UCHIBE Eiji 内部英治

Researcher Number	20426571
Other IDs
Affiliation (Current)	2025: 株式会社国際電気通信基礎技術研究所, 脳情報通信総合研究所, 主幹研究員
Affiliation (based on the past Project Information) *help	2015 – 2024: 株式会社国際電気通信基礎技術研究所, 脳情報通信総合研究所, 主幹研究員 2014: 沖縄科学技術大学院大学, 神経計算ユニット, グループリーダー 2013: 沖縄科学技術大学院大学, 神経計算ユニット, 研究員 2012: 沖縄科学技術大学院大学, その他の研究科, 研究員
Review Section/Research Field	Principal Investigator Complex systems / Basic Section 61050:Intelligent robotics-related / Intelligent robotics / Perception information processing/Intelligent robotics
Keywords	Principal Investigator 強化学習 / 逆強化学習 / モデルベース / モデルフリー / 非同期制御 / 並列学習 / 機械学習 / 重点サンプリング / 深層学習 / EMアルゴリズム … More / 密度比推定法 / 線形可解マルコフ決定過程 / 非同期分散 / 深層強化学習 / 非同期分散アーキテクチャ / 実時間制御 / マルチタイムスケール / マルチモジュール / 非同期分散型 / モデル学習 / 模倣学習 / 人工知能 / KL制御 / 知能ロボティックス / マルチエージェント強化学習 / 進化的計算 / 進化計算 / スマートフォンロボット / ロボット学習 / 部分観測環境 / KLダイバージェンス / 密度比推定 / 報酬関数 / 最適制御 Less

Development of Asynchronous Distributed Multi-module Deep Reinforcement Learning Focusing on Different Control PeriodsPrincipal Investigator
- Principal Investigator
  
  内部英治
- Project Period (FY)
  2021 – 2024
- Research Category
  
  Grant-in-Aid for Scientific Research (B)
- Review Section
  
  Basic Section 61050:Intelligent robotics-related
- Research Institution
  Advanced Telecommunications Research Institute International
Deep Parallel Reinforcement Learning with Model-Free and Model-Based MethodsPrincipal Investigator
- Principal Investigator
  
  内部英治
- Project Period (FY)
  2019 – 2020
- Research Category
  
  Grant-in-Aid for Scientific Research on Innovative Areas (Research in a proposed research area)
- Review Section
  
  Complex systems
- Research Institution
  Advanced Telecommunications Research Institute International
Parallel deep reinforcement learningPrincipal Investigator
- Principal Investigator
  
  内部英治
- Project Period (FY)
  2017 – 2018
- Research Category
  
  Grant-in-Aid for Scientific Research on Innovative Areas (Research in a proposed research area)
- Review Section
  
  Complex systems
- Research Institution
  Advanced Telecommunications Research Institute International
Integration of Kullback-Leibler control and intrinsic rewards for reinforcement learningPrincipal Investigator
- Principal Investigator
  
  UCHIBE Eiji
- Project Period (FY)
  2016 – 2018
- Research Category
  
  Grant-in-Aid for Challenging Exploratory Research
- Research Field
  
  Intelligent robotics
- Research Institution
  Advanced Telecommunications Research Institute International
部分観測環境下におけるモデルベース・モデルフリー強化学習の役割分担Principal Investigator
- Principal Investigator
  
  内部英治
- Project Period (FY)
  2014 – 2015
- Research Category
  
  Grant-in-Aid for Scientific Research on Innovative Areas (Research in a proposed research area)
- Review Section
  
  Complex systems
- Research Institution
  Advanced Telecommunications Research Institute International
  Okinawa Institute of Science and Technology Graduate University
モデルベース予測状態フィードバックを組み込んだ強化学習Principal Investigator
- Principal Investigator
  
  内部英治
- Project Period (FY)
  2012 – 2013
- Research Category
  
  Grant-in-Aid for Scientific Research on Innovative Areas (Research in a proposed research area)
- Review Section
  
  Complex systems
- Research Institution
  Okinawa Institute of Science and Technology Graduate University
Information theoretic optimization of intrinsic rewards for reinforcement learningPrincipal Investigator
- Principal Investigator
  
  UCHIBE Eiji
- Project Period (FY)
  2012 – 2014
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Research Field
  
  Perception information processing/Intelligent robotics
- Research Institution
  Okinawa Institute of Science and Technology Graduate University

All 2023 2022 2021 2020 2019 2018 2017 2016 2015 2014 2013 Other

All Journal Article Presentation Patent

[Journal Article] Modular deep reinforcement learning from reward and punishment for robot navigation2021
- Author(s)
  Jiexin Wang, Stefan Elfwing, and Eiji Uchibe
- Journal Title
  
  Neural Networks
  
  Volume: 135 Pages: 115-126
- DOI
  10.1016/j.neunet.2020.12.001
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-19H05001
[Journal Article] Constrained Deep Q-Learning Gradually Approaching Ordinary Q-Learning2019
- Author(s)
  Shota Ohnishi, Eiji Uchibe, Yotaro Yamaguchi, Kosuke Nakanishi, Yuji Yasui, and Shin Ishii
- Journal Title
  
  Frontiers in Neurorobotics
  
  Volume: 13
- DOI
  10.3389/fnbot.2019.00103
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PUBLICLY-19H05001, KAKENHI-PLANNED-17H06310, KAKENHI-PROJECT-19H04180
[Journal Article] Cooperative and Competitive Reinforcement and Imitation Learning for a Mixture of Heterogeneous Learning Modules2018
- Author(s)
  Eiji Uchibe
- Journal Title
  
  Frontiers in Neurorobotics
  
  Volume: 12
- DOI
  10.3389/fnbot.2018.00061
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-17H06042, KAKENHI-PROJECT-16K12504
[Journal Article] Model-Free Deep Inverse Reinforcement Learning by Logistic Regression2018
- Author(s)
  Eiji Uchibe
- Journal Title
  
  Neural Processing Letters
  
  Volume: 47 Issue: 3 Pages: 891-905
- DOI
  10.1007/s11063-017-9702-7
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-17H06042
[Journal Article] Robustness of linearly solvable Markov games employing inaccurate dynamics model2018
- Author(s)
  Ken Kinjo, Eiji Uchibe, and Kenji Doya
- Journal Title
  
  Artificial Life and Robotics
  
  Volume: 23 Issue: 1 Pages: 1-9
- DOI
  10.1007/s10015-017-0401-2
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16K12504, KAKENHI-PUBLICLY-17H06042
[Journal Article] Sigmoid-weighted linear units for neural network function approximation in reinforcement learning2018
- Author(s)
  Elfwing S, Uchibe E, Doya K
- Journal Title
  
  Neural Networks
  
  Volume: 2017 Specail issue Pages: 30297-6
- DOI
  10.1016/j.neunet.2017.12.012
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PLANNED-16H06563, KAKENHI-PUBLICLY-17H06042
[Journal Article] Deterministic Policy Search Method for Real Robot Control2017
- Author(s)
  内部英治, 王潔心
- Journal Title
  
  The Brain & Neural Networks
  
  Volume: 24 Issue: 4 Pages: 195-203
- DOI
  10.3902/jnns.24.195
- NAID
  130006337689
- ISSN
  1340-766X, 1883-0455
- Language
  Japanese
- Data Source
  KAKENHI-PROJECT-16K12504, KAKENHI-PUBLICLY-17H06042
[Journal Article] Adaptive Baseline Enhances EM-based Policy Search: Validation in a View-based Positioning Task of a Smartphone Balancer2017
- Author(s)
  Jiexin Wang, Eiji Uchibe, Kenji Doya
- Journal Title
  
  Frontiers in Neurorobotics
  
  Volume: 11 Pages: 1-15
- DOI
  10.3389/fnbot.2017.00001
- NAID
  120005980916
- Peer Reviewed / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PLANNED-16H06563, KAKENHI-PROJECT-16K12504
[Journal Article] Forward and Inverse Reinforcement Learning Based on Linearly Solvable Markov Decision Processes2016
- Author(s)
  内部英治
- Journal Title
  
  The Brain & Neural Networks
  
  Volume: 23 Issue: 1 Pages: 2-13
- DOI
  10.3902/jnns.23.2
- NAID
  130005150459
- ISSN
  1340-766X, 1883-0455
- Language
  Japanese
- Acknowledgement Compliant
- Data Source
  KAKENHI-PLANNED-23120007, KAKENHI-PUBLICLY-26120727
[Journal Article] EM-based policy hyper parameter exploration: application to standing and balancing of a two-wheeled smartphone robot2016
- Author(s)
  Wang J, Uchibe E, Doya K
- Journal Title
  
  Artificial Life and Robotics
  
  Volume: 21 Issue: 1 Pages: 125-131
- DOI
  10.1007/s10015-015-0260-7
- Peer Reviewed / Acknowledgement Compliant / Open Access / Int'l Joint Research
- Data Source
  KAKENHI-PLANNED-23120007, KAKENHI-PUBLICLY-26120727
[Journal Article] Expected energy-based restricted Boltzmann machine for classification2014
- Author(s)
  Elfwing S.,Uchibe E., Doya K.
- Journal Title
  
  Neural Networks
  
  Volume: 64 Pages: 29-38
- DOI
  10.1016/j.neunet.2014.09.006
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-ORGANIZER-23120001, KAKENHI-PLANNED-23120007, KAKENHI-PUBLICLY-26120727
[Journal Article] Evaluation of linearly solvable Markov decision process with dynamic model learning in a mobile robot navigation task2013
- Author(s)
  Kinjo K, Uchibe E, Doya K
- Journal Title
  
  Frontiers in Neurorobotics
  
  Volume: 7 Pages: 7-7
- DOI
  10.3389/fnbot.2013.00007
- Peer Reviewed
- Data Source
  KAKENHI-PLANNED-23120007, KAKENHI-PUBLICLY-24120527
[Patent] Direct Inverse Reinforcement Learning with Density Ratio Estimation2016
- Inventor(s)
  Eiji Uchibe and Kenji Doya
- Industrial Property Rights Holder
  OIST
- Industrial Property Rights Type
  特許
- Filing Date
  2016-03-15
- Overseas
- Data Source
  KAKENHI-PUBLICLY-26120727
[Patent] Inverse Reinforcement Learning by Density Ratio Estimation2015
- Inventor(s)
  Eiji Uchibe and Kenji Doya
- Industrial Property Rights Holder
  OIST
- Industrial Property Rights Type
  特許
- Filing Date
  2015-08-07
- Overseas
- Data Source
  KAKENHI-PUBLICLY-26120727
[Patent] Estimating goals using inverse reinforcement learning based on density ratio estimation2014
- Inventor(s)
  E. Uchibe and K. Doya
- Industrial Property Rights Holder
  E. Uchibe and K. Doya
- Industrial Property Rights Type
  特許
- Filing Date
  2014-07-31
- Overseas
- Data Source
  KAKENHI-PUBLICLY-26120727
[Patent] Estimating goals using inverse reinforcement learning based on density ratio estimation2014
- Inventor(s)
  E. Uchibe and K. Doya
- Industrial Property Rights Holder
  E. Uchibe and K. Doya
- Industrial Property Rights Type
  特許
- Filing Date
  2014-07-31
- Overseas
- Data Source
  KAKENHI-PROJECT-24500249
[Presentation] 方策とモデルのエントロピ正則を導入したオフラインモデルベース模倣学習2023
- Author(s)
  内部英治
- Organizer
  第37回人工知能学会全国大会
- Data Source
  KAKENHI-PROJECT-23K21710
[Presentation] 方策の積による報酬と罰からの並列強化学習2023
- Author(s)
  内部英治
- Organizer
  第33回日本神経回路学会全国大会
- Data Source
  KAKENHI-PROJECT-23K21710
[Presentation] 偏りのあるエキスパートデータから学習する生成模倣学習の多重化2023
- Author(s)
  内部英治
- Organizer
  第41回日本ロボット学会学術講演会
- Data Source
  KAKENHI-PROJECT-23K21710
[Presentation] Asynchronous competition and cooperation between model-based and model-free reinforcement learning systems2022
- Author(s)
  Eiji Uchibe
- Organizer
  Neuro 2022シンポジウム「適応的・予測的行動制御を支える並列的・階層的神経メカニズム」
- Invited
- Data Source
  KAKENHI-PROJECT-23K21710
[Presentation] モデルベース・モデルフリー強化学習の調停について2022
- Author(s)
  内部英治
- Organizer
  第36回人工知能学会全国大会
- Data Source
  KAKENHI-PROJECT-23K21710
[Presentation] 決定論的方策を学習するためのモデルベース強化学習2022
- Author(s)
  内部英治
- Organizer
  ロボティクス・メカトロニクス講演会予稿集
- Data Source
  KAKENHI-PROJECT-23K21710
[Presentation] 多目的強化学習のための経験再生バッファの分離2022
- Author(s)
  内部英治
- Organizer
  第40回日本ロボット学会学術講演会予稿集
- Data Source
  KAKENHI-PROJECT-23K21710
[Presentation] モデルフリーとモデルベース強化学習のための非同期並列学習2021
- Author(s)
  内部英治
- Organizer
  第35回人工知能学会全国大会
- Data Source
  KAKENHI-PUBLICLY-19H05001
[Presentation] 深層並列強化学習2021
- Author(s)
  内部英治
- Organizer
  第15回Motor Control研究会
- Data Source
  KAKENHI-PROJECT-23K21710
[Presentation] Parallel deep reinforcement learning with model-free and model-based methods2020
- Author(s)
  Eiji Uchibe
- Organizer
  International Symposium on Artificial Intelligence and Brain Science
- Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-19H05001
[Presentation] モデルフリーとモデルベースの協同による並列深層強化学習2020
- Author(s)
  内部英治
- Organizer
  第34回人工知能学会全国大会
- Data Source
  KAKENHI-PUBLICLY-19H05001
[Presentation] Latent brain dynamics estimation and deep generative imitation learning2020
- Author(s)
  Eiji Uchibe
- Organizer
  31st U.S.-Japan Technology Forum
- Invited / Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-19H05001
[Presentation] Parallel reward and punishment learning under entropy regularization2019
- Author(s)
  Eiji Uchibe
- Organizer
  第29回日本神経回路学会全国大会
- Data Source
  KAKENHI-PUBLICLY-19H05001
[Presentation] 階層強化学習の進展2019
- Author(s)
  内部英治
- Organizer
  第13回Motor Control研究会
- Invited
- Data Source
  KAKENHI-PUBLICLY-19H05001
[Presentation] Theoretical Analysis of Efficiency and Robustness of Softmax and Gap-Increasing Operators in Reinforcement Learning2019
- Author(s)
  Tadashi Kozuno, Eiji Uchibe, and Kenji Doya
- Organizer
  The 22nd International Conference on Artificial Intelligence and Statistics
- Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-17H06042
[Presentation] Imitation learning under entropy regularization2019
- Author(s)
  Eiji Uchibe
- Organizer
  Workshop on Reinforcement Learning & Biological Intelligence
- Invited / Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-17H06042
[Presentation] 強化学習と逆強化学習を組み合わせた模倣学習2019
- Author(s)
  内部英治
- Organizer
  第25回ステアラボ人工知能セミナー
- Invited
- Data Source
  KAKENHI-PUBLICLY-19H05001
[Presentation] Imitation learning under entropy regularization2019
- Author(s)
  Eiji Uchibe
- Organizer
  Workshop on Reinforcement Learning & Biological Intelligence
- Invited / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-16K12504
[Presentation] Online Meta-Learning by Parallel Algorithm Competition2018
- Author(s)
  Stefan Elfwing, Eiji Uchibe, and Kenji Doya
- Organizer
  Genetic and Evolutionary Computation Conference
- Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-17H06042
[Presentation] EM-based policy search for learning foraging and mating behaviors2018
- Author(s)
  Jiexin Wang and Eiji Uchibe
- Organizer
  ロボティクス・メカトロニクス講演会
- Data Source
  KAKENHI-PROJECT-16K12504
[Presentation] Cooperative and competitive reinforcement and imitation learning2018
- Author(s)
  Eiji Uchibe
- Organizer
  The 8th Joint IEEE International Conference on Development and Learning and Epigenetic Robotics
- Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-17H06042
[Presentation] Forward and inverse reinforcement learning and generative adversarial formulation2018
- Author(s)
  Eiji Uchibe
- Organizer
  NC/IBISML/IPSJ-MPS/IPSJ-BIO合同研究会
- Invited
- Data Source
  KAKENHI-PROJECT-16K12504
[Presentation] Cooperative and competitive reinforcement and imitation learning2018
- Author(s)
  Eiji Uchibe
- Organizer
  The 8th Joint IEEE International Conference on Development and Learning and Epigenetic Robotics
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-16K12504
[Presentation] 方策探査法のための多重重点サンプリングを用いた経験再利用2018
- Author(s)
  内部英治
- Organizer
  ロボティクス・メカトロニクス講演会
- Data Source
  KAKENHI-PUBLICLY-17H06042
[Presentation] 方策探査法のための多重重点サンプリングを用いた経験再利用2018
- Author(s)
  内部英治
- Organizer
  ロボティクス・メカトロニクス講演会
- Data Source
  KAKENHI-PROJECT-16K12504
[Presentation] Efficient sample reuse in policy search by multiple importance sampling2018
- Author(s)
  Eiji Uchibe
- Organizer
  Genetic and Evolutionary Computation Conference
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-16K12504
[Presentation] EM-based policy search for learning foraging and mating behaviors2018
- Author(s)
  Jiexin Wang and Eiji Uchibe
- Organizer
  ロボティクス・メカトロニクス講演会
- Data Source
  KAKENHI-PUBLICLY-17H06042
[Presentation] Deep reinforcement learning by parallelizing reward and punishment using MaxPain architecture2018
- Author(s)
  Jiexin Wang, Stefan Elfwing, and Eiji Uchibe
- Organizer
  The 8th Joint IEEE International Conference on Development and Learning and Epigenetic Robotics
- Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-17H06042
[Presentation] Forward and inverse reinforcement learning and generative adversarial formulation2018
- Author(s)
  Eiji Uchibe
- Organizer
  NC/IBISML/IPSJ-MPS/IPSJ-BIO合同研究会
- Invited
- Data Source
  KAKENHI-PUBLICLY-17H06042
[Presentation] Efficient Sample Reuse in Policy Search by Multiple Importance Sampling2018
- Author(s)
  Eiji Uchibe
- Organizer
  Genetic and Evolutionary Computation Conference
- Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-17H06042
[Presentation] Deep reinforcement learning by parallelizing reward and punishment using MaxPain architecture2018
- Author(s)
  Jiexin Wang, Stefan Elfwing, and Eiji Uchibe
- Organizer
  The 8th Joint IEEE International Conference on Development and Learning and Epigenetic Robotics
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-16K12504
[Presentation] ディープNNによる順・逆強化学習2017
- Author(s)
  内部英治
- Organizer
  第27回日本神経回路学会全国大会
- Data Source
  KAKENHI-PUBLICLY-17H06042
[Presentation] Deep inverse reinforcement learning2017
- Author(s)
  E. Uchibe
- Organizer
  The Third International Workshop on Intrinsically Motivated Open-ended learning
- Invited / Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-17H06042
[Presentation] From Neuroscience to Artificial Intelligence: Maximizing Average Reward in Episodic Reinforcement Learning Tasks with an Ensemble of Q-Learners2016
- Author(s)
  Chris Reinke, Eiji Uchibe, and Kenji Doya
- Organizer
  Third CiNet Conference, Neural mechanisms of decision making: Achievements and new directions
- Place of Presentation
  Osaka, Japan
- Year and Date
  2016-02-03
- Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-26120727
[Presentation] Learning of Stress Adaptive Habits with an Ensemble of Q-Learners2016
- Author(s)
  Chris Reinke, Eiji Uchibe, and Kenji Doya
- Organizer
  The 2nd International Workshop on Cognitive Neuroscience Robotics
- Place of Presentation
  Osaka, Japan
- Year and Date
  2016-02-21
- Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-26120727
[Presentation] Emergence of communication among reinforcement learning agents under coordination environment2016
- Author(s)
  Qiong Huang, Eiji Uchibe, and Kenji Doya
- Organizer
  6th Joint IEEE International Conference on Developmental Learning and Epigenetic Robotics
- Place of Presentation
  Cergy-Pontoise / Paris
- Year and Date
  2016-09-19
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-16K12504
[Presentation] Inverse reinforcement learning for behavior analysis and control2015
- Author(s)
  Eiji Uchibe, and Kenji Doya
- Organizer
  International Symposium on Prediction and Decision Making 2015
- Place of Presentation
  Tokyo, Japan
- Year and Date
  2015-10-31
- Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-26120727
[Presentation] Forward and inverse reinforcement learning for playing games2015
- Author(s)
  Eiji Uchibe, and Kenji Doya
- Organizer
  新学術領域研究「予測と意思決定の脳内計算機構の解明による人間理解と応用」第10回領域会議､2015年度包括脳冬のワークショップ
- Place of Presentation
  Tokyo, Japan
- Year and Date
  2015-12-17
- Data Source
  KAKENHI-PUBLICLY-26120727
[Presentation] Inverse Reinforcement Learning with Density Ratio Estimation2015
- Author(s)
  Eiji Uchibe, and Kenji Doya
- Organizer
  The 2nd Multidisciplinary Conference on Reinforcement Learning and Decision Making
- Place of Presentation
  The University of Alberta
- Year and Date
  2015-06-07
- Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-26120727
[Presentation] Maximizing the average reward in episodic reinforcement learning tasks2015
- Author(s)
  Chris Reinke, Eiji Uchibe, and Kenji Doya
- Organizer
  IEEE International Conference on Intelligent Informatics and Biomedical Sciences
- Place of Presentation
  Okinawa, Japan
- Year and Date
  2015-11-28
- Int'l Joint Research
- Data Source
  KAKENHI-PUBLICLY-26120727
[Presentation] Robustness of Linearly Solvable Markov Games with Inaccurate Dynamics Models2014
- Author(s)
  K. Kinjo, E. Uchibe, and K. Doya
- Organizer
  Proc. of International Symposium on Artificial Life and Robotics
- Place of Presentation
  Beppu, Japan
- Data Source
  KAKENHI-PUBLICLY-24120527
[Presentation] Combining learned controllers to achieve new goals based on linearly solvable MDPs2014
- Author(s)
  E. Uchibe and K. Doya
- Organizer
  Proc. of IEEE International Conference on Robotics and Automation
- Place of Presentation
  Hong Kong
- Data Source
  KAKENHI-PUBLICLY-24120527
[Presentation] Robustness of Linearly Solvable Markov Games with Inaccurate Dynamics Models2014
- Author(s)
  K. Kinjo, E. Uchibe, and K. Doya
- Organizer
  Proc. of International Symposium on Artificial Life and Robotics
- Place of Presentation
  Beppu, Japan
- Data Source
  KAKENHI-PROJECT-24500249
[Presentation] Combining learned controllers to achieve new goals based on linearly solvable MDPs2013
- Author(s)
  E. Uchibe, and K. Doya
- Organizer
  Neuro 2013
- Place of Presentation
  Kyoto International Conference Center
- Invited
- Data Source
  KAKENHI-PUBLICLY-24120527
[Presentation] Analysis of human behaviors by inverse reinforcement learning in a pole balancing task2013
- Author(s)
  S. Ota, E. Uchibe, and K. Doya
- Organizer
  The 3rd International Symposium on The Biology of Decision Making
- Place of Presentation
  Paris, France
- Data Source
  KAKENHI-PROJECT-24500249
[Presentation] Combining learned controllers to achieve new goals based on linearly solvable MDPs2013
- Author(s)
  E. Uchibe and K. Doya
- Organizer
  Neuro 2013
- Place of Presentation
  Kyoto International Conference Center
- Invited
- Data Source
  KAKENHI-PROJECT-24500249
[Presentation] Inverse reinforcement learning for understanding human behaviors2013
- Author(s)
  E. Uchibe
- Organizer
  International Symposium on Past and Future Directions of Cognitive Developmental Robotics
- Place of Presentation
  Osaka University Nakanoshima Center
- Invited
- Data Source
  KAKENHI-PROJECT-24500249
[Presentation] Inverse reinforcement learning for understanding human behaviors2013
- Author(s)
  E. Uchibe
- Organizer
  International Symposium on Past and Future Directions of Cognitive Developmental Robotics
- Place of Presentation
  Osaka University Nakanoshima Center 10F
- Invited
- Data Source
  KAKENHI-PUBLICLY-24120527
[Presentation] Inverse reinforcement learning for analysis of human behaviors2013
- Author(s)
  E. Uchibe, S. Ota, and K. Doya
- Organizer
  The 1st Multidisciplinary Conference on Reinforcement Learning and Decision Making
- Place of Presentation
  Princeton University
- Data Source
  KAKENHI-PUBLICLY-24120527
[Presentation] Analysis of human behaviors by inverse reinforcement learning in a pole balancing task2013
- Author(s)
  S. Ota, E. Uchibe, and K. Doya
- Organizer
  The 3rd International Symposium on The Biology of Decision Making
- Place of Presentation
  Paris, France
- Data Source
  KAKENHI-PUBLICLY-24120527
[Presentation] Scaled free-energy based reinforcement learning for robust and efficient learning in high-dimensional state spaces2013
- Author(s)
  E. Uchibe, S. Elfwing, and K. Doya
- Organizer
  Neuro 2013
- Place of Presentation
  Kyoto International Conference Center
- Invited
- Data Source
  KAKENHI-PUBLICLY-24120527
[Presentation] Inverse reinforcement learning for analysis of human behaviors2013
- Author(s)
  E. Uchibe, S. Ota, and K. Doya
- Organizer
  The 1st Multidisciplinary Conference on Reinforcement Learning and Decision Making
- Place of Presentation
  Princeton University, New Jersey, USA
- Data Source
  KAKENHI-PROJECT-24500249
[Presentation] Inverse reinforcement learning by density ratio estimation2013
- Author(s)
  E. Uchibe and K. Doya
- Organizer
  第16回情報論的学習理論ワークショップIBIS2013
- Place of Presentation
  東京工業大学蔵前会館
- Data Source
  KAKENHI-PROJECT-24500249
[Presentation] Standing-up and Balancing Behaviors of Android Phone Robot -- Control of Spring Attached Wheeled Inverted Pendulum --2013
- Author(s)
  J. Wang, E. Uchibe, and K. Doya
- Organizer
  IEICE Technical Committee on Nonlinear Problems (NLP)
- Place of Presentation
  City University of Hong Kong
- Data Source
  KAKENHI-PUBLICLY-24120527
[Presentation] Scaled free-energy based reinforcement learning for robust and efficient learning in high-dimensional state spaces2013
- Author(s)
  E. Uchibe, S. Elfwing, and K. Doya
- Organizer
  Neuro 2013
- Place of Presentation
  Kyoto International Conference Center
- Invited
- Data Source
  KAKENHI-PROJECT-24500249
[Presentation] Standing-up and Balancing Behaviors of Android Phone Robot -- Control of Spring Attached Wheeled Inverted Pendulum --2013
- Author(s)
  J. Wang, E. Uchibe, and K. Doya
- Organizer
  IEICE Technical Committee on Nonlinear Problems (NLP)
- Place of Presentation
  City University of Hong Kong
- Data Source
  KAKENHI-PROJECT-24500249
[Presentation] Inverse reinforcement learning by density ratio estimation2013
- Author(s)
  E. Uchibe, and K. Doya
- Organizer
  第16回情報論的学習理論ワークショップIBIS2013
- Place of Presentation
  東京工業大学蔵前会館
- Data Source
  KAKENHI-PUBLICLY-24120527
[Presentation] 密度比推定を用いた逆強化学習
- Author(s)
  内部英治，銅谷賢治
- Organizer
  第32回日本ロボット学会学術講演会
- Place of Presentation
  九州産業大学
- Year and Date
  2014-09-04 – 2014-09-06
- Data Source
  KAKENHI-PROJECT-24500249
[Presentation] Two-wheeled smartphone robot learns to stand up and balance by EM-based policy hyper parameter exploration
- Author(s)
  J. Wang, E. Uchibe, and K. Doya
- Organizer
  20th International Symposium on Artificial Life and Robotics
- Place of Presentation
  Beppu
- Year and Date
  2015-01-21 – 2015-01-23
- Data Source
  KAKENHI-PUBLICLY-26120727
[Presentation] Control of Two-Wheeled Balancing and Standing-up Behaviors by an Android Phone Robot
- Author(s)
  J. Wang, E. Uchibe, and K. Doya.
- Organizer
  第32回日本ロボット学会学術講演会
- Place of Presentation
  九州産業大学
- Year and Date
  2014-09-04 – 2014-09-06
- Data Source
  KAKENHI-PUBLICLY-26120727
[Presentation] Inverse Reinforcement Learning Using Dynamic Policy Programming
- Author(s)
  E. Uchibe and K. Doya
- Organizer
  4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics
- Place of Presentation
  Genoa
- Year and Date
  2014-10-13 – 2014-10-16
- Data Source
  KAKENHI-PUBLICLY-26120727
[Presentation] Inverse Reinforcement Learning Using Dynamic Policy Programming
- Author(s)
  E. Uchibe and K. Doya
- Organizer
  Proc. of the 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics
- Place of Presentation
  Genoa
- Year and Date
  2014-10-13 – 2014-10-16
- Data Source
  KAKENHI-PROJECT-24500249
[Presentation] Control of Two-Wheeled Balancing and Standing-up Behaviors by an Android Phone Robot
- Author(s)
  J. Wang, E. Uchibe, and K. Doya
- Organizer
  第32回日本ロボット学会学術講演会
- Place of Presentation
  九州産業大学
- Year and Date
  2014-09-04 – 2014-09-06
- Data Source
  KAKENHI-PROJECT-24500249
[Presentation] Two-wheeled smartphone robot learns to stand up and balance by EM-based policy hyper parameter exploration
- Author(s)
  J. Wang, E. Uchibe, and K. Doya
- Organizer
  International Symposium on Artificial Life and Robotics
- Place of Presentation
  Beppu
- Year and Date
  2015-01-21 – 2015-01-23
- Data Source
  KAKENHI-PROJECT-24500249
[Presentation] Combining learned controllers to achieve new goals based on linearly solvable MDPs
- Author(s)
  E. Uchibe and K. Doya
- Organizer
  Proc. of IEEE International Conference on Robotics and Automation
- Place of Presentation
  Hong Kong
- Year and Date
  2014-05-31 – 2014-06-07
- Data Source
  KAKENHI-PROJECT-24500249
[Presentation] 密度比推定を用いた逆強化学習
- Author(s)
  内部英治、銅谷健司
- Organizer
  第32回日本ロボット学会学術講演会
- Place of Presentation
  九州産業大学
- Year and Date
  2014-09-04 – 2014-09-06
- Data Source
  KAKENHI-PUBLICLY-26120727
[Presentation] Combining learned controllers to achieve new goals based on linearly solvable MDPs
- Author(s)
  E. Uchibe and K. Doya
- Organizer
  IEEE International Conference on Robotics and Automation
- Place of Presentation
  Hong Kong
- Year and Date
  2014-05-31 – 2014-06-07
- Data Source
  KAKENHI-PUBLICLY-26120727

1. DOYA Kenji

# of Collaborated Projects: 0 results

# of Collaborated Products: 5 results

UCHIBE Eiji 内部 英治

Research Projects

Research Products

Co-Researchers

Development of Asynchronous Distributed Multi-module Deep Reinforcement Learning Focusing on Different Control PeriodsPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Deep Parallel Reinforcement Learning with Model-Free and Model-Based MethodsPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Parallel deep reinforcement learningPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Integration of Kullback-Leibler control and intrinsic rewards for reinforcement learningPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

部分観測環境下におけるモデルベース・モデルフリー強化学習の役割分担Principal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

モデルベース予測状態フィードバックを組み込んだ強化学習Principal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Information theoretic optimization of intrinsic rewards for reinforcement learningPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

[Journal Article] Modular deep reinforcement learning from reward and punishment for robot navigation2021

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Constrained Deep Q-Learning Gradually Approaching Ordinary Q-Learning2019

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Cooperative and Competitive Reinforcement and Imitation Learning for a Mixture of Heterogeneous Learning Modules2018

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Model-Free Deep Inverse Reinforcement Learning by Logistic Regression2018

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Robustness of linearly solvable Markov games employing inaccurate dynamics model2018

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Sigmoid-weighted linear units for neural network function approximation in reinforcement learning2018

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Deterministic Policy Search Method for Real Robot Control2017

Author(s)

Journal Title

DOI

UCHIBE Eiji 内部英治