazawa. Владелец: HITACHI LTD. Дата публикации: 2024-01-11.

Using Graph Structures to Represent Node State in Deep Reinforcement Learning (RL)-Based Decision Tree Construction

Номер патента: US20220335300A1. Автор: Yaniv BEN-ITZHAK,Shay Vargaftik,Ayal Taitler. Владелец: VMware LLC. Дата публикации: 2022-10-20.

Boosting deep reinforcement learning performance by combining off line data and simulators

Номер патента: EP4156024A1. Автор: Haiyan Wang,Chetan GUPTA,Maria Teresa Gonzalez Diaz,Hamed KHORASGANI. Владелец: HITACHI LTD. Дата публикации: 2023-03-29.

System and method for reinforcement learning based on prior trajectories

Номер патента: WO2024068785A1. Автор: Ankit Anand,Robert David FERGUS,Jacob BRUCE. Владелец: DeepMind Technologies Limited. Дата публикации: 2024-04-04.

Method and apparatus for training graph federated learning models using reinforcement learning-based data augmentation

Номер патента: US20240202492A1. Автор: Soyoung LEE,Hogun PARK. Владелец: Sungkyunkwan University Research and Business Foundation. Дата публикации: 2024-06-20.

Environment navigation using reinforcement learning

Номер патента: EP3523762B8. Автор: Laurent Sifre,Hubert Josef Soyer,Koray Kavukcuoglu,Razvan PASCANU,Raia Thais HADSELL,Misha Man Ray DENIL,Andrew James Ballard,Andrea Banino,Sudarshan Kumaran,Piotr Wojciech Mirowski,Fabio VIOLA,Rostislav GOROSHIN. Владелец: DeepMind Technologies Ltd. Дата публикации: 2024-08-14.

Closed loop model-based action learning with model-free inverse reinforcement learning

Номер патента: US20190385061A1. Автор: Ryuki Tachibana,Tadanobu Inoue,Daiki Kimura,Subhajit CHAUDHURY. Владелец: International Business Machines Corp. Дата публикации: 2019-12-19.

Optimal policy learning and recommendation for distribution task using deep reinforcement learning model

Номер патента: US12093805B2. Автор: Avinash Achar,Sanjay Purushottam Bhat,Easwara SUBRAMANIAN,Vignesh LAKSHMANAN KANGADHARAN PALANIRADJA. Владелец: Tata Consultancy Services Ltd. Дата публикации: 2024-09-17.

Data-aware storage tiering and lifetime data valuation for deep learning

Номер патента: US20240232607A9. Автор: Cong Xu,Suparna Bhattacharya,Martin Foltin,Ryan Beethe. Владелец: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP. Дата публикации: 2024-07-11.

Data-aware storage tiering and lifetime data valuation for deep learning

Номер патента: US20240135162A1. Автор: Cong Xu,Suparna Bhattacharya,Martin Foltin,Ryan Beethe. Владелец: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP. Дата публикации: 2024-04-25.

Automated software testing with reinforcement learning

Номер патента: US12066920B2. Автор: Xiaoyan Liu,Timothy James Chapman,Steve K. LIM,Taylor Paul SPANGLER,Kashyap Maheshkumar PATEL,Marc Mas MEZQUITA,Levent OZGUR. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2024-08-20.

Method for self-learning manufacturing scheduling training, computer program product and reinforcement learning system

Номер патента: US20230297088A1. Автор: Danielle TURNER,Sebastian Pol,Schirin BÄR,Felix Bär. Владелец: SIEMENS AG. Дата публикации: 2023-09-21.

Reinforcement learning system for self-learning manufacturing scheduling training

Номер патента: EP4176384A1. Автор: Danielle TURNER,Sebastian Pol,Schirin BÄR,Felix Bär. Владелец: SIEMENS AG. Дата публикации: 2023-05-10.

Reinforcement learning system for self-learning manufacturing scheduling training

Номер патента: WO2022042847A1. Автор: Danielle TURNER,Sebastian Pol,Schirin BÄR,Felix Bär. Владелец: SIEMENS AKTIENGESELLSCHAFT. Дата публикации: 2022-03-03.

Automated software testing with reinforcement learning

Номер патента: US20230367703A1. Автор: Xiaoyan Liu,Timothy James Chapman,Steve K. LIM,Taylor Paul SPANGLER,Kashyap Maheshkumar PATEL,Marc Mas MEZQUITA,Levent OZGUR. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2023-11-16.

General reinforcement learning framework for process monitoring and anomaly/ fault detection

Номер патента: US20240119342A1. Автор: SHU Xu,Mark J. Nixon. Владелец: Fisher Rosemount Systems Inc. Дата публикации: 2024-04-11.

A general reinforcement learning framework for process monitoring and anomaly/ fault detection

Номер патента: WO2024072729A1. Автор: SHU Xu,Mark J. Nixon. Владелец: FISHER-ROSEMOUNT SYSTEMS, INC.. Дата публикации: 2024-04-04.

System and method for multi-objective reinforcement learning

Номер патента: CA3195081A1. Автор: Zhuo Yu,Hongfeng Huang,Jacob CHMURA. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-10-05.

Computer vision systems and methods for object detection with reinforcement learning

Номер патента: US12067644B2. Автор: Maneesh Kumar SINGH,Sina Ditzel. Владелец: Insurance Services Office Inc. Дата публикации: 2024-08-20.

Reinforcement learning algorithm search

Номер патента: US20220391687A1. Автор: Quoc V. Le,Daiyi Peng,Sergey Vladimir Levine,Aleksandra Faust,Honglak LEE,Yingjie Miao,John Dalton Co-Reyes. Владелец: Google LLC. Дата публикации: 2022-12-08.

Enhanced reinforcement learning algorithms using future state prediction scaled reward values

Номер патента: US12019712B2. Автор: Emil Janulewicz,Sergio SLOBODRIAN. Владелец: Ciena Corp. Дата публикации: 2024-06-25.

Making a failure scenario using adversarial reinforcement learning background

Номер патента: US20210064915A1. Автор: Akifumi Wachi. Владелец: International Business Machines Corp. Дата публикации: 2021-03-04.

System and method for multi-objective reinforcement learning

Номер патента: US20230316088A1. Автор: Zhuo Yu,Hongfeng Huang,Jacob CHMURA. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-10-05.

System and method for multi-objective reinforcement learning

Номер патента: WO2023193097A1. Автор: Zhuo Yu,Hongfeng Huang,Jacob CHMURA. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-10-12.

System and method for multi-objective reinforcement learning

Номер патента: EP4261744A1. Автор: Zhuo Yu,Hongfeng Huang,Jacob CHMURA. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-10-18.

Learning reinforcement learning policies with local planning

Номер патента: WO2024156877A1. Автор: Dong Yin,Botao Hao,Sridhar THIAGARAJAN,Nevena LAZIC,Csaba SZEPESVARI. Владелец: DeepMind Technologies Limited. Дата публикации: 2024-08-02.

Deep q-network reinforcement learning for testing case selection and prioritization

Номер патента: US20210064515A1. Автор: JIANWU Xu,Haifeng Chen,Yuchen Bian. Владелец: NEC Laboratories America Inc. Дата публикации: 2021-03-04.

Data augmented training of reinforcement learning software agent

Номер патента: US11797820B2. Автор: Biplav Srivastava,Murray S. Campbell,Tathagata Chakraborti,Kartik Talamadupula,Kshitij Fadnis. Владелец: International Business Machines Corp. Дата публикации: 2023-10-24.

Reinforcement learning-based apparatus and method for generating random numbers

Номер патента: EP4040286A1. Автор: Kyung Min Kim,Sung Ju Park,Keun Jin Kim. Владелец: Spiceware Co Ltd. Дата публикации: 2022-08-10.

Data augmented training of reinforcement learning software agent

Номер патента: GB2607738A. Автор: Srivastava Biplav,Talamadupula Kartik,Chakraborti Tathagata,Fadnis Kshitij,Scott Campbell Murray. Владелец: International Business Machines Corp. Дата публикации: 2022-12-14.

Toolpath generation by reinforcement learning for computer aided manufacturing

Номер патента: US11782396B2. Автор: Akmal Ariff Bin Abu Bakar,David Patrick Lovell,Saaras Mehan. Владелец: Autodesk Inc. Дата публикации: 2023-10-10.

Hardware trojan detection using path delay based side-channel analysis and reinforcement learning

Номер патента: US11775693B1. Автор: Prabhat Kumar Mishra,Jennifer Marie Sheldon,Zhixin Pan. Владелец: University of Florida Research Foundation Inc. Дата публикации: 2023-10-03.

Toolpath generation by reinforcement learning for computer aided manufacturing

Номер патента: EP4325401A2. Автор: Akmal Ariff Bin Abu Bakar,David Patrick Lovell,Saaras Mehan. Владелец: Autodesk Inc. Дата публикации: 2024-02-21.

Toolpath generation by reinforcement learning for computer aided manufacturing

Номер патента: EP4168867A1. Автор: Akmal Ariff Bin Abu Bakar,David Patrick Lovell,Saaras Mehan. Владелец: Autodesk Inc. Дата публикации: 2023-04-26.

Toolpath generation by reinforcement learning for computer aided manufacturing

Номер патента: US20240061383A1. Автор: Akmal Ariff Bin Abu Bakar,David Patrick Lovell,Saaras Mehan. Владелец: Autodesk Inc. Дата публикации: 2024-02-22.

Toolpath generation by reinforcement learning for computer aided manufacturing

Номер патента: EP4325401A3. Автор: Akmal Ariff Bin Abu Bakar,David Patrick Lovell,Saaras Mehan. Владелец: Autodesk Inc. Дата публикации: 2024-05-22.

Toolpath generation by reinforcement learning for computer aided manufacturing

Номер патента: WO2021262413A1. Автор: Akmal Ariff Bin Abu Bakar,David Patrick Lovell,Mehan SAARAS. Владелец: AUTODESK, INC.. Дата публикации: 2021-12-30.

Computer Vision Systems and Methods for Object Detection with Reinforcement Learning

Номер патента: US20210182533A1. Автор: Maneesh Kumar SINGH,Sina Ditzel. Владелец: Insurance Services Office Inc. Дата публикации: 2021-06-17.

Reinforcement learning techniques to improve searching and/or to conserve computational and network resources

Номер патента: US20220043810A1. Автор: Thomas Deselaers,Sandro Feuz. Владелец: Google LLC. Дата публикации: 2022-02-10.

System and method for multi-agent reinforcement learning in a multi-agent environment

Номер патента: US11783232B2. Автор: Kikuo Fujimura,David F. ISELE,Anahita Mohseni-Kabir. Владелец: Honda Motor Co Ltd. Дата публикации: 2023-10-10.

System and method for multi-agent reinforcement learning in a multi-agent environment

Номер патента: US20230104513A1. Автор: Kikuo Fujimura,David F. ISELE,Anahita Mohseni-Kabir. Владелец: Honda Motor Co Ltd. Дата публикации: 2023-04-06.

Methods and Devices for Analyzing a Reinforcement Learning Agent Based on an Artificial Neural Network

Номер патента: US20230376782A1. Автор: Wojciech Turlej,Mateusz Orlowski,Nikodem Pankiewicz,Pawel KOWALCZYK. Владелец: Aptiv Technologies Ag. Дата публикации: 2023-11-23.

States simulator for reinforcement learning models

Номер патента: US20210081829A1. Автор: Michael Masin,Alexander Zadorojniy. Владелец: International Business Machines Corp. Дата публикации: 2021-03-18.

Apparatus and method for reinforcement learning based post-training sparsification

Номер патента: US20240289598A1. Автор: Xu Qian,Yuanyuan Li,Darren Crews. Владелец: Intel Corp. Дата публикации: 2024-08-29.

Uncertainty-aware deep reinforcement learning for anatomical landmark detection in medical images

Номер патента: US12039728B2. Автор: LI ZHANG,James Browning,Benjamin Odry,Richard Herzog,Micha KORNREICH,Jayashri PAWAR,Aubrey Chow. Владелец: Covera Health Inc. Дата публикации: 2024-07-16.

Reinforcement learning using confidence scores

Номер патента: US09536191B1. Автор: Itamar Arel,Khashayar Rohanimanesh,Michael Kahane. Владелец: Osaro Inc. Дата публикации: 2017-01-03.

States simulator for reinforcement learning models

Номер патента: EP4028959A1. Автор: Michael Masin,Alexander Zadorojniy. Владелец: International Business Machines Corp. Дата публикации: 2022-07-20.

Batched reinforcement learning

Номер патента: EP3616128A1. Автор: Danijar Hafner. Владелец: Google LLC. Дата публикации: 2020-03-04.

Device for generating verification vector for circuit design verification, circuit design system, and reinforcement learning method of the device and the circuit design system

Номер патента: US11861280B2. Автор: Kwang-Il Park,Tae-Ho Lee,Jeong-Hoon Ko,Youn-Sik Park,Seung-ju Kim,Chang-Wook Jeong,Joon-Wan Chai,Jun-Haeng Lee,Hyun-Sun Park,In HUH,Young-Min Oh,Hyo-Jin Choi. Владелец: SAMSUNG ELECTRONICS CO LTD. Дата публикации: 2024-01-02.

Deep Q-network reinforcement learning for testing case selection and prioritization

Номер патента: US11249887B2. Автор: JIANWU Xu,Haifeng Chen,Yuchen Bian. Владелец: NEC Corp. Дата публикации: 2022-02-15.

System and method for task control based on bayesian meta-reinforcement learning

Номер патента: WO2022121665A1. Автор: Zhiwei Qin,Yayi ZOU. Владелец: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.. Дата публикации: 2022-06-16.

Managing data stored in a cache using a reinforcement learning agent

Номер патента: US20230121843A1. Автор: Haoran Li,Pengcheng Li. Владелец: Alibaba Group Holding Ltd. Дата публикации: 2023-04-20.

Managing data stored in a cache using a reinforcement learning agent

Номер патента: WO2021253168A1. Автор: Haoran Li,Pengcheng Li. Владелец: ALIBABA GROUP HOLDING LIMITED. Дата публикации: 2021-12-23.

Reinforcement-learning based system for camera parameter tuning to improve analytics

Номер патента: WO2022256246A1. Автор: Srimat Chakradhar,Giuseppe Coviello,Murugan Sankaradas,Kunal Rao,Oliver Po,Sibendu PAUL. Владелец: NEC Laboratories America, Inc.. Дата публикации: 2022-12-08.

Device for generating verification vector for circuit design verification, circuit design system, and reinforcement learning method of the device and the circuit design system

Номер патента: US20240086603A1. Автор: Tae-Ho Lee,Jeong-Hoon Ko,Kwang-II Park,Youn-Sik Park,Seung-ju Kim,Chang-Wook Jeong,Joon-Wan Chai,Jun-Haeng Lee,Hyun-Sun Park,In HUH,Young-Min Oh,Hyo-Jin Choi. Владелец: SAMSUNG ELECTRONICS CO LTD. Дата публикации: 2024-03-14.

Approximate nearest neighbor searching strategy generating based on reinforcement learning

Номер патента: WO2020060605A1. Автор: Wei Li,QI Chen,Wei Luo,Jingdong Wang,Lintao Zhang,Gang Ren,Mingqin LI. Владелец: Microsoft Technology Licensing, LLC. Дата публикации: 2020-03-26.

Method for multi-time scale voltage quality control based on reinforcement learning in a power distribution network

Номер патента: US20220405633A1. Автор: Bin Wang,Qinglai Guo,Hongbin Sun,Wenchuan Wu,Haotian Liu. Владелец: TSINGHUA UNIVERSITY. Дата публикации: 2022-12-22.

Reinforcement learning for diverse content generation

Номер патента: US20230419187A1. Автор: Zhenwen Dai,Federico TOMASI,Joseph CAUTERUCCIO,Mehdi Ben Ayed. Владелец: SPOTIFY AB. Дата публикации: 2023-12-28.

States simulator for reinforcement learning models

Номер патента: WO2021047842A1. Автор: Michael Masin,Alexander Zadorojniy. Владелец: Ibm United Kingdom Limited. Дата публикации: 2021-03-18.

Reinforcement Learning Techniques for Automated Video Summarization

Номер патента: US20220156503A1. Автор: Viswanathan Swaminathan,Stefano Petrangeli,Hongxiang Gu. Владелец: Adobe Inc. Дата публикации: 2022-05-19.

Hybrid agent for parameter optimization using prediction and reinforcement learning

Номер патента: WO2023174630A1. Автор: Konstantinos Vandikas,Maxim TESLENKO,Wenfeng Hu,Alexandros NIKOU,Jaeseong JEONG. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2023-09-21.

Reinforcement learning systems for controlling wireless communication networks

Номер патента: WO2021069309A1. Автор: Martin Isaksson,Jaeseong JEONG,Lukas BJARRE. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2021-04-15.

A computer-implemented method and an apparatus for reinforcement learning

Номер патента: WO2023225941A1. Автор: Dong Yan,HANG Su,Jun Zhu,Xiaoqiang Wang,Chengyang YING,Zhongkai HAO,Xinning ZHOU. Владелец: ROBERT BOSCH GMBH. Дата публикации: 2023-11-30.

Distributed reinforcement learning on a gpu

Номер патента: WO2021247777A1. Автор: Robert J. Zigon. Владелец: Beckman Coulter, Inc.. Дата публикации: 2021-12-09.

Multi-agent reinforcement learning processes

Номер патента: WO2023232374A1. Автор: Konstantinos Vandikas,Klaus RAIZER,Hassam Riaz,Anil Ramachandran Nair. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2023-12-07.

Methods and devices for analyzing a reinforcement learning agent based on an artificial neural network

Номер патента: EP4280117A1. Автор: Wojciech Turlej,Mateusz Orlowski,Nikodem Pankiewicz,Pawel KOWALCZYK. Владелец: Aptiv Technologies Ltd. Дата публикации: 2023-11-22.

System and method for multi-objective reinforcement learning with gradient modulation

Номер патента: CA3198016A1. Автор: Zhuo Yu,Hongfeng Huang,Jacob CHMURA,Muhammad Mustajab AZAM. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-10-27.

System and method for multi-objective reinforcement learning with gradient modulation

Номер патента: EP4270256A1. Автор: Zhuo Yu,Hongfeng Huang,Jacob CHMURA,Muhammad Mustajab AZAM. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-11-01.

System and method for multi-objective reinforcement learning with gradient modulation

Номер патента: WO2023205891A1. Автор: Zhuo Yu,Hongfeng Huang,Jacob CHMURA,Muhammad Mustajab AZAM. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-11-02.

Reinforcement learning machine learning models for intervention recommendation

Номер патента: US20230252338A1. Автор: Raghav Bali,Swaroop S. Shekar,Rohan Khilnani,V. Kishore Ayyadevara,Joseph C. Cremaldi,Fritz T. Wilhelm,Vinod Burugupalli. Владелец: Optum Inc. Дата публикации: 2023-08-10.

System and method for multi-objective reinforcement learning with gradient modulation

Номер патента: US20230351201A1. Автор: Zhuo Yu,Hongfeng Huang,Jacob CHMURA,Muhammad Mustajab AZAM. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-11-02.

Method and device for reinforcement learning

Номер патента: US20230132482A1. Автор: Jan Peters,Melih Kandemir,Hamish Flynn. Владелец: ROBERT BOSCH GMBH. Дата публикации: 2023-05-04.

Adversarial attacks for improving cooperative multi-agent reinforcement learning systems

Номер патента: US20240119298A1. Автор: Jie Chen,Subhro Das,Thanh Lam Hoang,Lam Minh Nguyen,Nhan Huu Pham. Владелец: International Business Machines Corp. Дата публикации: 2024-04-11.

Generalized reinforcement learning agent

Номер патента: US20210097445A1. Автор: Cheng Zhang,Yingzhen Li,Sebastian TSCHIATSCHEK,Katja Hofmann,Sam Michael DEVLIN,Kamil Andrzej CIOSEK,Maximilian IGL. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2021-04-01.

Method and system for fairness-aware data valuation processing for supervised learning

Номер патента: EP4369257A1. Автор: Pedro dos Santos SALEIRO,Pedro Gustavo Santos Rodrigues Bizarro,José Maria Pereira Rosa Correia Pombal. Владелец: Feedzai Consultadoria e Inovacao Tecnologica SA. Дата публикации: 2024-05-15.

Method for fairness-aware data valuation processing for supervised learning

Номер патента: US20240169268A1. Автор: Pedro dos Santos SALEIRO,Pedro Gustavo Santos Rodrigues Bizarro,José Maria Pereira Rosa Correia Pombal. Владелец: Feedzai Consultadoria e Inovacao Tecnologica SA. Дата публикации: 2024-05-23.

Systems and methods for compression of deep learning model using reinforcement learning for low rank decomposition

Номер патента: WO2024159541A1. Автор: Yang Liu,Walid Mohamed Aly AHMED,Habib Hajimolahoseini,Mehdi Ahmadi,Gurpreet GOSAL,Shuangyue WEN,Kangling LIU. Владелец: Huawei Technologies Co., Ltd.. Дата публикации: 2024-08-08.

Generalized reinforcement learning agent

Номер патента: US11526812B2. Автор: Cheng Zhang,Yingzhen Li,Sebastian TSCHIATSCHEK,Katja Hofmann,Sam Michael DEVLIN,Kamil Andrzej CIOSEK,Maximilian IGL. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2022-12-13.

Generalized reinforcement learning agent

Номер патента: US20230111659A1. Автор: Cheng Zhang,Yingzhen Li,Sebastian TSCHIATSCHEK,Katja Hofmann,Sam Michael DEVLIN,Kamil Andrzej CIOSEK,Maximilian IGL. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2023-04-13.

Reinforcement learning for credit limit optimizer

Номер патента: US20230065404A1. Автор: Subarna ROY. Владелец: International Business Machines Corp. Дата публикации: 2023-03-02.

Apparatus and method for controlling traffic signals of traffic lights in sub-area by using reinforcement learning model

Номер патента: US20240013654A1. Автор: Seong Jin Lee,Jin Won YOON,Seung Eon BAEK. Владелец: Nota Inc. Дата публикации: 2024-01-11.

3D environment risks identification utilizing reinforced learning

Номер патента: AU2020218172A1. Автор: Bryan John Chasko. Владелец: Electronic Caregiver Inc. Дата публикации: 2021-08-12.

3D environment risks identification utilizing reinforced learning

Номер патента: US11791050B2. Автор: Bryan John Chasko. Владелец: Electronic Caregiver Inc. Дата публикации: 2023-10-17.

3d environment risks identification utilizing reinforced learning

Номер патента: WO2020163180A1. Автор: Bryan John Chasko. Владелец: Electronic Caregiver, Inc.. Дата публикации: 2020-08-13.

3d environment risks identification utilizing reinforced learning

Номер патента: EP3920797A1. Автор: Bryan John Chasko. Владелец: Electronic Caregiver Inc. Дата публикации: 2021-12-15.

Configuring a reinforcement learning agent based on relative feature contribution

Номер патента: EP4288904A1. Автор: Rafia Inam,Alberto HATA,Ahmad Ishtar TERRA,Ajay Kattepur,Hassam Riaz. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2023-12-13.

Deep reinforcement learning for robotic manipulation

Номер патента: EP3784451A1. Автор: Alexander Herzog,Eric Jang,Sergey LEVINE,Peter PASTOR SAMPEDRO,Alexander Irpan,Ethan Holly,Julian Ibarz,Dmitry Kalashnikov,Deirdre QUILLEN. Владелец: Google LLC. Дата публикации: 2021-03-03.

Solar energy management method and system using deep reinforcement learning

Номер патента: US20230350366A1. Автор: Dongjun Suh,Geonkyo Hong,Minjeong Sim. Владелец: Industry Academic Cooperation Foundation of KNU. Дата публикации: 2023-11-02.

Method for self-adaptive service function chain mapping based on deep reinforcement learning

Номер патента: US20230376748A1. Автор: Song Li,Jing Cheng,Xiao Zhang,Erlin TIAN,Wanwei HUANG,Weide LIANG,Zuhe Li. Владелец: Zhengzhou University of Light Industry. Дата публикации: 2023-11-23.

Reinforcement learning method, recording medium, and reinforcement learning apparatus

Номер патента: US20200234123A1. Автор: Hitoshi Yanami,Hidenao Iwane,Junichi Shigezumi. Владелец: Fujitsu Ltd. Дата публикации: 2020-07-23.

Reinforcement learning model for balanced unit recommendation

Номер патента: US20230196140A1. Автор: Lei DING,Yangyang Chu. Владелец: SAP SE. Дата публикации: 2023-06-22.

Trainieren eines reinforcement learning agenten zur steuerung eines autonomen systems

Номер патента: WO2022033746A1. Автор: Moritz Werling,Joschka Bödecker,Gabriel Kalweit,Maria Hügle. Владелец: Bayerische Motoren Werke Aktiengesellschaft. Дата публикации: 2022-02-17.

Use of episode attributes in reinforcement learning

Номер патента: US20240338568A1. Автор: Jacob White. Владелец: Wells Fargo Bank NA. Дата публикации: 2024-10-10.

Configuring a reinforcement learning agent based on relative feature contribution

Номер патента: US20240119300A1. Автор: Rafia Inam,Alberto HATA,Ahmad Ishtar TERRA,Ajay Kattepur,Hassam Riaz. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2024-04-11.

Secure exploration for reinforcement learning

Номер патента: US20230199031A1. Автор: Harm Hendrik VAN SEIJEN,Seyed Mehdi Fatemi Booshehri. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2023-06-22.

Inverse reinforcement learning with model predictive control

Номер патента: US11579575B2. Автор: Jinxin ZHAO,Liangjun ZHANG. Владелец: Baidu USA LLC. Дата публикации: 2023-02-14.

Apparatus and method for quantum multi-agent meta reinforcement learning

Номер патента: US20240104390A1. Автор: Joongheon Kim,Won Joon YUN. Владелец: KOREA UNIVERSITY RESEARCH AND BUSINESS FOUNDATION. Дата публикации: 2024-03-28.

Trade platform with reinforcement learning

Номер патента: US11715017B2. Автор: Shary MUDASSIR,Weiguang Ding,Hasham BURHANI,Xiao Qi SHI,Connor LAWLESS. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-08-01.

Trade platform with reinforcement learning

Номер патента: US20230342619A1. Автор: Shary MUDASSIR,Weiguang Ding,Hasham BURHANI,Xiao Qi SHI,Connor LAWLESS. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-10-26.

Multi-agent-based reinforcement learning system and method therefor

Номер патента: US20240046110A1. Автор: Dong Hoon Jeong,Byeong Wook Jeon,Hyung Seuk Ohn,Jung Hwan Bang,Won Seok Jeon,Ki Sang Kim,Dong Hoon Won,Hee Yeon Nah. Владелец: Kia Corp. Дата публикации: 2024-02-08.

Extraction of high-value sequential patterns using reinforcement learning techniques

Номер патента: US20240005146A1. Автор: Piyush Gupta,Nikaash Puri,Balaji Krishnamurthy,Pinkesh Badjatiya,Tanay Anand,Rachit BANSAL,Jayakumar SUBRAMANIAN,Chirag Singla,Anil Singh Parihar. Владелец: Delhi Technological University. Дата публикации: 2024-01-04.

Methods and systems to adapt pid coefficients through reinforcement learning

Номер патента: EP4314959A1. Автор: Fabrizio Santini,Peter Wurman,Varun KOMPELLA,James MACGLASHAN,Samuel Barrett,Goker ERDOGAN. Владелец: Sony Corp of America. Дата публикации: 2024-02-07.

Methods and systems to adapt pid coefficients through reinforcement learning

Номер патента: WO2022236195A1. Автор: Fabrizio Santini,Peter Wurman,Varun KOMPELLA,James MACGLASHAN,Samuel Barrett,Goker ERDOGAN. Владелец: SONY CORPORATION OF AMERICA. Дата публикации: 2022-11-10.

Reinforcement learning by sharing individual data within dynamic groups

Номер патента: US12026610B2. Автор: LI ZHANG,Zhi Hu Wang,Chun Yang Ma,Shiwan Zhao. Владелец: International Business Machines Corp. Дата публикации: 2024-07-02.

Positioning method and system for autonomous driving through long short-term memory (lstm)-based deep reinforcement learning (drl)

Номер патента: US20240174257A1. Автор: Bo Li,Shengli Xie,Kan Xie,Victor Fedorovich Kuzin,Zhenni Li,Ci CHEN,Haoli ZHAO. Владелец: GUANGDONG UNIVERSITY OF TECHNOLOGY. Дата публикации: 2024-05-30.

Reinforcement learning-based enhanced distributed channel access

Номер патента: US20240232679A9. Автор: George Cherian,Sai Yiu Duncan Ho,Yanjun SUN,Abhishek Pramod PATIL,Alfred ASTERJADHI,Abdel Karim AJAMI,Gaurang NAIK. Владелец: Qualcomm Inc. Дата публикации: 2024-07-11.

Reinforcement learning-based enhanced distributed channel access

Номер патента: WO2024085953A1. Автор: George Cherian,Sai Yiu Duncan Ho,Yanjun SUN,Abhishek Pramod PATIL,Alfred ASTERJADHI,Abdel Karim AJAMI,Gaurang NAIK. Владелец: QUALCOMM INCORPORATED. Дата публикации: 2024-04-25.

Data-efficient hierarchical reinforcement learning

Номер патента: US20240308068A1. Автор: Sergey LEVINE,Shixiang Gu,Honglak LEE. Владелец: Google LLC. Дата публикации: 2024-09-19.

Reinforcement learning-based enhanced distributed channel access

Номер патента: US20240135231A1. Автор: George Cherian,Sai Yiu Duncan Ho,Yanjun SUN,Abhishek Pramod PATIL,Alfred ASTERJADHI,Abdel Karim AJAMI,Gaurang NAIK. Владелец: Qualcomm Inc. Дата публикации: 2024-04-25.

Method and system for deep reinforcement learning (drl) based scheduling in a wireless system

Номер патента: WO2022010409A1. Автор: Soma TAYAMON,Vidit SAXENA,Euhanna GHADIMI,Jakob Stigenberg. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2022-01-13.

Meta-reinforcement learning gradient estimation with variance reduction

Номер патента: US11922323B2. Автор: HAO LIU. Владелец: Salesforce Inc. Дата публикации: 2024-03-05.

Secure exploration for reinforcement learning

Номер патента: US20200076857A1. Автор: Harm Hendrik VAN SEIJEN,Seyed Mehdi Fatemi Booshehri. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2020-03-05.

Deep reinforcement learning based models for hard-exploration problems

Номер патента: US11829870B2. Автор: Joel Anthony Lehman,Kenneth Owen Stanley,Jeffrey Michael Clune,Adrien Lucas Ecoffet,Joost Huizinga. Владелец: Uber Technologies Inc. Дата публикации: 2023-11-28.

Method and system for modeling personalized car-following driving styles with model-free inverse reinforcement learning

Номер патента: US20240124003A1. Автор: Rohit Gupta,Ziran Wang,Kyungtae Han. Владелец: Toyota Motor Engineering and Manufacturing North America Inc. Дата публикации: 2024-04-18.

Reinforcement learning-based electric vehicle charging method and system

Номер патента: US20210300198A1. Автор: YeonHo Choi,Yeonjung KIM,Junghwa Choi,Minkook KIM,Kyungyul KIM,Sungyong YOON. Владелец: LG ELECTRONICS INC. Дата публикации: 2021-09-30.

Kalman filter and deep reinforcement learning based wind turbine yaw misalignment control method

Номер патента: WO2022146058A1. Автор: Inwoo CHUNG. Владелец: Chung Inwoo. Дата публикации: 2022-07-07.

A method for efficient and scalable training of reinforcement learning agents based on evolutionary computation

Номер патента: WO2023222248A1. Автор: Alexandros NIKOU,Marios DAOUTIS,Anirudh Seth. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2023-11-23.

Training a Reinforcement Learning Agent to Control an Autonomous System

Номер патента: US20240037447A1. Автор: Moritz Werling,Joschka BOEDECKER,Maria HUEGLE,Gabriel Kalweit. Владелец: Bayerische Motoren Werke AG. Дата публикации: 2024-02-01.

Kalman filter and deep reinforcement learning based wind turbine yaw misalignment control method

Номер патента: US20240052804A1. Автор: Inwoo CHUNG. Владелец: Individual. Дата публикации: 2024-02-15.

Reinforcement learning to train a character using disparate target animation data

Номер патента: WO2020190415A1. Автор: Michael Taylor. Владелец: Sony Interactive Entertainment Inc.. Дата публикации: 2020-09-24.

Devices and methods for reinforcement learning visualization using immersive environments

Номер патента: US20210034974A1. Автор: Frank Maurer,Matthew Edmund TAYLOR,Bilal KARTAL,Pablo Francisco HERNANDEZ LEAL,Nathan DOUGLAS,Dianna YIM. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2021-02-04.

Enhancing package formation in a food packaging system based on reinforcement learning

Номер патента: EP4263363A1. Автор: Gabriele Borelli,Stefano FORNASARI. Владелец: Tetra Laval Holdings and Finance SA. Дата публикации: 2023-10-25.

Performing web tensioning adjustments in a food packaging system based on reinforcement learning

Номер патента: EP4263403A1. Автор: Gabriele Borelli,Stefano FORNASARI. Владелец: Tetra Laval Holdings and Finance SA. Дата публикации: 2023-10-25.

Method and system for deep reinforcement learning (drl) based scheduling in a wireless system

Номер патента: US20230262683A1. Автор: Soma TAYAMON,Vidit SAXENA,Euhanna GHADIMI,Jakob Stigenberg. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2023-08-17.

System and method for constructing molecular reaction force field based on reinforcement learning

Номер патента: LU501574B1. Автор: Xiangying Meng. Владелец: Univ Northeastern. Дата публикации: 2022-09-01.

Data-efficient hierarchical reinforcement learning

Номер патента: EP3793784A1. Автор: Sergey LEVINE,Shixiang Gu,Honglak LEE. Владелец: Google LLC. Дата публикации: 2021-03-24.

Enhancing package formation in a food packaging system based on reinforcement learning

Номер патента: US20240067376A1. Автор: Gabriele Borelli,Stefano FORNASARI. Владелец: Tetra Laval Holdings and Finance SA. Дата публикации: 2024-02-29.

Performing web tensioning adjustments in a food packaging system based on reinforcement learning

Номер патента: US20240059442A1. Автор: Gabriele Borelli,Stefano FORNASARI. Владелец: Tetra Laval Holdings and Finance SA. Дата публикации: 2024-02-22.

Data-efficient hierarchical reinforcement learning

Номер патента: US11992944B2. Автор: Sergey LEVINE,Shixiang Gu,Honglak LEE. Владелец: Google LLC. Дата публикации: 2024-05-28.

Data-efficient hierarchical reinforcement learning

Номер патента: WO2019222634A1. Автор: Sergey LEVINE,Shixiang Gu,Honglak LEE. Владелец: Google LLC. Дата публикации: 2019-11-21.

Reinforcement learning to train a character using disparate target animation data

Номер патента: EP3939010A1. Автор: Michael Taylor. Владелец: Sony Interactive Entertainment Inc. Дата публикации: 2022-01-19.

Reinforcement learning to train a character using disparate target animation data

Номер патента: US20200293881A1. Автор: Michael Taylor. Владелец: Sony Interactive Entertainment Inc. Дата публикации: 2020-09-17.

Method and system for deep reinforcement learning (drl) based scheduling in a wireless system

Номер патента: EP4179824A1. Автор: Soma TAYAMON,Vidit SAXENA,Euhanna GHADIMI,Jakob Stigenberg. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2023-05-17.

Method and system for implementing reinforcement learning agent using reinforcement learning processor

Номер патента: US20180260700A1. Автор: Nagendra Nagaraja. Владелец: Alphaics Corp. Дата публикации: 2018-09-13.

Training strategy search using reinforcement learning

Номер патента: GB2601946B. Автор: Yang Dong,Zhang Ling,Xu Ziyue,Xu Daguang,Milletari Fausto,Reinhard Roth Holger,Isaac Yang Te-Chung. Владелец: Nvidia Corp. Дата публикации: 2024-06-26.

MULTI-CHILLER SCHEDULING USING REINFORCEMENT LEARNING WITH TRANSFER LEARNING FOR POWER CONSUMPTION PREDICTION

Номер патента: US20210303998A1. Автор: NAGARATHINAM Srinarayana,Vasan Arunchandar,MANOHARAN Praveen,POONI VENKAT Malini. Владелец: TATA CONSULTANCY SERVICES LIMITED. Дата публикации: 2021-09-30.

System for providing carom billards guidance service using reinforcement learning of deep learning model

Номер патента: KR102315842B1. Автор: 김종우. Владелец: 김종우. Дата публикации: 2021-10-21.

Noisy text prediction in large volume clinical data using reinforcement learning

Номер патента: AU2020103756A4. Автор: RAMESH Kumar,Swati Sharma,Sathishkumar K.,G. Nalinipriya,G. Naga Rama Devi,Aradhana Behura,Rainu Nandal,Ajay Pratap,Bottu Gurunadha Rao,V. Lokeswara Reddy. Владелец: Individual. Дата публикации: 2021-02-11.

Hardware trojan detection using reinforcement learning

Номер патента: US20220188415A1. Автор: Prabhat Kumar Mishra,Zhixin Pan. Владелец: University of Florida Research Foundation Inc. Дата публикации: 2022-06-16.

Hardware trojan detection using reinforcement learning

Номер патента: US12079334B2. Автор: Prabhat Kumar Mishra,Zhixin Pan. Владелец: University of Florida Research Foundation Inc. Дата публикации: 2024-09-03.

Media for generating fast counterfactual explanations using reinforcement learning

Номер патента: US12033088B1. Автор: Keegan Hines,John Dickerson,Sahil Verma. Владелец: Arthur Ai Inc. Дата публикации: 2024-07-09.

Systems and methods for agent-based error resolution in private cloud application using reinforcement learning and chaos experiments

Номер патента: US20230252326A1. Автор: Bryan ZAKE,Pihu SHARMA,Taylor Haoyu XU,Aparajita RANA,Alexandra LACHMANN. Владелец: JPMorgan Chase Bank NA. Дата публикации: 2023-08-10.

Scene grammar based reinforcement learning in agent training

Номер патента: US20220058510A1. Автор: Robert P. Dooley,Dylan James Snow. Владелец: Accenture Global Solutions Ltd. Дата публикации: 2022-02-24.

Methods and apparatus for generating fast counterfactual explanations for black-box models using reinforcement learning

Номер патента: US11403538B1. Автор: Keegan Hines,John Dickerson,Sahil Verma. Владелец: Arthur Ai Inc. Дата публикации: 2022-08-02.

Reinforcement learning apparatus and method based on user learning environment

Номер патента: US20230088699A1. Автор: Sung Min Lee,Dong Hyun Lee,Won Young Cho,Ye Rin MIN,Yeon Sang YU,Ba Da KIM. Владелец: Agilesoda Inc. Дата публикации: 2023-03-23.

Method and system for designing circuit based on reinforcement learning

Номер патента: US20240220701A1. Автор: Taehyun Kim,Hyunjoong Kim,Jichull Jeong,Euihyun Cheon. Владелец: SAMSUNG ELECTRONICS CO LTD. Дата публикации: 2024-07-04.

Einrichtung und computerimplementiertes Verfahren zum Bereitstellen von Trainingsdaten für einen Reinforcement-Learning-Agenten zum Erzeugen einer Strategie, die zum Steuern eines Fahrzeugs ausgelegt ist, Einrichtung und Verfahren zum Erzeugen einer Strategie, die zum Steuern eines Fahrzeugs ausgelegt ist, und Fahrzeug

Номер патента: DE102022202689A1. Автор: Dotan Di Castro,Chana Ross,Yakov Miron. Владелец: ROBERT BOSCH GMBH. Дата публикации: 2023-09-21.

Systems and methods for adaptive digital reinforcement learning

Номер патента: US20230351038A1. Автор: Patrick Faga. Владелец: Firstwork LLC. Дата публикации: 2023-11-02.

Real-time real-world reinforcement learning systems and methods

Номер патента: EP3824358A1. Автор: Dmytro Korenkevych,Ashique Rupam MAHMOOD,Brent J. KOMER. Владелец: Kindred Systems Inc. Дата публикации: 2021-05-26.

Real-time real-world reinforcement learning systems and methods

Номер патента: US12005578B2. Автор: Dmytro Korenkevych,Ashique Rupam MAHMOOD,Brent J. KOMER. Владелец: Ocado Innovations Ltd. Дата публикации: 2024-06-11.

Reinforcement learning techniques for selecting a software policy network and autonomously controlling a corresponding software client based on selected policy network

Номер патента: US20210334628A1. Автор: Thomas Deselaers,Victor Carbune. Владелец: Google LLC. Дата публикации: 2021-10-28.

Performing network congestion control utilizing reinforcement learning

Номер патента: GB2603852A. Автор: Mannor Shie,Shpigelman Yuval,Mandelbaum Amit,Tessler Chen,Dalal Gal,Kazakov Doron,Fuhrer Benjamin. Владелец: Nvidia Corp. Дата публикации: 2022-08-17.

Performing network congestion control utilizing reinforcement learning

Номер патента: US20230041242A1. Автор: Yuval Shpigelman,Shie Mannor,Gal Dalal,Amit Mandelbaum,Benjamin Fuhrer,Chen Tessler,Doron Kazakov. Владелец: Nvidia Corp. Дата публикации: 2023-02-09.

Reinforcement learning with multiple objectives and tradeoffs

Номер патента: US20240232682A9. Автор: Parikshit Ram,Radu Marinescu,Paulito Palmes,Tejaswini Pedapati,Djallel Bouneffouf. Владелец: International Business Machines Corp. Дата публикации: 2024-07-11.

Reinforcement learning with multiple objectives and tradeoffs

Номер патента: US20240135234A1. Автор: Parikshit Ram,Radu Marinescu,Paulito Palmes,Tejaswini Pedapati,Djallel Bouneffouf. Владелец: International Business Machines Corp. Дата публикации: 2024-04-25.

Deep reinforcement learning intelligent decision-making platform based on unified artificial intelligence framework

Номер патента: US20240338570A1. Автор: Lu Ren,Changyin Sun,Wenzhang LIU,Chaoxu MU,Zhuoran SHI. Владелец: ANHUI UNIVERSITY. Дата публикации: 2024-10-10.

Method for exploration based on curiosity and prioritization of experience data in multi-agent reinforcement learning

Номер патента: US20220215204A1. Автор: Hyun Woo Kim,Sungwon Yi,Hwa Jeon Song,Byung Hyun Yoo,Ningombam Devarani Devi. Владелец: Electronics and Telecommunications Research Institute ETRI. Дата публикации: 2022-07-07.

Reinforced generation: reinforcement learning for text and knowledge graph bi-directional generation using pretrained language models

Номер патента: US20240070404A1. Автор: Payel Das,Inkit Padhi,Igor Melnyk,Pierre L. Dognin. Владелец: International Business Machines Corp. Дата публикации: 2024-02-29.

Method and apparatus for porting entity on reinforcement learning system

Номер патента: US20220164706A1. Автор: Hong Seok Jeon,Seung Jae Shin. Владелец: Electronics and Telecommunications Research Institute ETRI. Дата публикации: 2022-05-26.

Method for optimizing resource allocation basedon prediction with reinforcement learning

Номер патента: US20230267006A1. Автор: Ming-Jye Sheu,Henry H. Tzeng,Wen-Shyen Chen. Владелец: PROPHETSTOR DATA SERVICES Inc. Дата публикации: 2023-08-24.

Device and method for training a control strategy with the aid of reinforcement learning

Номер патента: US20220146997A1. Автор: Daria Stepanova,Felix Milo Richter,Johannes Oetsch,Nysret Musliu,Thomas Eiter. Владелец: ROBERT BOSCH GMBH. Дата публикации: 2022-05-12.

Automated generation of agent configurations for reinforcement learning

Номер патента: WO2023129340A1. Автор: Marco Rossi. Владелец: Microsoft Technology Licensing, LLC.. Дата публикации: 2023-07-06.

Methods and systems for using reinforcement learning for promotions

Номер патента: US20220253896A1. Автор: Vincent Francois Faber,Arun Karthik Ravindran,Victor Kostyuk. Владелец: Boston Consulting Group Inc. Дата публикации: 2022-08-11.

Quantum circuit mapping using reinforcement learning techniques

Номер патента: US20240330730A1. Автор: Yunong Shi,Yiheng Duan. Владелец: Amazon Technologies Inc. Дата публикации: 2024-10-03.

Method and computing system for molecular design via multi-task reinforcement learning

Номер патента: EP4152336A1. Автор: Reda ALAMI,Zhenwei Dai,Cécile PEREIRA,Diego PANTANO,Mauricio ARAYA,Denis AKHIYAROV. Владелец: TotalEnergies Onetech SAS. Дата публикации: 2023-03-22.

Method for using reinforcement learning to optimize order fulfillment

Номер патента: WO2024028839A1. Автор: Raja RAMNARAYAN,Matthew Haley,Sunil Nakrani,Francisco Arzu. Владелец: Dematic Corp.. Дата публикации: 2024-02-08.

Method for using reinforcement learning to optimize order fulfillment

Номер патента: US20240046204A1. Автор: Raja RAMNARAYAN,Matthew Haley,Sunil Nakrani,Francisco Arzu. Владелец: Dematic Corp. Дата публикации: 2024-02-08.

System and method for optimizing communication operations using reinforcement learing

Номер патента: WO2018126286A1. Автор: Alan McCord. Владелец: Newvoicemedia Us Inc.. Дата публикации: 2018-07-05.

Systems and methods for efficiently implementing hierarchial states in machine learning models using reinforcement learning

Номер патента: US20240028948A1. Автор: James Brennan WORTH. Владелец: Substrate AL Spain SL. Дата публикации: 2024-01-25.

Reinforcement learning for continued learning of optimal battery charging

Номер патента: US20240144078A1. Автор: Nikhil Ravi,Reinhardt Klein,Christoph KROENER,Jared Evans. Владелец: ROBERT BOSCH GMBH. Дата публикации: 2024-05-02.

Optimizing deep learning recommender model data pipelines with reinforcement learning

Номер патента: US20240354585A1. Автор: Lingyi Liu,Prasanna Padmanabhan,Kabir Nagrecha,Pablo A. Delgado Aqueveque. Владелец: Netflix Inc. Дата публикации: 2024-10-24.

Systems and methods for real-time reinforcement learning

Номер патента: US20240249198A1. Автор: Francois Chabot. Владелец: Ai Redefined Inc. Дата публикации: 2024-07-25.

Systems and methods for real-time reinforcement learning

Номер патента: CA3218649A1. Автор: Francois Chabot. Владелец: Ai Redefined Inc. Дата публикации: 2022-11-24.

Transfer reinforcement learning method and apparatus, and multi-task reinforcement learning method and apparatus

Номер патента: US20240362491A1. Автор: Wei Xu,Haichao Zhang,Lingfeng Sun. Владелец: Horizon Robotics Inc. Дата публикации: 2024-10-31.

Transfer reinforcement learning method and apparatus, and multi-task reinforcement learning method and apparatus

Номер патента: EP4455947A1. Автор: Wei Xu,Haichao Zhang,Lingfeng Sun. Владелец: Horizon Robotics Inc. Дата публикации: 2024-10-30.

Reinforcement learning in robotic process automation

Номер патента: US11775860B2. Автор: Prabhdeep Singh,Marco Alban Hidalgo. Владелец: UiPath Inc. Дата публикации: 2023-10-03.

Systems and methods for real-time reinforcement learning

Номер патента: WO2022241556A1. Автор: Francois Chabot. Владелец: Ai Redefined Inc.. Дата публикации: 2022-11-24.

Machine learning techniques for reinforcement learning using cross-support likelihood model similarity determinations

Номер патента: US20240232725A9. Автор: Vijay S. Nori,Reem A. Hussain,Yagnesh J. Patel. Владелец: UnitedHealth Group Inc. Дата публикации: 2024-07-11.

Method of generating energy storage system control information using reinforcement training result and computing device for performing the same

Номер патента: US20240232641A1. Автор: Cheol-Ho Shin. Владелец: Electronics and Telecommunications Research Institute ETRI. Дата публикации: 2024-07-11.

Reinforcement learning with quantum oracle

Номер патента: WO2022164548A1. Автор: Ashish Kapoor,Martin Henri Roetteler,Daochen WANG,Robin Ashok KOTHARI,Aarthi MEENAKSHI SUNDARAM. Владелец: Microsoft Technology Licensing, LLC. Дата публикации: 2022-08-04.

Generating training curricula for a plurality of reinforcement learning control agents

Номер патента: US20230267365A1. Автор: Alexander Zadorojniy,Akifumi Wachi,Lan Ngoc Hoang. Владелец: International Business Machines Corp. Дата публикации: 2023-08-24.

Imitation and reinforcement learning for multi-agent simulation

Номер патента: US20240303501A1. Автор: Kelvin Wong,Raquel Urtasun,James Tu,Lunjun ZHANG,Simon SUO,Chris ZHANG. Владелец: Waabi Innovation Inc. Дата публикации: 2024-09-12.

Technique for configuring a reinforcement learning agent

Номер патента: US20240193430A1. Автор: Rafia Inam,Alberto HATA,Ahmad Ishtar TERRA,Ajay Kattepur,Hassam Riaz,Prayag Gowgi SOMANAHALLI KRISHNA MURTHY. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2024-06-13.

Method and apparatus for analyzing multi-target based on reinforcement learning for learning under-explored target

Номер патента: US20240152762A1. Автор: Minsu Lee,Byoung-tak Zhang,Kibeom Kim,Min Whoo LEE,Hyundo LEE,Dong-Sig HAN. Владелец: SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION. Дата публикации: 2024-05-09.

Autonomous vehicle testing optimization using offline reinforcement learning

Номер патента: US20240051575A1. Автор: Ritchie Lee. Владелец: GM Cruise Holdings LLC. Дата публикации: 2024-02-15.

Device and method for data-based reinforcement learning

Номер патента: US20220230097A1. Автор: Cheol-Kyun RHO,Yong CHA,Kwon-Yeol LEE. Владелец: Agilesoda Inc. Дата публикации: 2022-07-21.

Reinforcement learning method and motor control unit

Номер патента: US20240289630A1. Автор: Akihiro Katayama,Shiro Yano,Kenichiro Kumada. Владелец: Toyota Motor Corp. Дата публикации: 2024-08-29.

Reinforcement learning method and device

Номер патента: US11366433B2. Автор: Yoshihiro Okawa,Hidenao Iwane. Владелец: Fujitsu Ltd. Дата публикации: 2022-06-21.

Server of reinforcement learning system and reinforcement learning method

Номер патента: US12106190B2. Автор: Yang-Han Lee,Ching-Chang Wong,Kung-Han CHEN. Владелец: Tamkang University. Дата публикации: 2024-10-01.

Method and apparatus for state-adaptive reinforcement learning

Номер патента: WO2024212212A1. Автор: Gao HUANG,Ze Cheng,Qisen YANG,Shenzhi WANG,Shiji Song,Jiawei Gao,Mattieu Gaetan LIN. Владелец: ROBERT BOSCH GMBH. Дата публикации: 2024-10-17.

System and method for risk sensitive reinforcement learning architecture

Номер патента: US20220405643A1. Автор: Yue Gao,Yik Chau LUI,Pablo Francisco Hernandez-Leal. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2022-12-22.

System and method for risk sensitive reinforcement learning architecture

Номер патента: CA3162812A1. Автор: Yue Gao,Yik Chau LUI,Pablo Francisco HERNANDEZ LEAL. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2022-12-11.

Reinforcement learning with optimization-based policy

Номер патента: US20230289612A1. Автор: Ming Jin. Владелец: Virginia Tech Intellectual Properties Inc. Дата публикации: 2023-09-14.

Multi-agent reinforcement learning systems

Номер патента: WO2023213402A1. Автор: David MGUNI,Taher JAFFERJEE. Владелец: Huawei Technologies Co., Ltd.. Дата публикации: 2023-11-09.

Reinforcement Learning für kontinuierliches Lernen des optimalen Ladens einer Batterie

Номер патента: DE102023210856A1. Автор: Nikhil Ravi,Reinhardt Klein,Christoph KROENER,Jeffrey Keating Thompson,Jared Evans. Владелец: ROBERT BOSCH GMBH. Дата публикации: 2024-05-02.

Warm up table for fast reinforcement learning model training

Номер патента: US20240249149A1. Автор: Eduardo Vera Sousa,Yanexis Pupo Toledo,Micael Veríssimo de Araújo,Julia Drummond Noce,João Victor Pinto. Владелец: Dell Products LP. Дата публикации: 2024-07-25.

Method and apparatus for guided offline reinforcement learning

Номер патента: WO2024050712A1. Автор: Xiaonan LU,Wenjie SHI,Gao HUANG,Qisen YANG,Shenzhi WANG,Qihang ZHANG,Haigang ZHOU,Shiji Song. Владелец: ROBERT BOSCH GMBH. Дата публикации: 2024-03-14.

Reinforcement learning agent to evaluate monitoring system strength

Номер патента: US20230281504A1. Автор: Saurabh Arora,Govind Gopinathan NAIR,Mohini SHRIVASTAVA,Jason P. SOMRAK. Владелец: Oracle Financial Services Software Ltd. Дата публикации: 2023-09-07.

Reinforcement learning in robotic process automation

Номер патента: US20210110300A1. Автор: Prabhdeep Singh,Marco Alban Hidalgo. Владелец: UiPath Inc. Дата публикации: 2021-04-15.

Reinforcement learning in robotic process automation

Номер патента: WO2021076222A1. Автор: Prabhdeep Singh,Marco Alban Hidalgo. Владелец: UiPath, Inc.. Дата публикации: 2021-04-22.

Reinforcement learning agent training method, modal bandwidth resource scheduling method and apparatus

Номер патента: US20240015079A1. Автор: QI Xu,Huifeng Zhang,Ruyun Zhang,Congqi Shen,Shaofeng YAO. Владелец: Zhejiang Lab. Дата публикации: 2024-01-11.

Reinforcement learning agent training method, modal bandwidth resource scheduling method and apparatus

Номер патента: US11979295B2. Автор: QI Xu,Huifeng Zhang,Ruyun Zhang,Congqi Shen,Shaofeng YAO. Владелец: Zhejiang Lab. Дата публикации: 2024-05-07.

Machine learning techniques for reinforcement learning using cross-support likelihood model similarity determinations

Номер патента: US20240135263A1. Автор: Vijay S. Nori,Reem A. Hussain,Yagnesh J. Patel. Владелец: UnitedHealth Group Inc. Дата публикации: 2024-04-25.

Reinforcement learning with quantum oracle

Номер патента: US20220253743A1. Автор: Ashish Kapoor,Martin Henri Roetteler,Daochen WANG,Robin Ashok KOTHARI,Aarthi MEENAKSHI SUNDARAM. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2022-08-11.

Efficient reinforcement learning based on merging of trained learners

Номер патента: US20200193333A1. Автор: Hidenao Iwane. Владелец: Fujitsu Ltd. Дата публикации: 2020-06-18.

Pessimistic offline reinforcement learning system and method

Номер патента: US20240037445A1. Автор: WEI Zhan,Chen Tang,Minglei Huang,Masayoshi Tomizuka,Jinning LI. Владелец: Denso International America Inc. Дата публикации: 2024-02-01.

Technique for configuring a reinforcement learning agent

Номер патента: WO2022218512A1. Автор: Rafia Inam,Alberto HATA,Ahmad Ishtar TERRA,Ajay Kattepur,Prayag Gowgi S K,Hassam Riaz. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2022-10-20.

Technique for configuring a reinforcement learning agent

Номер патента: EP4323931A1. Автор: Rafia Inam,Alberto HATA,Ahmad Ishtar TERRA,Ajay Kattepur,Hassam Riaz,Prayag Gowgi SOMANAHALLI KRISHNA MURTHY. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2024-02-21.

Autonomous Supply Chain by Collaborative Software Agents and Reinforcement Learning

Номер патента: US20230281558A1. Автор: Felix Christopher Wick,Dale Lachlan McDonald. Владелец: Blue Yonder Group Inc. Дата публикации: 2023-09-07.

Server of reinforcement learning system and reinforcement learning method

Номер патента: US20220172104A1. Автор: Yang-Han Lee,Ching-Chang Wong,Kung-Han CHEN. Владелец: Tamkang University. Дата публикации: 2022-06-02.

Methods and apparatus for implementing reinforcement learning

Номер патента: WO2022152404A1. Автор: Alexandros NIKOU,Anusha Pradeep MUJUMDAR. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2022-07-21.

Reinforcement learning system and method for generating a decision policy including failsafe

Номер патента: EP4078453A1. Автор: Kenneth L. Moore,Bradley A. OKRESIK. Владелец: Raytheon Co. Дата публикации: 2022-10-26.

Training a reinforcement learning agent

Номер патента: WO2024165187A1. Автор: Konstantinos Vandikas,Lackis ELEFTHERIADIS,Athanasios KARAPANTELAKIS,Marin ORLIC. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2024-08-15.

Exploration method and apparatus in multi-agent reinforcement learning

Номер патента: US20230186154A1. Автор: Hyun Woo Kim,Ran HAN,Sungwon Yi,Jeon Gue Park,Euisok Chung,Hwa Jeon Song,Jeongmin YANG,Byunghyun YOO. Владелец: Electronics and Telecommunications Research Institute ETRI. Дата публикации: 2023-06-15.

Non-Uniform Pessimistic Reinforcement Learning

Номер патента: US20240320504A1. Автор: Takayuki Osogami,Ryo Iwaki. Владелец: International Business Machines Corp. Дата публикации: 2024-09-26.

Methods And Apparatus For Implementing Reinforcement Learning

Номер патента: US20240311687A1. Автор: Alexandros NIKOU,Anusha Pradeep MUJUMDAR. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2024-09-19.

Reinforcement learning system and method for generating a decision policy including failsafe

Номер патента: WO2021126311A1. Автор: Kenneth L. Moore,Bradley A. OKRESIK. Владелец: Raytheon Company. Дата публикации: 2021-06-24.

Reinforcement Learning In A Processing Element Method And System Thereof

Номер патента: US20230087326A1. Автор: Sameer Sadashiv PAWANEKAR,Upendra Narayan Tripathi. Владелец: Us Technology International Pvt Ltd. Дата публикации: 2023-03-23.

Coordinating Reinforcement Learning (RL) for multiple agents in a distributed system

Номер патента: US20240303498A1. Автор: Emil Janulewicz,Sergio SLOBODRIAN. Владелец: Ciena Corp. Дата публикации: 2024-09-12.

Systems and methods for risk-sensitive reinforcement learning

Номер патента: US20210232970A1. Автор: Maria Manuela Veloso,Nelson VADORI,Sumitra GANESH. Владелец: JPMorgan Chase Bank NA. Дата публикации: 2021-07-29.

Quantum reinforcement learning agent

Номер патента: US20210049498A1. Автор: Peng Liu,Stephen Wood,Marco Pistoia,Shaohan Hu,Arthur Giuseppe Rattew. Владелец: International Business Machines Corp. Дата публикации: 2021-02-18.

Reinforcement-learning-agent-based gui metrics for monitoring system effectiveness

Номер патента: US20240135382A1. Автор: Saurabh Arora,Govind Gopinathan NAIR,Mohini SHRIVASTAVA,Jason P. SOMRAK. Владелец: Oracle Financial Services Software Ltd. Дата публикации: 2024-04-25.

Quantum reinforcement learning agent

Номер патента: US20240161002A1. Автор: Peng Liu,Stephen Wood,Marco Pistoia,Shaohan Hu,Arthur Giuseppe Rattew. Владелец: International Business Machines Corp. Дата публикации: 2024-05-16.

Reinforcement learning device and method using conditional episode configuration

Номер патента: US20230206079A1. Автор: Pham-Tuyen LE,Ye-Rin MIN,Cheol-Kyun RHO,Seong-Ryeong LEE. Владелец: Agilesoda Inc. Дата публикации: 2023-06-29.

Pre-Training of a Reinforcement Learning Ground Vehicle Controller Using Monte Carlo Simulation

Номер патента: US20190378042A1. Автор: SYED ALI,Ali Maleki,Gerti TUZI,Saeed ZAMANZAD GAVIDEL. Владелец: Traxen Inc. Дата публикации: 2019-12-12.

Reward for tilt optimization based on reinforcement learning (rl)

Номер патента: WO2023131822A1. Автор: Juan Ramiro Moreno,Jose OUTES CARNERO,Paulo Antonio MOREIRA MIJARES,Jose Maria RUIZ AVILES,Adriano MENDO MATEO,Yak Ng MOLINA,Rakibul ISLAM RONY. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2023-07-13.

Reinforcement learning system

Номер патента: US11586897B2. Автор: Yoshifumi Nishi,Kumiko Nomura,Takao Marukame,Radu Berdan. Владелец: Toshiba Corp. Дата публикации: 2023-02-21.

Method for inverse reinforcement learning and information processing apparatus

Номер патента: US20220398607A1. Автор: Katsumi Homma. Владелец: Fujitsu Ltd. Дата публикации: 2022-12-15.

Optimized reinforcement learning for artificial intelligence models

Номер патента: US20240177015A1. Автор: Christopher Connolly. Владелец: SRI International Inc. Дата публикации: 2024-05-30.

Methods and apparatus for implementing reinforcement learning

Номер патента: EP4278310A1. Автор: Alexandros NIKOU,Anusha Pradeep MUJUMDAR. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2023-11-22.

System and method for automated multi-objective policy implementation, using reinforcement learning

Номер патента: IL288142B1. Автор: . Владелец: B G Negev Technologies And Applications Ltd At Ben Gurion Univ. Дата публикации: 2024-04-01.

System and method for automated multi-objective policy implementation, using reinforcement learning

Номер патента: IL288142B2. Автор: . Владелец: B G Negev Technologies And Applications Ltd At Ben Gurion Univ. Дата публикации: 2024-08-01.

METHOD FOR UNSUPERVISED SEQUENCE LEARNING USING REINFORCEMENT LEARNING AND NEURAL NETWORKS

Номер патента: US20190197409A1. Автор: Frinken Volkmar,Jayachandran Guha,Palakodety Shriphani,Singh Veni. Владелец: . Дата публикации: 2019-06-27.

Administrator-monitored reinforcement-learning-based application manager

Номер патента: US20200065118A1. Автор: Gregory T. Burk,Dongni Wang,Dev Nag,Yanislav Yankov,Nicholas Mark Grant Stephen. Владелец: VMware LLC. Дата публикации: 2020-02-27.

Monitoring apparatus for quality monitoring with adaptive data valuation

Номер патента: WO2022194561A1. Автор: Hans-Georg Kopken,Denis Krompaß,Ahmed FRIKHA. Владелец: SIEMENS AKTIENGESELLSCHAFT. Дата публикации: 2022-09-22.

Monitoring apparatus for quality monitoring with adaptive data valuation

Номер патента: EP4288908A1. Автор: Hans-Georg Kopken,Denis Krompaß,Ahmed FRIKHA. Владелец: SIEMENS AG. Дата публикации: 2023-12-13.

Monitoring apparatus for quality monitoring with adaptive data valuation

Номер патента: US20240160195A1. Автор: Hans-Georg Kopken,Denis Krompaß,Ahmed FRIKHA. Владелец: SIEMENS AG. Дата публикации: 2024-05-16.

Monitoring apparatus for quality monitoring with adaptive data valuation

Номер патента: EP4060561A1. Автор: Hans-Georg Kopken,Denis Krompaß,Ahmed FRIKHA. Владелец: SIEMENS AG. Дата публикации: 2022-09-21.

DATA VALUATION USING META-LEARNING FOR MACHINE LEARNING PROGRAMS

Номер патента: US20220138561A1. Автор: Prendki Jennifer Laetitia. Владелец: . Дата публикации: 2022-05-05.

Radar resource management system, apparatus to train an agent in a radar system using reinforcement learning, method for managing radar resources, and method to train an agent in a radar system using reinforcement learning

Номер патента: EP3971659A1. Автор: Christoph Fischer,Stefan Brüggenwirth,Sebastian Durst. Владелец: Hensoldt Sensors GmbH. Дата публикации: 2022-03-23.

Operation of sectorized communications from aerospace platforms using reinforcement learning

Номер патента: US20240306014A1. Автор: JIN Zhang,Sharath Ananth,Brian Barritt. Владелец: Aalyria Technologies Inc. Дата публикации: 2024-09-12.

One shot multi-user multiple-input multiple-output (mu-mimo) resource pairing using reinforcement learning based deep q network (dqn)

Номер патента: WO2020094630A1. Автор: Chandrasekar Sankaran. Владелец: NOKIA SOLUTIONS AND NETWORKS OY. Дата публикации: 2020-05-14.

One shot multi-user multiple-input multiple-output (MU-MIMO) resource pairing using reinforcement learning based deep Q network (DQN)

Номер патента: US12040856B2. Автор: Chandrasekar Sankaran. Владелец: NOKIA SOLUTIONS AND NETWORKS OY. Дата публикации: 2024-07-16.

Operation Of Sectorized Communications From Aerospace Platforms Using Reinforcement Learning

Номер патента: US20220191715A1. Автор: JIN Zhang,Sharath Ananth,Brian Barritt. Владелец: Aalyria Technologies Inc. Дата публикации: 2022-06-16.

Operation of sectorized communications from aerospace platforms using reinforcement learning

Номер патента: WO2020131522A1. Автор: JIN Zhang,Sharath Ananth,Brian Barritt. Владелец: LOON LLC. Дата публикации: 2020-06-25.

Operation Of Sectorized Communications From Aerospace Platforms Using Reinforcement Learning

Номер патента: US20200196167A1. Автор: JIN Zhang,Sharath Ananth,Brian Barritt. Владелец: LOON LLC. Дата публикации: 2020-06-18.

Operation of sectorized communications from aerospace platforms using reinforcement learning

Номер патента: US11751076B2. Автор: JIN Zhang,Sharath Ananth,Brian Barritt. Владелец: Aalyria Technologies Inc. Дата публикации: 2023-09-05.

Evaluating varying-sized action spaces using reinforcement learning

Номер патента: US11243532B1. Автор: Martin Levihn,Pekka Tapani Raiko. Владелец: Apple Inc. Дата публикации: 2022-02-08.

Controller for autonomous agents using reinforcement learning with control barrier functions to overcome inaccurate safety region

Номер патента: WO2023034028A1. Автор: Amit Chakraborty,Biswadip Dey,Ioannis Akrotirianakis. Владелец: Siemens Corporation. Дата публикации: 2023-03-09.

Precision hygiene using reinforcement learning

Номер патента: WO2021009574A1. Автор: Olivia GRABMAIER. Владелец: Grabmaier Olivia. Дата публикации: 2021-01-21.

Precision hygiene using reinforcement learning

Номер патента: US20210012224A1. Автор: Olivia Karen Grabmaier. Владелец: Individual. Дата публикации: 2021-01-14.

Controller for autonomous agents using reinforcement learning with control barrier functions to overcome inaccurate safety region

Номер патента: US20230064332A1. Автор: Amit Chakraborty,Biswadip Dey,Ioannis Akrotirianakis. Владелец: SIEMENS AG. Дата публикации: 2023-03-02.

Microgrid spatial-temporal perception energy management method based on safe deep reinforcement learning

Номер патента: US20240330396A1. Автор: Peiling CHEN,Yujian Ye. Владелец: SOUTHEAST UNIVERSITY. Дата публикации: 2024-10-03.

Communication-channel tracking aided by reinforcement learning

Номер патента: US20210266202A1. Автор: Paschalis Tsiaflakis. Владелец: NOKIA SOLUTIONS AND NETWORKS OY. Дата публикации: 2021-08-26.

System and method for optimizing communications using reinforcement learning

Номер патента: EP3513358A1. Автор: Alan McCord. Владелец: NewVoiceMedia US Inc. Дата публикации: 2019-07-24.

System and method for optimizing communications using reinforcement learning

Номер патента: WO2018053438A1. Автор: Alan McCord. Владелец: Newvoicemedia Us Inc.. Дата публикации: 2018-03-22.

Electronic device for effect-driven dynamic media selection for visual iot service using reinforcement learning and operating method thereof

Номер патента: US20210352153A1. Автор: In-Young Ko,Kyeongdeok BAEK. Владелец: Korea Advanced Institute of Science and Technology KAIST. Дата публикации: 2021-11-11.

User plane selection using reinforcement learning

Номер патента: EP4022958A1. Автор: Dinand Roeland,Jaeseong JEONG,Andreas YOKOBORI SÄVÖ. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2022-07-06.

User plane selection using reinforcement learning

Номер патента: US20220358335A1. Автор: Dinand Roeland,Jaeseong JEONG,Andreas YOKOBORI SÄVÖ. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2022-11-10.

Method and device for attention-driven resource allocation by using reinforcement learning and v2x communication to thereby achieve safety of autonomous driving

Номер патента: US20200250526A1. Автор: Kye-Hyeon Kim,Hak-Kyoung Kim,Sukhoon Boo,Myungchul Sung,Dongsoo Shin,Donghun Yeo,Wooju Ryu,Myeong-Chun Lee,Hyungsoo Lee,Taewoong Jang,Kyungjoong Jeong,Hongmo Je,Hojin Cho,Yongjoong Kim,Woonhyun Nam. Владелец: Stradvision Inc. Дата публикации: 2020-08-06.

Evaluating software license usage using reinforcement learning agents

Номер патента: US11854102B2. Автор: Amihai Savir,Assaf Natanzon,Shiri Gaber. Владелец: EMC IP Holding Co LLC. Дата публикации: 2023-12-26.

Vision-based sample-efficient reinforcement learning framework for autonomous driving

Номер патента: US20190302785A1. Автор: Ming-Chang Liu,Su-Hui Chiang. Владелец: Sony Corp. Дата публикации: 2019-10-03.

Automatic health indicator learning using reinforcement learning for predictive maintenance

Номер патента: US20190384257A1. Автор: Chi Zhang,Dipanjan Ghosh,Ahmed Khairy Farahat,Chetan GUPTA,Kosta RISTOVSKI. Владелец: HITACHI LTD. Дата публикации: 2019-12-19.

Maze-driven self-diagnostics using reinforcement learning

Номер патента: US20220405162A1. Автор: Kenneth Armstrong,Chunzhi CHEN,Guo Rong Zheng. Владелец: RingCentral Inc. Дата публикации: 2022-12-22.

Job scheduling using reinforcement learning

Номер патента: US11803999B2. Автор: Zhuo Chen,Andrej Zdravkovic,Mehdi Saeedi,Steven Tovey,Thomas Daniel Perry. Владелец: Advanced Micro Devices Inc. Дата публикации: 2023-10-31.

Job scheduling using reinforcement learning

Номер патента: US20230154100A1. Автор: Zhuo Chen,Andrej Zdravkovic,Mehdi Saeedi,Steven Tovey,Thomas Daniel Perry. Владелец: Advanced Micro Devices Inc. Дата публикации: 2023-05-18.

System and method of identifying self-healing actions for computing systems using reinforcement learning

Номер патента: US20210303388A1. Автор: Aneesh George,Rashmi M.G.. Владелец: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP. Дата публикации: 2021-09-30.

Modular reinforcement-learning-based application manager

Номер патента: US20200065128A1. Автор: Gregory T. Burk,Nick Stephen,Dongni Wang,Dev Nag,Janislav Jankov. Владелец: VMware LLC. Дата публикации: 2020-02-27.

Computing apparatus and method for performing reinforcement learning using multimodal artificial intelligence agent

Номер патента: US20230177820A1. Автор: Hyun Seok Oh,Minsu Lee,Youngki Lee,Byoung-tak Zhang,Junseok Park,Min Whoo LEE,Kwanyoung PARK,Ganghun Lee. Владелец: SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION. Дата публикации: 2023-06-08.

Sample-efficient reinforcement learning

Номер патента: WO2023171102A1. Автор: Nicolas Bruno Alexandre BOUGIE. Владелец: NATIONAL INSTITUTE OF ADVANCED INDUSTRIAL SCIENCE AND TECHNOLOGY. Дата публикации: 2023-09-14.

Reinforcement learning for jitter buffer control

Номер патента: US20210258235A1. Автор: Yan Lu,Sriram Srinivasan,Xiulian Peng,Vinod Prakash,Xiangyu Kong. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2021-08-19.

Reinforcement learning for jitter buffer control

Номер патента: US12113680B2. Автор: Yan Lu,Sriram Srinivasan,Xiulian Peng,Vinod Prakash,Xiangyu Kong. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2024-10-08.

Emotion recognition as feedback for reinforcement learning and as an indicator of the explanation need of users

Номер патента: WO2021225550A1. Автор: Yaser Deniz IREN,Banu Emine AYSOLMAZ. Владелец: Aysolmaz Banu Emine. Дата публикации: 2021-11-11.

Automated reinforcement learning scenario variation and impact penalties

Номер патента: US12037013B1. Автор: Gary Linscott,Marin KOBILAROV,Jefferson Bradfield Packer,Andreas Pasternak. Владелец: Zoox Inc. Дата публикации: 2024-07-16.

Safe-operation-constrained reinforcement-learning-based application manager

Номер патента: US20200065495A1. Автор: Gregory T. Burk,Dongni Wang,Dev Nag,Yanislav Yankov,Nicholas Mark Grant Stephen. Владелец: VMware LLC. Дата публикации: 2020-02-27.

Reinforcement learning stability optimization

Номер патента: US20230316122A1. Автор: Samuel Mathew Jawaharlal,Sathya Santhar,Sarbajit K. Rakshit,Sridevi Kannan. Владелец: International Business Machines Corp. Дата публикации: 2023-10-05.

Adversarial automated reinforcement-learning-based application-manager training

Номер патента: US20200065703A1. Автор: Gregory T. Burk,Dongni Wang,Dev Nag,Yanislav Yankov,Nicholas Mark Grant Stephen. Владелец: VMware LLC. Дата публикации: 2020-02-27.

Storage system IO throttling utilizing a reinforcement learning framework

Номер патента: US11797189B1. Автор: CHI Chen,Hailan Dong,Changyue Dai. Владелец: Dell Products LP. Дата публикации: 2023-10-24.

Customizable reinforcement learning of column placement in structural design

Номер патента: US20240202381A1. Автор: Yi Wang,Medhi NOURBAKHSH. Владелец: Autodesk Inc. Дата публикации: 2024-06-20.

Storage system io throttling utilizing a reinforcement learning framework

Номер патента: US20230333745A1. Автор: CHI Chen,Hailan Dong,Changyue Dai. Владелец: Dell Products LP. Дата публикации: 2023-10-19.

Reinforcement learning algorithm-based predictive control method for lateral and longitudinal coupled vehicle formation

Номер патента: US20240083428A1. Автор: HONG Chen,Baojun Lin,Yunyong LI,Yangyang Feng,Shuyou YU,Encong SHENG. Владелец: Jilin University. Дата публикации: 2024-03-14.

Generating parameter values for snapshot schedules utilizing a reinforcement learning framework

Номер патента: US20240311337A1. Автор: CHI Chen,En Shi,Changyue Dai. Владелец: Dell Products LP. Дата публикации: 2024-09-19.

Method and system for automatically processing point cloud based on reinforcement learning

Номер патента: US11703596B2. Автор: SeongJoo MOON. Владелец: HL Klemove Corp. Дата публикации: 2023-07-18.

Reinforcement learning agent simulation to measure monitoring system strength

Номер патента: US20230376961A1. Автор: Saurabh Arora,Govind Gopinathan NAIR,Mohini SHRIVASTAVA,Jason P. SOMRAK. Владелец: Oracle Financial Services Software Ltd. Дата публикации: 2023-11-23.

Apparatus and method of ensuring quality of control operations of system on the basis of reinforcement learning

Номер патента: US20200167611A1. Автор: Seung Hyun Yoon,Chung Lae CHO,Hong Seok Jeon,Seung Jae Shin. Владелец: Electronics and Telecommunications Research Institute ETRI. Дата публикации: 2020-05-28.

Recording medium that stores reinforcement learning program, reinforcement learning method, and reinforcement learning apparatus

Номер патента: US20200184277A1. Автор: Tomotake SASAKI,Hitoshi Yanami,Hidenao Iwane. Владелец: Fujitsu Ltd. Дата публикации: 2020-06-11.

Reinforcement learning-based decision optimization method of oilfield production system

Номер патента: US20230358123A1. Автор: MING Yue,Jiulong Wang,Hongqing SONG,Shuyi DU,Liying Song. Владелец: Beijing Zhongke Zhishang Technology Co Ltd. Дата публикации: 2023-11-09.

Reinforcement learning model training through simulation

Номер патента: US11836577B2. Автор: Leo Parker Dirac,Sahika Genc,Sunil Mallya KASARAGOD,Bharathan Balaji,Eric Li Sun,Marthinus Coenraad De Clercq Wentzel. Владелец: Amazon Technologies Inc. Дата публикации: 2023-12-05.

Automated reinforcement-learning-based application manager that uses local agents

Номер патента: US20200065702A1. Автор: Gregory T. Burk,Dongni Wang,Dev Nag,Yanislav Yankov,Nicholas Mark Grant Stephen. Владелец: VMware LLC. Дата публикации: 2020-02-27.

Method and apparatus for generating multi-drone network cooperative operation plan based on reinforcement learning

Номер патента: US20230297859A1. Автор: Ui Hwan CHOI. Владелец: Electronics and Telecommunications Research Institute ETRI. Дата публикации: 2023-09-21.

Memory Device With Reinforcement Learning With Q-Learning Acceleration

Номер патента: US20220066697A1. Автор: Ran ZAMIR,Stella Achtenberg,Ofir Pele,Omer FAINZILBER. Владелец: Western Digital Technologies Inc. Дата публикации: 2022-03-03.

Adversarial reinforcement learning system for simulating security checkpoint environments

Номер патента: US20220414231A1. Автор: Brian Jacob LEWIS,Jason Adam DEICH,Stephen John MELSOM,Kara Jean DODENHOFF,William Tyler NIGGEL. Владелец: Noblis Inc. Дата публикации: 2022-12-29.

Infrastructure refactoring via fuzzy upside down reinforcement learning

Номер патента: US20220350732A1. Автор: Madhu Sudhanan Krishnamoorthy,Sreeram Raghavan,Rajarajan Pandiyan. Владелец: Bank of America Corp. Дата публикации: 2022-11-03.

Systems and methods for deep reinforcement learning using a brain-artificial intelligence interface

Номер патента: US11755108B2. Автор: Paul Sajda,Victor Shih,Sameer Saproo,Sonakshi Bose Roy,David Jangraw. Владелец: Columbia University in the City of New York. Дата публикации: 2023-09-12.

Inverse reinforcement learning for user-specific behaviors

Номер патента: US11710072B1. Автор: Mark Drummond,Behrooz Mahasseni. Владелец: Apple Inc. Дата публикации: 2023-07-25.

Solid state drive cache eviction policy by an unsupervised reinforcement learning scheme

Номер патента: US12038844B2. Автор: Ariel Navon,Shay Benisty,Alexander Bazarsky,Opher Lieber. Владелец: Western Digital Technologies Inc. Дата публикации: 2024-07-16.

Method and apparatus for control energy management system based on reinforcement learning

Номер патента: US20220138874A1. Автор: Jeonghoon Lee,Minjoo Lee,Sungho JOO,Wonshick KO,Joongjae KIM,Je Yeol LEE,Kyeong Min WOO. Владелец: MakinaRocks Co Ltd. Дата публикации: 2022-05-05.

Trade platform with reinforcement learning network and matching engine

Номер патента: US12099874B2. Автор: Hasham BURHANI,Zichang LONG,Jonathan CUPILLARI. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2024-09-24.

Customizable reinforcement learning of column placement in structural design

Номер патента: US11941327B2. Автор: Yi Wang,Mehdi Nourbakhsh. Владелец: Autodesk Inc. Дата публикации: 2024-03-26.

Reinforcement learning for chatbots

Номер патента: US20210158203A1. Автор: Raghu Kiran Ganti,Mudhakar Srivatsa,Linsong Chu,Shreeranjani Srirangamsridharan,Yeon-Sup Lim. Владелец: International Business Machines Corp. Дата публикации: 2021-05-27.

Device and method for providing object placement model of interior design service on basis of reinforcement learning

Номер патента: US20230315929A1. Автор: Soo Min KIM. Владелец: UrbanBase Inc. Дата публикации: 2023-10-05.

Method and system for evolved sarsa reinforcement learning for flow shop scheduling

Номер патента: EP4250107A1. Автор: Venkataramana Runkana,Pallavi Venugopal Minimol,Sagar Srinivas Sakhinana. Владелец: Tata Consultancy Services Ltd. Дата публикации: 2023-09-27.

Apparatus and method for altruistic scheduling based on reinforcement learning

Номер патента: US20210168827A1. Автор: Seung Jae Shin. Владелец: Electronics and Telecommunications Research Institute ETRI. Дата публикации: 2021-06-03.

Method for generating analog schematic diagram based on building block classification and reinforcement learning

Номер патента: US20240086606A1. Автор: Po-Hung Lin,Hung-Yun Hsu,Yu-Tsang Hsieh. Владелец: AnaGlobe Tech Inc. Дата публикации: 2024-03-14.

Method and system for evolved sarsa reinforcement learning for flow shop scheduling

Номер патента: US20230306271A1. Автор: Venkataramana Runkana,Pallavi Venugopal Minimol,Sagar Srinivas Srinivas Sakhinana. Владелец: Tata Consultancy Services Ltd. Дата публикации: 2023-09-28.

Reinforcement Learning Based Adaptive State Observation for Brain-Machine Interface

Номер патента: US20230010664A1. Автор: Xiang Zhang,Zhiwei Song,Yiwen Wang. Владелец: Hong Kong University of Science and Technology HKUST. Дата публикации: 2023-01-12.

Device and method for providing object placement model of interior design service on basis of reinforcement learning

Номер патента: EP4246418A1. Автор: Soo Min KIM. Владелец: UrbanBase Inc. Дата публикации: 2023-09-20.

Reinforcement learning and simulation based dispatching method within a factory, and an apparatus thereof

Номер патента: KR102251316B1. Автор: 김병희,이원준,정구환. Владелец: (주)브이엠에스 솔루션스. Дата публикации: 2021-05-12.

Solid State Drive Cache Eviction Policy by an Unsupervised Reinforcement Learning Scheme

Номер патента: US20230176976A1. Автор: Ariel Navon,Shay Benisty,Alexander Bazarsky,Opher Lieber. Владелец: Western Digital Technologies Inc. Дата публикации: 2023-06-08.

Trade platform with reinforcement learning network and matching engine

Номер патента: US11714679B2. Автор: Hasham BURHANI,Zichang LONG,Jonathan CUPILLARI. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-08-01.

Webpage phishing detection using deep reinforcement learning

Номер патента: US20220353292A1. Автор: Jugal Parikh,Nitin Kumar Goel,Cristian Craioveanu,Eleanor Catherine QUINT,Mariusz Hieronim JAKUBOWSKI,Douglas J HINES. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2022-11-03.

Utilizing reinforcement learning for serverless function tuning

Номер патента: US20220303333A1. Автор: Huamin Chen,JinJun Xiong,Roland Ludwig Huss. Владелец: Red Hat Inc. Дата публикации: 2022-09-22.

Dynamic resource reservation with reinforcement learning

Номер патента: US20230385116A1. Автор: Srimat Chakradhar,Murugan Sankaradas,Kunal Rao,Oliver Po,Wang-Pin Hsiung,Anousheh Gholami. Владелец: NEC Laboratories America Inc. Дата публикации: 2023-11-30.

Remote agent implementation of reinforcement learning policies

Номер патента: US20230281277A1. Автор: Johannes Hendrik VERWEY. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2023-09-07.

Central node and a method for reinforcement learning in a radio access network

Номер патента: US20230403574A1. Автор: Yu Wang,Pablo SOLDATI,Vidit SAXENA,Wenfeng Hu. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2023-12-14.

Method and apparatus for task scheduling based on deep reinforcement learning, and device

Номер патента: US11886993B2. Автор: Qi Qi,Jing Wang,Jingyu Wang,Haifeng Sun,Lingxin ZHANG,Jianxin Liao. Владелец: BEIJING UNIVERSITY OF POSTS AND TELECOMMUNICATIONS. Дата публикации: 2024-01-30.

Dynamic resource reservation with reinforcement learning

Номер патента: WO2023230125A1. Автор: Srimat Chakradhar,Murugan Sankaradas,Kunal Rao,Oliver Po,Wang-Pin Hsiung,Anousheh Gholami. Владелец: NEC Laboratories America, Inc.. Дата публикации: 2023-11-30.

Automatically tuning a quality of service setting for a distributed storage system with a deep reinforcement learning agent

Номер патента: US20240004576A1. Автор: Tyler W. Cady. Владелец: NetApp Inc. Дата публикации: 2024-01-04.

Methods and apparatus for the application of reinforcement learning to animal medical diagnostics

Номер патента: US20230253120A1. Автор: Neil Gavin SHAW,Lior Kuyer. Владелец: SignalPet LLC. Дата публикации: 2023-08-10.

System and method for reinforcement learning based controlled natural language generation

Номер патента: WO2021247231A1. Автор: Arjun Maheswaran,Akhilesh Sudhakar,Bhargav UPADHYAY. Владелец: PM Labs, Inc.. Дата публикации: 2021-12-09.

Webpage phishing detection using deep reinforcement learning

Номер патента: US20230179629A1. Автор: Jugal Parikh,Nitin Kumar Goel,Cristian Craioveanu,Douglas J. Hines,Eleanor Catherine QUINT,Mariusz Hieronim JAKUBOWSKI. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2023-06-08.

Method for Performing Multi-Agent Reinforcement Learning in the Presence of Unreliable Communications Via Distributed Consensus

Номер патента: US20200380401A1. Автор: Michael W. Walton,Benjamin J. Migliori,John Reeder. Владелец: US Department of Navy. Дата публикации: 2020-12-03.

Trade platform with reinforcement learning network and matching engine

Номер патента: US11086674B2. Автор: Hasham BURHANI,Zichang LONG,Jonathan CUPILLARI. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2021-08-10.

System and method for providing multiple input multiple output (mimo) detector selection with reinforced learning neural network

Номер патента: US20200343962A1. Автор: Hyukjoon Kwon,Kee-Bong Song. Владелец: SAMSUNG ELECTRONICS CO LTD. Дата публикации: 2020-10-29.

Solid state drive cache eviction policy by an unsupervised reinforcement learning scheme

Номер патента: US20200104260A1. Автор: Ariel Navon,Shay Benisty,Opher Lieber,Alex Bazarsky. Владелец: Western Digital Technologies Inc. Дата публикации: 2020-04-02.

Trade platform with reinforcement learning network and matching engine

Номер патента: US20190361739A1. Автор: Hasham BURHANI,Zichang LONG,Jonathan CUPILLARI. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2019-11-28.

Trade platform with reinforcement learning network and matching engine

Номер патента: US20230367635A1. Автор: Hasham BURHANI,Zichang LONG,Jonathan CUPILLARI. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2023-11-16.

Trade platform with reinforcement learning network and matching engine

Номер патента: US20210349758A1. Автор: Hasham BURHANI,Zichang LONG,Jonathan CUPILLARI. Владелец: ROYAL BANK OF CANADA. Дата публикации: 2021-11-11.

Webpage phishing detection using deep reinforcement learning

Номер патента: WO2022231740A1. Автор: Jugal Parikh,Nitin Kumar Goel,Cristian Craioveanu,Eleanor Catherine QUINT,Mariusz Hieronim JAKUBOWSKI,Douglas J HINES. Владелец: Microsoft Technology Licensing, LLC. Дата публикации: 2022-11-03.

New rule creation using mdp and inverse reinforcement learning

Номер патента: US20180293512A1. Автор: Akira Koseki,Toshiro Takase,Tetsuro Morimura,Hiroki Yanagisawa. Владелец: International Business Machines Corp. Дата публикации: 2018-10-11.

Method and apparatus for control energy management system based on reinforcement learning

Номер патента: US11645728B2. Автор: Jeonghoon Lee,Minjoo Lee,Sungho JOO,Wonshick KO,Joongjae KIM,Je Yeol LEE,Kyeong Min WOO. Владелец: MakinaRocks Co Ltd. Дата публикации: 2023-05-09.

Reinforcement learning-based sensor data management method and system

Номер патента: US20210201084A1. Автор: Ik Jun Yeom,Seung Hwan Jeong,Min Jong Yoo,Gwang Pyo YOO,Hong Uk WOO. Владелец: Sungkyunkwan University Research and Business Foundation. Дата публикации: 2021-07-01.

Webpage phishing detection using deep reinforcement learning

Номер патента: US11997137B2. Автор: Jugal Parikh,Nitin Kumar Goel,Cristian Craioveanu,Eleanor Catherine QUINT,Mariusz Hieronim JAKUBOWSKI,Douglas J HINES. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2024-05-28.

Online multi-workflow scheduling method based on reinforcement learning

Номер патента: GB2624736A. Автор: HUANG Zixin,Yin Yuyu,Huang Binbin. Владелец: Hangzhou Dianzi University. Дата публикации: 2024-05-29.

Online multi-workflow scheduling method based on reinforcement learning

Номер патента: US20240137404A1. Автор: Binbin Huang,Yuyu Yin,Zixin Huang. Владелец: Hangzhou Dianzi University. Дата публикации: 2024-04-25.

Automatically tuning a quality of service setting for a distributed storage system with a deep reinforcement learning agent

Номер патента: US11842068B2. Автор: Tyler W. Cady. Владелец: NetApp Inc. Дата публикации: 2023-12-12.

Remote agent implementation of reinforcement learning policies

Номер патента: WO2023172365A1. Автор: Johannes Hendrik VERWEY. Владелец: Microsoft Technology Licensing, LLC.. Дата публикации: 2023-09-14.

Central node and a method for reinforcement learning in a radio access network

Номер патента: EP4252442A1. Автор: Yu Wang,Pablo SOLDATI,Vidit SAXENA,Wenfeng Hu. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2023-10-04.

Adversarial reinforcement learning system for simulating security checkpoint environments

Номер патента: US11423157B2. Автор: Brian Jacob LEWIS,Jason Adam DEICH,Stephen John MELSOM,Kara Jean DODENHOFF,William Tyler NIGGEL. Владелец: Noblis Inc. Дата публикации: 2022-08-23.

Reinforcement learning engine for a radar system

Номер патента: US12000958B2. Автор: Matthew Paul Harrison. Владелец: Bdcm A2 LLC. Дата публикации: 2024-06-04.

Adversarial reinforcement learning system for simulating security checkpoint environments

Номер патента: US20200364347A1. Автор: Brian Jacob LEWIS,Jason Adam DEICH,Stephen John MELSOM,Kara Jean DODENHOFF,William Tyler NIGGEL. Владелец: Noblis Inc. Дата публикации: 2020-11-19.

Hardware acceleration of reinforcement learning within network devices

Номер патента: US20230306082A1. Автор: Gal Yefet,Shridhar Rasal. Владелец: MELLANOX TECHNOLOGIES LTD. Дата публикации: 2023-09-28.

Method and apparatus for baseball strategy planning based on reinforcement learning

Номер патента: US20210387070A1. Автор: Wei-Yu Chiu,Song-Jen Chen. Владелец: National Tsing Hua University NTHU. Дата публикации: 2021-12-16.

Hierarchical reinforcement learning algorithm for NFV server power management

Номер патента: US12001932B2. Автор: ZHU Zhou,Atul Kwatra,Chris Macnamara,Stephen Doyle,Xiaotian Gao. Владелец: Intel Corp. Дата публикации: 2024-06-04.

Aligning large language models with specific objectives using reinforcement learning and human preference

Номер патента: US20240289632A1. Автор: Li Tan,JIAN Li,Haixun Wang. Владелец: Maplebear Inc. Дата публикации: 2024-08-29.

Systems and methods of deploying reinforcement learning

Номер патента: US20220358404A1. Автор: Arun Karthik Ravindran,Muhammad Arjumand Masood. Владелец: Boston Consulting Group Inc. Дата публикации: 2022-11-10.

Systems and methods for coordinated vehicle lane assignment using reinforcement learning

Номер патента: US12142141B2. Автор: Kentaro Oguchi,Abdul Rahman Kreidieh,Yashar Zeiynali Farid. Владелец: Toyota Motor Engineering and Manufacturing North America Inc. Дата публикации: 2024-11-12.

System and method for parking spot selection using reinforcement learning

Номер патента: US20240169839A1. Автор: Alireza Esna Ashari Esfahani. Владелец: GM GLOBAL TECHNOLOGY OPERATIONS LLC. Дата публикации: 2024-05-23.

Factory simulator-based scheduling system using reinforcement learning

Номер патента: US20240029177A1. Автор: Young Min Yun,Ho Yeoul LEE. Владелец: Neurocore Co Ltd. Дата публикации: 2024-01-25.

Improving the safety of reinforcement learning models

Номер патента: AU2019253703B2. Автор: Bibhrajit Halder. Владелец: Safeai Inc. Дата публикации: 2024-05-16.

Improving the safety of reinforcement learning models

Номер патента: WO2019199870A1. Автор: Bibhrajit Halder. Владелец: SafeAI, Inc.. Дата публикации: 2019-10-17.

Communication time allocation method using reinforcement learning for wireless powered communication network and base station

Номер патента: US20210320706A1. Автор: Sung-Yu Tsai,Wei-Yu Chiu. Владелец: National Tsing Hua University NTHU. Дата публикации: 2021-10-14.

Communication time allocation method using reinforcement learning for wireless powered communication network and base station

Номер патента: US11323167B2. Автор: Sung-Yu Tsai,Wei-Yu Chiu. Владелец: National Tsing Hua University NTHU. Дата публикации: 2022-05-03.

Systems and methods for coordinated vehicle lane assignment using reinforcement learning

Номер патента: US20230127576A1. Автор: Kentaro Oguchi,Abdul Rahman Kreidieh,Yashar Zeiynali Farid. Владелец: Toyota Motor Engineering and Manufacturing North America Inc. Дата публикации: 2023-04-27.

Control apparatus, control method for control apparatus, non-transitory computer readable storage medium, information processing server, information processing method, and control system for controlling system using reinforcement learning

Номер патента: US20210192344A1. Автор: Gakuyo Fujimoto. Владелец: Honda Motor Co Ltd. Дата публикации: 2021-06-24.

Method of determining continuous drug dose using reinforcement learning and pharmacokinetic-pharmacodynamic models

Номер патента: US20220199217A1. Автор: Seung Hyun Lee,Sung Min Park. Владелец: POSTECH Research and Business Development Foundation. Дата публикации: 2022-06-23.

Control apparatus, control method for control apparatus, non-transitory computer readable storage medium, information processing server, information processing method, and control system for controlling system using reinforcement learning

Номер патента: US11934951B2. Автор: Gakuyo Fujimoto. Владелец: Honda Motor Co Ltd. Дата публикации: 2024-03-19.

Risk optimization through reinforcement learning

Номер патента: US11810038B2. Автор: James Robert Kozloski,Suraj Pandey,Timothy Michael Lynar,John Michael Wagner. Владелец: International Business Machines Corp. Дата публикации: 2023-11-07.

Controlling operation of an electrical grid using reinforcement learning and multi-particle modeling

Номер патента: US11892809B2. Автор: Wolf Kohn,Chad Edward Steelberg,Andrew Elvin Badgett,Leslie Gene Engelbrecht. Владелец: Veritone Inc. Дата публикации: 2024-02-06.

Demonstration-conditioned reinforcement learning for few-shot imitation

Номер патента: US20220395975A1. Автор: Julien Perez,Christopher Dance,Theo CACHET. Владелец: Naver Labs Corp. Дата публикации: 2022-12-15.

Randomized reinforcement learning for control of complex systems

Номер патента: US20190130263A1. Автор: Siegmund DÜLL,Steffen Udluft,Kai Heesche,Raymond S. Nordlund,Marc Christian Weber. Владелец: SIEMENS AG. Дата публикации: 2019-05-02.

Randomized reinforcement learning for control of complex systems

Номер патента: WO2019086243A1. Автор: Siegmund DÜLL,Steffen Udluft,Kai Heesche,Raymond S. Nordlund,Marc Christian Weber. Владелец: SIEMENS AKTIENGESELLSCHAFT. Дата публикации: 2019-05-09.

Link change decision-making using reinforcement learning based on tracked rewards and outcomes in a wireless communication system

Номер патента: US11963047B2. Автор: David Lindero,Elena Fersman,Markus Andersson,Athanasios KARAPANTELAKIS,Rafia Inam. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2024-04-16.

Calibrating parameters within a virtual environment using reinforcement learning

Номер патента: US20230376832A1. Автор: Sayyed Rouhollah Jafari Tafti,Alireza Esna Ashari Esfahani. Владелец: GM GLOBAL TECHNOLOGY OPERATIONS LLC. Дата публикации: 2023-11-23.

Randomized reinforcement learning for control of complex systems

Номер патента: EP3682301A1. Автор: Siegmund DÜLL,Steffen Udluft,Kai Heesche,Raymond S. Nordlund,Marc Christian Weber. Владелец: SIEMENS AG. Дата публикации: 2020-07-22.

Dc-dc converter control method based on td3 reinforcement learning algorithm

Номер патента: ZA202303806B. Автор: Jian Ye,huanyu Guo. Владелец: Harbin Inst Technology Shenzhen. Дата публикации: 2024-04-24.

Reinforcement learning method, recording medium, and reinforcement learning apparatus

Номер патента: US20200233384A1. Автор: Hidenao Iwane. Владелец: Fujitsu Ltd. Дата публикации: 2020-07-23.

Variable structure reinforcement learning

Номер патента: US20220172103A1. Автор: Sergiy Zhuk,Jonathan Peter Epperlein,Djallel Bouneffouf. Владелец: International Business Machines Corp. Дата публикации: 2022-06-02.

Reinforcement learning system for recommended associations

Номер патента: US20190114561A1. Автор: CUI Lin,Ye Chen,Teodor J. Bally,Himanshu Pande. Владелец: CA Inc. Дата публикации: 2019-04-18.

Method and apparatus of deep reinforcement learning for marketing cost control

Номер патента: US20210117999A1. Автор: Jianshan He. Владелец: Advanced New Technologies Co Ltd. Дата публикации: 2021-04-22.

Signal detection method and apparatus based on reinforcement learning for vehicular mimo communication

Номер патента: US20220169267A1. Автор: Chung Yong Lee,Chae Hun IM. Владелец: University Industry Foundation UIF of Yonsei University. Дата публикации: 2022-06-02.

Reinforcement learning for automated allocation of resources to sub-campaigns of a content campaign

Номер патента: US20240289873A1. Автор: Ramasubramanian Balasubramanian,Karuna Ahuja,Chakshu Ahuja. Владелец: Maplebear Inc. Дата публикации: 2024-08-29.

Deep reinforcement learning methods and apparatuses for referral marketing

Номер патента: US20210049632A1. Автор: Jianshan He. Владелец: Advanced New Technologies Co Ltd. Дата публикации: 2021-02-18.

JOINT DESIGN OF USER ASSOCIATION AND HYBRID BEAMFORMING METHOD AND SYSTEM FOR SUB-THz UDN USING MULTI-AGENT DEEP REINFORCEMENT LEARNING

Номер патента: US20240204843A1. Автор: Seunghun LEE,Hyuncheol Park. Владелец: Korea Advanced Institute of Science and Technology KAIST. Дата публикации: 2024-06-20.

Method and apparatus for reinforcement learning training sessions with consideration of resource costing and resource utilization

Номер патента: US11748611B2. Автор: Sumit Sanyal,Tijmen TIELEMAN,Anil HEBBAR,ABDUL Puliyadan Kunnil MUNEER,Abhinav Kaushik,Bharat Kumar Padi,Jeroen Bédorf. Владелец: Individual. Дата публикации: 2023-09-05.

Method and apparatus for reinforcement learning training sessions with consideration of resource costing and resource utilization

Номер патента: US20200265302A1. Автор: Sumit Sanyal,Tijmen TIELEMAN,Anil HEBBAR,ABDUL Puliyadan Kunnil MUNEER,Abhinav Kaushik,Bharat Kumar Padi,Jeroen Bédorf. Владелец: Individual. Дата публикации: 2020-08-20.

Industrial 5G dynamic multi-priority multi-access method based on deep reinforcement learning

Номер патента: US12035380B2. Автор: Xi Jin,Peng Zeng,Xiaoyu Liu,Haibin Yu,Chi XU,Changqing Xia. Владелец: Shenyang Institute of Automation of CAS. Дата публикации: 2024-07-09.

Method and system for event-triggered distributed reinforcement learning for unit commitment optimization and dispatch

Номер патента: US20230297842A1. Автор: Xian Li,Bo Sun,Haoran Zhao,Xiaowen Wang,Shuai LIU,Ruiqi Wang,Lantao XING. Владелец: Shandong University. Дата публикации: 2023-09-21.

Wind turbine yaw offset control based on reinforcement learning

Номер патента: US12037981B2. Автор: Bert Gollnick. Владелец: Siemens Gamesa Renewable Energy AS. Дата публикации: 2024-07-16.

Energy-aware routing based on reinforcement learning

Номер патента: WO2023014250A1. Автор: Konstantinos Vandikas,Lackis ELEFTHERIADIS,Athanasios KARAPANTELAKIS,Marin ORLIC,Maxim TESLENKO,Aneta VULGARAKIS FELJAN,Alexandros NIKOU,Marios DAOUTIS. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2023-02-09.

Method and apparatus for user association based on fuzzy logic and accelerated reinforcement learning for dense cloud wireless network

Номер патента: US20230156556A1. Автор: Wooyeol Choi,Rehenumna Tasnim RODOSHI. Владелец: Industry Academic Cooperation Foundation of Chosun National University. Дата публикации: 2023-05-18.

Energy-aware routing based on reinforcement learning

Номер патента: EP4381709A1. Автор: Konstantinos Vandikas,Lackis ELEFTHERIADIS,Athanasios KARAPANTELAKIS,Marin ORLIC,Maxim TESLENKO,Aneta VULGARAKIS FELJAN,Alexandros NIKOU,Marios DAOUTIS. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2024-06-12.

A low latency reinforcement learning-supported and digital twin-enabled data traffic management and optimization system for 6g smart city infrastructures and an operation method thereof

Номер патента: WO2024162924A1. Автор: Hamed Ahmadi,Berk Canberk,Özgür PALANTÖKEN,Gökhan YURDAKUL,Yağmur YİĞİT,Trang HOANG,Trung Quang DUONG. Владелец: Bts Kurumsal Bi̇li̇şi̇m Teknoloji̇leri̇ Anoni̇m Şi̇rketi̇. Дата публикации: 2024-08-08.

Reinforcement learning system for recommended associations

Номер патента: US20190114560A1. Автор: CUI Lin,Ye Chen,Teodor J. Bally,Himanshu Pande. Владелец: CA Inc. Дата публикации: 2019-04-18.

Deep reinforcement learning for long term rewards in an online connection network

Номер патента: US20210216944A1. Автор: Aastha Jain,Siyuan GAO,Parag Agrawal,Yiou Xiao. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2021-07-15.

Method for reinforcement learning, recording medium storing reinforcement learning program, and reinforcement learning apparatus

Номер патента: US20210063974A1. Автор: Yoshihiro Okawa,Tomotake SASAKI,Hitoshi Yanami,Hidenao Iwane. Владелец: Fujitsu Ltd. Дата публикации: 2021-03-04.

Method for performing reinforcement learning by v2x communication device in autonomous driving system

Номер патента: US20240031786A1. Автор: Sungjin Kim,JaYeong KIM,Sangrim LEE,Ikjoo JUNG,Yeongjun KIM. Владелец: LG ELECTRONICS INC. Дата публикации: 2024-01-25.

Method and apparatus for peer-to-peer energy sharing based on reinforcement learning

Номер патента: US20220122174A1. Автор: Wei-Yu Chiu,Tsan-Po Huang. Владелец: National Tsing Hua University NTHU. Дата публикации: 2022-04-21.

Method and system for reinforcement learning and dual channel action embedding based robotic navigation

Номер патента: US20240028039A1. Автор: Harshad KHADILKAR,Hardik Bharat Meisheri,Omkar Dilip Shelke,Durgesh Kalwar,Pranavi Pathakota. Владелец: Tata Consultancy Services Ltd. Дата публикации: 2024-01-25.

Overload Protection for Edge Cluster Using Two Tier Reinforcement Learning Models

Номер патента: US20230344899A1. Автор: Zhongwen Zhu,Hatem ABOU-ZEID,Aditya Mahajan,Anirudha Jitani. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2023-10-26.

Overload protection for edge cluster using two tier reinforcement learning models

Номер патента: US11943284B2. Автор: Zhongwen Zhu,Hatem ABOU-ZEID,Aditya Mahajan,Anirudha Jitani. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2024-03-26.

Overload protection for edge cluster using two tier reinforcement learning models

Номер патента: EP4226598A1. Автор: Zhongwen Zhu,Hatem ABOU-ZEID,Aditya Mahajan,Anirudha Jitani. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2023-08-16.

Intelligent collision avoidance method for a swarm of unmanned surface vehicles based on deep reinforcement learning

Номер патента: US11990044B2. Автор: Yong Ma,Yulong Wang,Yujiao Zhao. Владелец: Wuhan University of Technology WUT. Дата публикации: 2024-05-21.

Handover optimisation in a cellular network by multi-objective deep reinforcement learning applied by agents deployed in base-stations

Номер патента: EP4391644A1. Автор: Andra LUTU,Ioannis ARAPAKIS,José Rafael Suárez-Varela Maciá. Владелец: Telefonica Innovacion Digital Sl. Дата публикации: 2024-06-26.

Master policy training method of hierarchical reinforcement learning with asymmetrical policy architecture

Номер патента: US20230362196A1. Автор: Chun-yi Lee. Владелец: National Tsing Hua University NTHU. Дата публикации: 2023-11-09.

Periodically cooperative multi-agent reinforcement learning

Номер патента: US20240152774A1. Автор: David Andre,Lam Thanh Nguyen,Grace Taixi Brentano,Gearoid Murphy,Salil Vijaykumar Pradhan. Владелец: X Development LLC. Дата публикации: 2024-05-09.

Explainable reinforcement learning through artificial intelligence-powered creation of pseudo-equivalent expert rules

Номер патента: WO2024165899A1. Автор: Juan Ramiro Moreno,Jose OUTES CARNERO,Paulo Antonio MOREIRA MIJARES,Jose Maria RUIZ AVILES,Adriano MENDO MATEO,Yak Ng MOLINA,Rakibul ISLAM RONY. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2024-08-15.

Optimizing flights of a fleet of aircraft using a reinforcement learning model

Номер патента: US12094349B2. Автор: Dragos D. Margineantu,Alvin L. Sipe,Kirk A. Vining. Владелец: Boeing Co. Дата публикации: 2024-09-17.

Multi-user scheduling method and system based on reinforcement learning for 5g iot system

Номер патента: US20230345451A1. Автор: Hong Zhu,Jun Zhao,Su Pan,Pu Wang,Zibo Li,Xin Qian,Wendi WANG,Honghua XU,Dongxu Zhou,Xuanxuan SHI,Junkang WANG,Zhongzhong XU. Владелец: Nanjing Power Supply Co of State Grid Jiangsu Electric Power Co Ltd. Дата публикации: 2023-10-26.

Tcr engineering with deep reinforcement learning for increasing efficacy and safety of tcr-t immunotherapy

Номер патента: US20230304189A1. Автор: Hans Peter Graf,Renqiang Min. Владелец: NEC Laboratories America Inc. Дата публикации: 2023-09-28.

Inverse reinforcement learning by density ratio estimation

Номер патента: WO2016021210A1. Автор: Kenji Doya,Eiji UCHIBE. Владелец: OKINAWA INSTITUTE OF SCIENCE AND TECHNOLOGY SCHOOL CORPORATION. Дата публикации: 2016-02-11.

Tcr engineering with deep reinforcement learning for increasing efficacy and safety of tcr-t immunotherapy

Номер патента: WO2023183121A1. Автор: Hans Peter Graf,Renqiang Min. Владелец: NEC Laboratories America, Inc.. Дата публикации: 2023-09-28.

Power grid reactive voltage control method based on two-stage deep reinforcement learning

Номер патента: US20210356923A1. Автор: Tian Xia,Bin Wang,Qinglai Guo,Hongbin Sun,Wenchuan Wu,Haotian Liu. Владелец: TSINGHUA UNIVERSITY. Дата публикации: 2021-11-18.

Power grid reactive voltage control method based on two-stage deep reinforcement learning

Номер патента: US11442420B2. Автор: Tian Xia,Bin Wang,Qinglai Guo,Hongbin Sun,Wenchuan Wu,Haotian Liu. Владелец: TSINGHUA UNIVERSITY. Дата публикации: 2022-09-13.

Signal control apparatus and signal control method based on reinforcement learning

Номер патента: US11823573B2. Автор: Tae Wook Choi. Владелец: Laon Road Inc. Дата публикации: 2023-11-21.

Recording medium, reinforcement learning method, and reinforcement learning apparatus

Номер патента: US11645574B2. Автор: Tomotake SASAKI,Hitoshi Yanami,Hirokazu Anai,Hidenao Iwane,Kenji Doya,Eiji UCHIBE. Владелец: Okinawa Institute of Science and Technology School Corp. Дата публикации: 2023-05-09.

Multi-agent deep reinforcement learning for dynamically controlling electrical equipment in buildings

Номер патента: US20210200163A1. Автор: Arunchandar VASAN,Srinarayana NAGARATHINAM,Avinash Achar. Владелец: Tata Consultancy Services Ltd. Дата публикации: 2021-07-01.

System and method for clinical decision support system with inquiry based on reinforcement learning

Номер патента: US11763944B2. Автор: Wei Fan,Kun Wang,Yusheng Xie,Nan Du,Min Tu,Xiaozhong Chen,Shangqing ZHANG. Владелец: Tencent America LLC. Дата публикации: 2023-09-19.

Inverse reinforcement learning by density ratio estimation

Номер патента: EP3178040A1. Автор: Kenji Doya,Eiji UCHIBE. Владелец: Okinawa Institute of Science and Technology School Corp. Дата публикации: 2017-06-14.

Direct inverse reinforcement learning with density ratio estimation

Номер патента: WO2017159126A1. Автор: Kenji Doya,Eiji UCHIBE. Владелец: OKINAWA INSTITUTE OF SCIENCE AND TECHNOLOGY SCHOOL CORPORATION. Дата публикации: 2017-09-21.

Direct inverse reinforcement learning with density ratio estimation

Номер патента: EP3430578A1. Автор: Kenji Doya,Eiji UCHIBE. Владелец: Okinawa Institute of Science and Technology School Corp. Дата публикации: 2019-01-23.

Reinforcement learning-based channel access control

Номер патента: KR102289471B1. Автор: 정철,김형석,알리 라시드. Владелец: 세종대학교산학협력단. Дата публикации: 2021-08-11.

Method for intelligent traffic scheduling based on deep reinforcement learning

Номер патента: US20230362095A1. Автор: Jing Cheng,Xiao Zhang,Erlin TIAN,Wanwei HUANG,Qiuwen ZHANG,Weide LIANG,Xiangyu ZHENG. Владелец: Zhengzhou University of Light Industry. Дата публикации: 2023-11-09.

Deep reinforcement learning for robotic manipulation

Номер патента: US11897133B2. Автор: Sergey LEVINE,Shixiang Gu,Ethan Holly,Timothy LILLICRAP. Владелец: Google LLC. Дата публикации: 2024-02-13.

Method and apparatus for reinforcement learning based energy bidding

Номер патента: US11063434B2. Автор: Wei-Yu Chiu,Chan-Wei Hu. Владелец: National Tsing Hua University NTHU. Дата публикации: 2021-07-13.

Reinforcement learning in real-time communications

Номер патента: US20210012227A1. Автор: Thang Duong,Ross Garrett Cutler,David Yuheng ZHAO,Martin Ellis,Joyce S FANG. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2021-01-14.

Reinforcement learning in real-time communications

Номер патента: EP3997853A1. Автор: Thang Duong,Ross Garrett Cutler,David Yuheng ZHAO,Martin Ellis,Joyce S. FANG. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2022-05-18.

Reinforcement learning method for driver incentives: generative adversarial network for driver-system interactions

Номер патента: US11861643B2. Автор: Yang Yu,Jieping Ye,Zhiwei Qin,Qingyang Li,Yiping MENG,Wenjie SHANG. Владелец: Beijing Didi Infinity Technology and Development Co Ltd. Дата публикации: 2024-01-02.

Reinforcement learning model for selecting a network function producer

Номер патента: WO2023140758A1. Автор: Ioannis Fikouras,Lackis ELEFTHERIADIS,Athanasios KARAPANTELAKIS,Maxim TESLENKO,Alessandro Previti. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2023-07-27.

Constraint adaptor for reinforcement learning control

Номер патента: EP3824356A1. Автор: Abraham Goldsmith,Uros Kalabic,Zaojian LI. Владелец: Mitsubishi Electric Corp. Дата публикации: 2021-05-26.

Constraint adaptor for reinforcement learning control

Номер патента: WO2021033380A1. Автор: Abraham Goldsmith,Uros Kalabic,Zhaojian Li. Владелец: Mitsubishi Electric Corporation. Дата публикации: 2021-02-25.

System and Method for Building Ensemble Models Using Competitive Reinforcement Learning

Номер патента: US20210248517A1. Автор: Manjunath Ramachandra Iyer,Chandrashekar Bangalore Nagaraj,Shashidhar Soppin. Владелец: Wipro Ltd. Дата публикации: 2021-08-12.

Radio access network control with deep reinforcement learning

Номер патента: US20230095706A1. Автор: YU Chen,Jie Chen,Huahui Wang,Ganesh Krishnamurthi,Wenjie Zhao,Huijing Yang. Владелец: AT&T INTELLECTUAL PROPERTY I LP. Дата публикации: 2023-03-30.

Deep reinforcement learning for robotic manipulation

Номер патента: US20240131695A1. Автор: Sergey LEVINE,Shixiang Gu,Ethan Holly,Timothy LILLICRAP. Владелец: Google LLC. Дата публикации: 2024-04-25.

USV formation path-following method based on deep reinforcement learning

Номер патента: US11914376B2. Автор: HAO LI,Yong Ma,Yujiao Zhao. Владелец: Wuhan University of Technology WUT. Дата публикации: 2024-02-27.

Radio access network control with deep reinforcement learning

Номер патента: US20210241090A1. Автор: YU Chen,Jie Chen,Huahui Wang,Ganesh Krishnamurthi,Wenjie Zhao,Huijing Yang. Владелец: AT&T INTELLECTUAL PROPERTY I LP. Дата публикации: 2021-08-05.

Application of simple random search approach for reinforcement learning to controller tuning parameters

Номер патента: US20210132587A1. Автор: Nathan Lawrence,Gregory E. Stewart,Philip D. LOEWEN,Bhushan Gopaluni. Владелец: Honeywell International Inc. Дата публикации: 2021-05-06.

Method and apparatus for reinforcement learning based energy bidding

Номер патента: US20200366094A1. Автор: Wei-Yu Chiu,Chan-Wei Hu. Владелец: National Tsing Hua University NTHU. Дата публикации: 2020-11-19.

Decentralized policy gradient descent and ascent for safe multi-agent reinforcement learning

Номер патента: US20230113168A1. Автор: Songtao Lu,Lior Horesh,Tianyi Chen,Pin-Yu Chen,Sijia Liu. Владелец: International Business Machines Corp. Дата публикации: 2023-04-13.

System and method for reconfigurable intelligent surface (ris)-assisted energy-efficient (ee) radio access network (ran) using hierarchical reinforcement learning

Номер патента: WO2023214384A1. Автор: Hao Zhou,Majid Bavand,Raimundas Gaigalas,Long Kong,Steve FURR,Melike Erol-Kantarci,Medhat Elsayed. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2023-11-09.

Self-powered integrated sensing and communication interactive method of high-speed railway based on hierarchical deep reinforcement learning

Номер патента: US20230196119A1. Автор: QIANG LI,ZHUANG Ling,Long Lv,Zhijun Li,Hailong Li,Fengye Hu,Wuliji Nashun,Tanda Liu,Difei Jia. Владелец: Jilin University. Дата публикации: 2023-06-22.

Reinforcement learning systems and methods for inventory control and optimization

Номер патента: WO2020088962A1. Автор: Rodrigo Alejandro Acuna Agost,Thomas Fiig,Nicolas Bondoux,Anh-Quan Nguyen. Владелец: AMADEUS S.A.S.. Дата публикации: 2020-05-07.

Reinforcement learning systems and methods for inventory control and optimization

Номер патента: CA3117745A1. Автор: Rodrigo Alejandro Acuna Agost,Thomas Fiig,Nicolas Bondoux,Anh-Quan Nguyen. Владелец: Amadeus SAS. Дата публикации: 2020-05-07.

Reinforcement learning systems and methods for inventory control and optimization

Номер патента: EP3874428A1. Автор: Rodrigo Alejandro Acuna Agost,Thomas Fiig,Nicolas Bondoux,Anh-Quan Nguyen. Владелец: Amadeus SAS. Дата публикации: 2021-09-08.

Time-varying reinforcement learning for robust adaptive estimator design with application to HVAC flow control

Номер патента: US20230341141A1. Автор: Mouhacine Benosman,Saleh NABI,Saviz Mowlavi. Владелец: Mitsubishi Electric Research Laboratories Inc. Дата публикации: 2023-10-26.

Creating a global Reinforcement Learning (RL) model from subnetwork RL agents

Номер патента: US20230216747A1. Автор: David CÔTÉ,Christopher Barber,Shervin Shirmohammadi,Sa'di Altamimi. Владелец: Ciena Corp. Дата публикации: 2023-07-06.

Model-assisted deep reinforcement learning based scheduling in wireless networks

Номер патента: NL2029288A. Автор: Vannithamby Rath,Balakrishnan Ravikumar,SOMAYAZULU VALLABHAJOSYULA,Anand Arjun. Владелец: Intel Corp. Дата публикации: 2022-06-03.

Antenna phase error compensation with reinforced learning

Номер патента: WO2023170452A1. Автор: Xixian Chen,Jonas Karlsson,Guoqiang Lu,Edward Mah,Haomin LI. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2023-09-14.

Method and system for training autonomous driving agent on basis of deep reinforcement learning

Номер патента: EP3936963A2. Автор: Minsu Kim,Jinyoung Choi,Kay PARK,Joonho SEO,Sangok Seok. Владелец: Naver Labs Corp. Дата публикации: 2022-01-12.

Task-oriented Dialogue System with Hierarchical Reinforcement Learning

Номер патента: US20220130546A1. Автор: Zhongyu Wei. Владелец: Individual. Дата публикации: 2022-04-28.

Providing trained reinforcement learning systems

Номер патента: US20240211794A1. Автор: WANG Zhang,Alexandre Megretski,Subhro Das,Luca Daniel,Lam Minh Nguyen. Владелец: International Business Machines Corp. Дата публикации: 2024-06-27.

Reinforcement learning-based optimization of manufacturing lines

Номер патента: US20230176552A1. Автор: Kartavya Neema,Brice Hoani Valentin Chung,Amir Hossein Jafari. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2023-06-08.

Environment Aware Application-based Resource Management Using Reinforcement Learning

Номер патента: US20210209419A1. Автор: Reetesh Mukul,Bhakti Ramnani,Sachin Tripathi,Prabal Kumar Ghosh. Владелец: Adobe Inc. Дата публикации: 2021-07-08.

Data valuation and sensor data management

Номер патента: US20200128093A1. Автор: Stephen J. Todd. Владелец: EMC IP Holding Co LLC. Дата публикации: 2020-04-23.

Reinforcement learning-based optimization of manufacturing lines

Номер патента: WO2023101785A1. Автор: Kartavya Neema,Brice Hoani Valentin Chung,Amir Hossein Jafari. Владелец: Microsoft Technology Licensing, LLC.. Дата публикации: 2023-06-08.

Context-based data valuation and transmission

Номер патента: US11962664B1. Автор: John Hayes,Volkmar Uhlig. Владелец: Ghost Autonomy Inc. Дата публикации: 2024-04-16.

Automatic cinematography system using reinforcement learning

Номер патента: US12058469B2. Автор: Haohong Wang,Zixiao YU. Владелец: TCL Research America Inc. Дата публикации: 2024-08-06.

Apparatus and systems for power system protective relay control using reinforcement learning

Номер патента: US20210334441A1. Автор: Dongqi WU,Le Xie,Xiangtian Zheng,Miroslav Begovic,Dileep Kalathil. Владелец: TEXAS A&M UNIVERSITY SYSTEM. Дата публикации: 2021-10-28.

Search-query suggestions using reinforcement learning

Номер патента: US20230140702A1. Автор: Praveen Kumar Bodigutla. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2023-05-04.

Implementing reinforcement learning based flash control

Номер патента: US20140359197A1. Автор: Ashish Jagmohan,Michele M. Franceschini,Hillery C. Hunter,Janani Mukundan. Владелец: International Business Machines Corp. Дата публикации: 2014-12-04.

Resource isolation using reinforcement learning and domain-specific constraints

Номер патента: US8429097B1. Автор: Swaminathan Sivasubramanian,Parikshit S. Pol. Владелец: Amazon Technologies Inc. Дата публикации: 2013-04-23.

Automated prediction of computing resource performance scaling using reinforcement learning

Номер патента: US11775352B1. Автор: Samir KAKKAR,Nikhil Krishnegowda,Saloni Priyani. Владелец: FMR LLC. Дата публикации: 2023-10-03.

System and method for generating a floorplan for a digital circuit using reinforcement learning

Номер патента: US20230252215A1. Автор: Zhanguang Zhang,Yingxue Zhang,Wulong LIU,Mohammad AMINI. Владелец: Individual. Дата публикации: 2023-08-10.

Systems and methods for semantic separation of multiple intentions in text data using reinforcement learning

Номер патента: US20240160847A1. Автор: Prakash Ranganathan,Miruna JAYAKRISHNASAMY. Владелец: VERIZON PATENT AND LICENSING INC. Дата публикации: 2024-05-16.

Reinforcement learning apparatus and reinforcement learning method for optimizing position of object based on design data

Номер патента: US20230086563A1. Автор: Sung Min Lee,Dong Hyun Lee,Won Young Cho,Ye Rin MIN,Yeon Sang YU,Ba Da KIM. Владелец: Agilesoda Inc. Дата публикации: 2023-03-23.

System and method for designing system on chip (SoC) circuits through artificial intelligence and reinforcement learning

Номер патента: US09792397B1. Автор: Nagendra Nagaraja. Владелец: Alphaics Corp. Дата публикации: 2017-10-17.

Systems and methods for implementing reinforcement learning in task-facilitation services

Номер патента: EP4396734A1. Автор: Yoky Matsuoka,Lingyun Liu,Nitin Viswanathan,Gwendolyn W. van der Linden,Malia Beaulieu,Benjamin Deming,Sean Paterson. Владелец: Yohana LLC. Дата публикации: 2024-07-10.

K-nearest multi-agent reinforcement learning for collaborative tasks with variable number of agents

Номер патента: US20230306084A1. Автор: Haiyan Wang,Hsiu-Khuern Tang,Chetan GUPTA,Hamed KHORASGANI. Владелец: HITACHI LTD. Дата публикации: 2023-09-28.

Reinforcement learning based correction of timing failures

Номер патента: GB2623541A. Автор: BECK Manuel,von der Ehe Marvin,Boronowsky Gregor,Niklas Stegmaier Jan,Friedmann Simon Hermann. Владелец: International Business Machines Corp. Дата публикации: 2024-04-24.

Reinforcement learning space state pruning using restricted boltzmann machines

Номер патента: US20240231938A1. Автор: Eduardo Vera Sousa,Yanexis Pupo Toledo,Micael Veríssimo de Araújo. Владелец: Dell Products LP. Дата публикации: 2024-07-11.

Artificial intelligence (ai) model trained using clustering and reinforcement learning for data de-identification engine

Номер патента: US20240303360A1. Автор: Richard Vidal,Laetitia KAMENI,Laura Wendy Hélène Sylvie Angèle Degioanni,Nantomiaro Ramanjakanoro Ralibera. Владелец: Accenture Global Solutions Ltd. Дата публикации: 2024-09-12.

Systems and methods for implementing reinforcement learning in task-facilitation services

Номер патента: AU2022339969A1. Автор: Yoky Matsuoka,Lingyun Liu,Nitin Viswanathan,Gwendolyn W. van der Linden,Malia Beaulieu,Benjamin Deming,Sean Paterson. Владелец: Yohana LLC. Дата публикации: 2024-03-14.

Persona based co-operative multi-agent reinforcement learning to enhance user experience

Номер патента: US11847679B2. Автор: Priya Shanmugasundaram. Владелец: Dell Products LP. Дата публикации: 2023-12-19.

Systems and methods for implementing reinforcement learning in task-facilitation services

Номер патента: CA3230724A1. Автор: Yoky Matsuoka,Lingyun Liu,Nitin Viswanathan,Gwendolyn W. van der Linden,Malia Beaulieu,Benjamin Deming,Sean Paterson. Владелец: Yohana LLC. Дата публикации: 2023-03-09.

Infrastructure optimization controlled by reinforcement-learning-based agent controllers

Номер патента: US20240036530A1. Автор: Shashi Kumar,Marius VILCU,Nicholas Mark Grant Stephen,Madan Singhal,Jad EI-Zein. Владелец: VMware LLC. Дата публикации: 2024-02-01.

System and method for designing system on chip (soc) circuits through artificial intelligence and reinforcement learning

Номер патента: WO2018128653A1. Автор: Nagendra Nagaraja. Владелец: Alphaics Corporation. Дата публикации: 2018-07-12.

Apparatus and method for reinforcement learning for object position optimization based on semiconductor design data

Номер патента: US20230205954A1. Автор: Junho Kim,Kyuwon CHOI,Pham-Tuyen LE,Ye-Rin MIN,DoKyoon YOON. Владелец: Agilesoda Inc. Дата публикации: 2023-06-29.

Reducing power consumption of a data center utilizing reinforcement learning framework

Номер патента: US20210405727A1. Автор: Michael David Shepherd,Ashutosh Singh. Владелец: Dell Products LP. Дата публикации: 2021-12-30.

Constraint-based index tuning in database management systems utilizing reinforcement learning

Номер патента: US20230315702A1. Автор: Surajit Chaudhuri,Wentao Wu,Chi Wang,Vivek Ravindranath Narasayya,Tarique Ashraf Siddiqui. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2023-10-05.

Reinforcement learning and nonlinear programming based system design

Номер патента: US20240160802A1. Автор: Johan De Kleer,Ion MATEI,Maksym I. Zhenirovskyy. Владелец: Palo Alto Research Center Inc. Дата публикации: 2024-05-16.

Content personalization based on reinforcement learning

Номер патента: US20240259634A1. Автор: Dhananjay Lal,Kamal J. Koshy,Reda Harb. Владелец: Adeia Guides Inc. Дата публикации: 2024-08-01.

Method for controlling a laser processing operation by means of a reinforcement learning agent and laser material processing head using the same

Номер патента: US09373163B2. Автор: Ingo Stork Genannt Wersborg,Adrian Garcea. Владелец: Precitec Itm Gmbh. Дата публикации: 2016-06-21.

Constraint-based index tuning in database management systems utilizing reinforcement learning

Номер патента: US12066993B2. Автор: Surajit Chaudhuri,Wentao Wu,Chi Wang,Vivek Ravindranath Narasayya,Tarique Ashraf Siddiqui. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2024-08-20.

Reinforcement learning method for video encoder

Номер патента: US20200344472A1. Автор: Yun Liang,Yung-Han Ho,Wen-Hsiao Peng,Guo-Lun Jin. Владелец: National Chiao Tung University NCTU. Дата публикации: 2020-10-29.

Reinforcement learning method for video encoder

Номер патента: US11166017B2. Автор: Yun Liang,Yung-Han Ho,Wen-Hsiao Peng,Guo-Lun Jin. Владелец: National Chiao Tung University NCTU. Дата публикации: 2021-11-02.

Reinforcement learning-based remote control device and method for an unmanned aerial vehicle

Номер патента: US20200183379A1. Автор: Yong Guk Kim,Sang Yun SHIN,Yong Won Kang. Владелец: INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY. Дата публикации: 2020-06-11.

Reinforcement learning (rl) based chip design optimization using trained graph convolutional networks (gcn) for ultra-fast cost function calculation

Номер патента: US20240169135A1. Автор: Joseph Robb WALSTON,Stylianos DIAMANTIDIS,Akash LEVY. Владелец: Synopsys Inc. Дата публикации: 2024-05-23.

Layout design system using deep reinforcement learning and learning method thereof

Номер патента: US20240126971A1. Автор: Taehyun Kim,Hyunjoong Kim,Jichull Jeong,Euihyun Cheon. Владелец: SAMSUNG ELECTRONICS CO LTD. Дата публикации: 2024-04-18.

Deep reinforcement learning-based integrated circuit design system using partitioning and deep reinforcement learning-based integrated circuit design method using partitioning

Номер патента: US20230385506A1. Автор: DoKyoon YOON,Pham Tuyen LE. Владелец: Agilesoda Inc. Дата публикации: 2023-11-30.

Deep reinforcement learning based wireless network simulator

Номер патента: US20230135745A1. Автор: Qiang Liu,Nak Jung Choi. Владелец: NOKIA SOLUTIONS AND NETWORKS OY. Дата публикации: 2023-05-04.

Dymamic control of a manufacturing process using deep reinforcement learning

Номер патента: US20220373980A1. Автор: Donghyun Kim,Brian W. Anthony,Sangwoon Kim. Владелец: Massachusetts Institute of Technology. Дата публикации: 2022-11-24.

Constraint-based index tuning in database management systems utilizing reinforcement learning

Номер патента: WO2023191964A1. Автор: Surajit Chaudhuri,Wentao Wu,Chi Wang,Vivek Ravindranath Narasayya,Tarique Ashraf Siddiqui. Владелец: Microsoft Technology Licensing, LLC. Дата публикации: 2023-10-05.

Swarm multi-agent reinforcement learning-based pipeline for workload placement

Номер патента: US20240012685A1. Автор: Hugo de Oliveira Barbalho,Eduardo Vera Sousa. Владелец: Dell Products LP. Дата публикации: 2024-01-11.

Deep reinforcement learning based wireless network simulator

Номер патента: EP4175245A1. Автор: Qiang Liu,Nak Jung Choi. Владелец: NOKIA SOLUTIONS AND NETWORKS OY. Дата публикации: 2023-05-03.

Leveraging sensor data valuation

Номер патента: US20200126095A1. Автор: Stephen J. Todd. Владелец: EMC IP Holding Co LLC. Дата публикации: 2020-04-23.

Reinforcement learning to perform localization, segmentation, and classification on biomedical images

Номер патента: WO2022076367A1. Автор: Hrithwik SHALU,Joseph N. Stember. Владелец: Memorial Sloan Kettering Cancer Center. Дата публикации: 2022-04-14.

Multi-chiller scheduling using reinforcement learning with transfer learning for power consumption prediction

Номер патента: US20210303998A1. Автор: Arunchandar VASAN,Srinarayana NAGARATHINAM,Malini POONI VENKAT,Praveen Manoharan. Владелец: Tata Consultancy Services Ltd. Дата публикации: 2021-09-30.

Simulation augmented reinforcement learning for real-time content selection

Номер патента: US11847670B1. Автор: XING Zhao,Xinyu Zhou,Qie Hu Huang,Kirtan Modi,Jae In Cho,Jiahui Jeff Wang. Владелец: Amazon Technologies Inc. Дата публикации: 2023-12-19.

Reinforcement learning to perform localization, segmentation, and classification on biomedical images

Номер патента: US20230377195A1. Автор: Hrithwik SHALU,Joseph N. Stember. Владелец: Memorial Sloan Kettering Cancer Center. Дата публикации: 2023-11-23.

Reinforcement learning to perform localization, segmentation, and classification on biomedical images

Номер патента: CA3194826A1. Автор: Hrithwik SHALU,Joseph N. Stember. Владелец: Memorial Sloan Kettering Cancer Center. Дата публикации: 2022-04-14.

Reinforcement learning to perform localization, segmentation, and classification on biomedical images

Номер патента: EP4226320A1. Автор: Hrithwik SHALU,Joseph N. Stember. Владелец: Memorial Sloan Kettering Cancer Center. Дата публикации: 2023-08-16.

Reinforcement learning to perform localization, segmentation, and classification on biomedical images

Номер патента: AU2021358905A9. Автор: Hrithwik SHALU,Joseph N. Stember. Владелец: Memorial Sloan Kettering Cancer Center. Дата публикации: 2024-06-20.

Multi-chiller scheduling using reinforcement learning with transfer learning for power consumption prediction

Номер патента: EP3885850A1. Автор: Arunchandar VASAN,Srinarayana NAGARATHINAM,Malini POONI VENKAT,Praveen Manoharan. Владелец: Tata Consultancy Services Ltd. Дата публикации: 2021-09-29.

Reinforcement learning agent to measure robustness of black-box image classification models

Номер патента: US20240193927A1. Автор: Soumyendu Sarkar,Vineet Gundecha,Sahand Ghorbanpour,Avisek Naug,Ashwin Ramesh Babu,Seyed Sajad Mousavi. Владелец: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP. Дата публикации: 2024-06-13.

Mri reconstruction based on reinforcement learning

Номер патента: US20240331222A1. Автор: Zhang Chen,Xiao Chen,Terrence Chen,Shanhui Sun,Yikang Liu. Владелец: Shanghai United Imaging Intelligence Co Ltd. Дата публикации: 2024-10-03.

Supply chain optimization with reinforcement learning

Номер патента: WO2024068571A1. Автор: Patric HAMMLER,Nicolas Oliver RIESTERER. Владелец: F. Hoffmann-La Roche AG. Дата публикации: 2024-04-04.

Learning ordinal representations for deep reinforcement learning based object localization

Номер патента: US20220327814A1. Автор: Renqiang Min,Shaobo HAN,Tingfeng LI. Владелец: NEC Laboratories America Inc. Дата публикации: 2022-10-13.

Self-adaptive Energy-saving Control Method and System for Smart Street Lamps Based on Deep Reinforcement Learning

Номер патента: AU2021105964A4. Автор: Huamin Chen,Jiaxin Liu,Shaofu Lin. Владелец: Individual. Дата публикации: 2021-10-28.

Method for performing reinforcement learning by v2x communication device in autonomous driving system

Номер патента: US20230368584A1. Автор: JaYeong KIM,Sangrim LEE,Hojae Lee,Ikjoo JUNG,Yeongjun KIM. Владелец: LG ELECTRONICS INC. Дата публикации: 2023-11-16.

Deep reinforcement learning-enabled cryo-em data collection

Номер патента: US20230288354A1. Автор: Quanfu Fan,Michael Cianfrocco,Yilai Li,Seychelle Vos. Владелец: International Business Machines Corp. Дата публикации: 2023-09-14.

Bound enhanced reinforcement learning system for distribution supply chain management

Номер патента: US20240265339A1. Автор: Haiyan Wang,Hsiu-Khuern Tang,Chetan GUPTA,Wenhuan SUN,Atsuki KIUCHI,Ibrahim EL-SHAR. Владелец: HITACHI LTD. Дата публикации: 2024-08-08.

Image segmentation using multi-agent deep reinforcement learning

Номер патента: WO2021244754A1. Автор: Tinghuai Wang,Guangming Wang,Kuan Eeik TAN. Владелец: Huawei Technologies Co., Ltd.. Дата публикации: 2021-12-09.

Nodal graph and reinforcement-learning model based systems and methods for managing moving agents

Номер патента: US20240029012A1. Автор: Rohit Gupta,Prashant Tiwari,Nejib Ammar,Akila Ganlath. Владелец: Toyota Motor Engineering and Manufacturing North America Inc. Дата публикации: 2024-01-25.

Reinforcement learning method and reinforcement learning system

Номер патента: US20200285204A1. Автор: Yoshihiro Okawa,Tomotake SASAKI,Hitoshi Yanami,Hidenao Iwane,Junichi Shigezumi. Владелец: Fujitsu Ltd. Дата публикации: 2020-09-10.

Methods and apparatus for natural language processing and reinforcement learning to increase data analysis and efficiency

Номер патента: EP4266226A1. Автор: Vijay Perincherry,Janine GELBART,Marc INZELSTEIN. Владелец: Indiggo LLC. Дата публикации: 2023-10-25.

Methods and apparatus for natural language processing and reinforcement learning to increase data analysis and efficiency

Номер патента: US20230334387A1. Автор: Vijay Perincherry,Janine GELBART,Marc INZELSTEIN. Владелец: Indiggo LLC. Дата публикации: 2023-10-19.

Selecting automation scripts using reinforced learning

Номер патента: US20220188213A1. Автор: Sergio Varga,Igor Monteiro Vieira,Marcelo Mota Manhaes,Rogerio Baldini Das Neves,Joao Luiz Todari. Владелец: Kyndryl Inc. Дата публикации: 2022-06-16.

User plane selection using reinforcement learning

Номер патента: EP4022958A4. Автор: Dinand Roeland,Jaeseong JEONG,Andreas YOKOBORI SÄVÖ. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2023-08-30.

System and method for fuzzing test orchestration using reinforcement learning

Номер патента: US11734161B2. Автор: Andrew R. Calvano. Владелец: Raytheon Co. Дата публикации: 2023-08-22.

Maze-driven self-diagnostics using reinforcement learning

Номер патента: CA3123807A1. Автор: Kenneth Armstrong,Chunzhi CHEN,Guo Rong Zheng. Владелец: Mitel Cloud Services Inc. Дата публикации: 2022-01-06.

Apparatus and method for frequency allocation using reinforced learning for low earth orbit satellite network

Номер патента: US20230132791A1. Автор: Bon Jun Ku,Dae Sub Oh,Ji Hyeon Yun,Chang Hee JOO,Tae Gun AN,Hae Sung JO. Владелец: Electronics and Telecommunications Research Institute ETRI. Дата публикации: 2023-05-04.

Request routing system using reinforcement learning

Номер патента: US11811645B1. Автор: Sarandeth Reth. Владелец: Microsoft Technology Licensing LLC. Дата публикации: 2023-11-07.

Request routing system using reinforcement learning

Номер патента: WO2023235056A1. Автор: Sarandeth Reth. Владелец: Microsoft Technology Licensing, LLC. Дата публикации: 2023-12-07.

Dual connectivity handover optimization using reinforcement learning

Номер патента: WO2023199264A1. Автор: Majid Bavand,Raimundas Gaigalas,Steve FURR,Pedro Enrique ITURRIA RIVERA,Melike Erol-Kantarci,Medhat Elsayed. Владелец: Telefonaktiebolaget lM Ericsson (publ). Дата публикации: 2023-10-19.

Environment prediction using reinforcement learning

Номер патента: US20190259051A1. Автор: David Silver,Tom Schaul,Hado Philip VAN HASSELT,Matteo HESSEL. Владелец: DeepMind Technologies Ltd. Дата публикации: 2019-08-22.

Method and electronic device for providing information by using reinforcement learning

Номер патента: US20240221018A1. Автор: Minsoo Kim,Taehun Kim,Yunhu JI,Eunkyu OH,Hongjun JANG. Владелец: SAMSUNG ELECTRONICS CO LTD. Дата публикации: 2024-07-04.

Building control system using reinforcement learning

Номер патента: US20240329610A1. Автор: Gerald A. Asp,Michael M. Huber,Daniel A. Mellenthin,Jeffrey J. G. Senzig. Владелец: Tyco Fire and Security GmbH. Дата публикации: 2024-10-03.

Using reinforcement learning to scale queue-based services

Номер патента: US11700302B2. Автор: Michael Friedrich,Stefanie Grunwald. Владелец: Adobe Inc. Дата публикации: 2023-07-11.

Network node and a method performed in a wireless communication network for handling configuration of radio network nodes using reinforcement learning

Номер патента: US20230319597A1. Автор: Rafia Inam,Kaushik Dey. Владелец: Telefonaktiebolaget LM Ericsson AB. Дата публикации: 2023-10-05.

Data valuation based on development and deployment velocity

Номер патента: US09778931B2. Автор: Stephen Todd,Aidan J. O'Brien. Владелец: EMC IP Holding Co LLC. Дата публикации: 2017-10-03.

Metadata-based data valuation

Номер патента: US20200097446A1. Автор: Narayanan Krishnakumar,Qing Ye,Stephen Todd,Anand Singh,Sudhir Vijendra. Владелец: EMC IP Holding Co LLC. Дата публикации: 2020-03-26.

Systems, methods, and computer-readable media for secure and private data valuation and transfer

Номер патента: WO2023193703A1. Автор: Yong Zhang,Gursimran Singh,Lanjun Wang,Ahnaf Tazwar Ayub,Chendi WANG. Владелец: Huawei Cloud Computing Technologies Co., Ltd.. Дата публикации: 2023-10-12.

Systems, methods, and computer-readable media for secure and private data valuation and transfer

Номер патента: US20230315885A1. Автор: Yong Zhang,Gursimran Singh,Lanjun Wang,Ahnaf Tazwar Ayub,Chendi WANG. Владелец: Individual. Дата публикации: 2023-10-05.

Data valuation based on development and deployment velocity

Номер патента: US20170185396A1. Автор: Stephen Todd,Aidan J. O'Brien. Владелец: EMC IP Holding Co LLC. Дата публикации: 2017-06-29.

Method and system for performing domain level scheduling of an application in a distributed multi-tiered computing environment using reinforcement learning

Номер патента: US20230333884A1. Автор: Said Tabet,William Jeffery White. Владелец: Dell Products LP. Дата публикации: 2023-10-19.

Rectilinear-block placement method for early floorplan using reinforcement learning

Номер патента: US20240311542A1. Автор: Te-Wei Chen,Chun-Chih Yang,Wei-Hsien Lin,Tai-Lai Tung,Yi-Ying Liao,Chih-Wei Ko,Kun-Yu Wang,Bo-Jiun HSU,Sheng-Tai Tseng,Jen-Wei Lee,Ronald Kuo-Hua Ho. Владелец: MediaTek Inc. Дата публикации: 2024-09-19.

Method for self-supervised representation learning for vision-based reinforcement learning robust to visual distraction, data inference apparatus using self-supervised learning model, and storage medium storing instructions to perform method for self-supervised representation learning

Номер патента: US20240273792A1. Автор: Yusung KIM. Владелец: Sungkyunkwan University Research and Business Foundation. Дата публикации: 2024-08-15.

Efficient adaption of robot control policy for new task using meta-learning based on meta-imitation learning and meta-reinforcement learning

Номер патента: US12083678B2. Автор: Alexander Herzog,Yunfei Bai,Mrinal Kalakrishnan,Paul WOHLHART,Eric Jang,Chelsea FINN,Seyed Mohammad Khansari Zadeh,Sergey LEVINE,Allan ZHOU,Daniel KAPPLER. Владелец: Google LLC. Дата публикации: 2024-09-10.

Multi-intelligence federal reinforcement learning-based vehicle-road cooperative control system and method at complex intersection

Номер патента: US11862016B1. Автор: Hai Wang,Long Chen,Qingchao Liu,Yicheng Li,Yingfeng Cai,Chaochun YUAN,Sikai Lu. Владелец: Jiangsu University. Дата публикации: 2024-01-02.

Multi-intelligence federal reinforcement learning-based vehicle-road cooperative control system and method at complex intersection

Номер патента: US20240038066A1. Автор: Hai Wang,Long Chen,Qingchao Liu,Yicheng Li,Yingfeng Cai,Chaochun YUAN,Sikai Lu. Владелец: Jiangsu University. Дата публикации: 2024-02-01.

Номер патента: US20230125620A1. Автор: Supriya Agrawal,Sagar Kumar VERMA,Srinarayana NAGARATHINAM,Rajesh Jayaprakash,Venkatesh Ramanathan,Ulka Shrotri,Aabriti Dutta. Владелец: Tata Consultancy Services Ltd. Дата публикации: 2023-04-27.

Inferring device, training device, inferring method, method of generating reinforcement learning model and method of generating molecular structure

Номер патента: US20240079099A1. Автор: Toshiki Kataoka,Ryuichiro Ishitani. Владелец: Preferred Networks Inc. Дата публикации: 2024-03-07.

Reinforcement learning for final setups and intermediate staging in clear tray aligners

Номер патента: WO2024127303A1. Автор: Jonathan D. Gandrud,Nitsan Ben-Gal Nguyen,Haleh Hagh-Shenas,Seyed Amir Hossein Hosseini,Alireza SADEGHI,Mariah Sonja Pereira Penha,Haozhu WANG,Francis J. T. YATES. Владелец: 3M INNOVATIVE PROPERTIES COMPANY. Дата публикации: 2024-06-20.

Method for automatically regulating explicit congestion notification of data center network based on multi-agent reinforcement learning

Номер патента: US20240080270A1. Автор: Ting Wang,Kai Cheng,Puyu CAI. Владелец: EAST CHINA NORMAL UNIVERSITY. Дата публикации: 2024-03-07.

Deep reinforcement learning-based random access method for low earth orbit satellite network and terminal for the operation

Номер патента: US11832314B2. Автор: Ju Hyung Lee,Young Chai Ko. Владелец: KOREA UNIVERSITY RESEARCH AND BUSINESS FOUNDATION. Дата публикации: 2023-11-28.