Eiji Uchibe

Profile Information

Affiliation: 主幹研究員, 脳情報研究所, 株式会社国際電気通信基礎技術研究所

Degree: Ph.D.(Osaka University)

Other name(s) (e.g. nickname): ATR
Researcher number: 20426571
ORCID iD: https://orcid.org/0000-0001-7908-0258
J-GLOBAL ID: 201301084954588726
researchmap Member ID: B000229342

External link: http://www.cns.atr.jp/bri/en/

Research Interests

Research Areas

Research History

Oct, 2015 - Present

Principal Researcher, Computational Neuroscience Laboratories, Department of Brain Robot Interface, Advanced Telecommunications Research Institute International
Oct, 2008 - Sep, 2015

Group Leader, Neural Computation Unit, Okinawa Institute of Science and Technology, Graduate University
Oct, 2005 - Sep, 2008

Group Leader, Neural Computation Unit, Okinawa Institute of Science and Technology, Initial Research Project
Apr, 2004 - Sep, 2005

Group Leader, Neural Computation Unit, Okinawa Institute of Science and Technology, Initial Research Project
May, 2003 - Mar, 2004

Researcher, Dept. of Computational Neurobiology, Computational Neuroscience Labs., Advanced Telecommunications Research Institute International
Oct, 2001 - Apr, 2003

Researcher, Human Information Science Labs., Dept.3, Advanced Telecommunications Research Institute International
Apr, 2001 - Sep, 2001

Researcher, Kawato Dynamic Brain Project, JST, ERATO
Apr, 1999 - Mar, 2001

研究員, 分散協調視覚による動的3次元状況理解, JSPS未来開拓学術研究推進事業

Awards

2021

全国大会優秀賞, 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, 人工知能学会
2019

全国大会優秀賞, エントロピ正則された強化学習を用いた模倣学習, 人工知能学会

内部英治
2007

Best paper awards in Proc. of ICONIP

Eiji Uchibe
2004

Best philosophical paper awards in Proc. of International Conference on Simulation of Adaptive Behavior

Eiji Uchibe
1997

人工知能学会研究会優秀賞, 人工知能学会

内部英治

Major Papers

Estimating cost function of expert players in differential games: A model-based method and its data-driven extension

Hamed Jabbari Asl, Eiji Uchibe

Expert Systems with Applications, Dec, 2024
Online estimation of objective function for continuous-time deterministic systems

Hamed Jabbari Asl, Eiji Uchibe

Neural Networks, 172 106116-106116, Apr, 2024 Peer-reviewedLast author
Online Reinforcement Learning Control of Nonlinear Dynamic Systems: A State-action Value Function Based Solution

Hamed Jabbari Asl, Eiji Uchibe

Neurocomputing, 544 126291-126291, Aug, 2023 Peer-reviewedLast author
Reinforcement learning-based optimal control of unknown constrained-input nonlinear systems using simulated experience

Hamed Jabbari Asl, Eiji Uchibe

Nonlinear Dynamics, Jul 19, 2023 Peer-reviewedLast author
Model-Based Imitation Learning Using Entropy Regularization of Model and Policy

Eiji Uchibe

IEEE Robotics and Automation Letters, 7(4) 10922-10929, Oct, 2022 Peer-reviewedLead author
Deep learning, reinforcement learning, and world models

Yutaka Matsuo, Yann LeCun, Maneesh Sahani, Doina Precup, David Silver, Masashi Sugiyama, Eiji Uchibe, Jun Morimoto

Neural Networks, 152 267-275, Aug, 2022 Peer-reviewed
Forward and inverse reinforcement learning sharing network weights and hyperparameters

Eiji Uchibe, Kenji Doya

Neural Networks, 144 138-153, Dec, 2021 Peer-reviewedLead author
Parallel and hierarchical neural mechanisms for adaptive and predictive behavioral control

Tom Macpherson, Masayuki Matsumoto, Hiroaki Gomi, Jun Morimoto, Eiji Uchibe, Takatoshi Hikida

Neural Networks, 144 507-521, Sep, 2021 Peer-reviewed
Generative Imitation Learning using Forward and Inverse Reinforcement Learning

Eiji Uchibe

Journal of the Robotics Society of Japan, 39(7) 617-620, Sep, 2021 InvitedLead author
Modular deep reinforcement learning from reward and punishment for robot navigation

Jiexin Wang, Stefan Elfwing, Eiji Uchibe

Neural Networks, 135 115-126, Mar, 2021 Peer-reviewedLast author

Major Misc.

Unsupervised Neural Motion Retargeting for Humanoid Teleoperation

Satoshi Yagi, Mitsunori Tada, Eiji Uchibe, Suguru Kanoga, Takamitsu Matsubara, Jun Morimoto

Jun 2, 2024
Reward-Punishment Reinforcement Learning with Maximum Entropy

Jiexin Wang, Eiji Uchibe

May 20, 2024
人と生成的模倣学習の共進化による人間参加型ロボット学習システム

内部英治

ロボティクス・メカトロニクス講演会予稿集, Jun, 2023 Lead author
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

内部英治

第37回人工知能学会全国大会, Jun, 2023 Lead author
モデルベース・モデルフリー強化学習の調停について

内部英治

第36回人工知能学会全国大会, Jun, 2022 Lead author

Major Presentations

Asynchronous competition and cooperation between model-based and model-free reinforcement learning systems

Eiji Uchibe

Jul 1, 2022 Invited
並列深層強化学習

内部英治

第15回Motor Control研究会, Sep 10, 2021
強化学習と逆強化学習を組み合わせた模倣学習

内部英治

第25回ステアラボ人工知能セミナー, Sep, 2019 Invited
階層強化学習の進展

内部英治

第13回Motor Control研究会, Aug, 2019 Invited
Imitation learning under entropy regularization

Eiji Uchibe

Reinforcement Learning & Biological Intelligence, Mar 7, 2019 Invited

Professional Memberships

Major Research Projects

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

Grant-in-Aid for Scientific Research (B), Grant-in-Aid for Scientific Research (B), JSPS, Apr, 2021 - Mar, 2025

Eiji Uchibe
サイボーグ AI に関する研究開発

人と共に進化する次世代人工知能に関する技術開発事業, NEDO, Sep, 2020 - Mar, 2025
製造業に革新をもたらすスマートロボット技術の開発

未来社会創造事業, 科学技術振興機構, May, 2021

内部英治

Industrial Property Rights

特開2009-289199 制御器、制御方法および制御プログラム

森村哲郎, 内部英治, 吉本潤一郎, 銅谷賢治
特開2009-230645 制御器、制御方法および制御プログラム

森村哲郎, 内部英治, 吉本潤一郎, 銅谷賢治
特開2007-65929 制御器、制御方法および制御プログラム

森村哲郎, 内部英治, 銅谷賢治
特開2005-078516 並列学習装置、並列学習方法及び並列学習プログラム

内部英治, 銅谷賢治

Profile Information

Research Interests

Research Areas

Research History

Awards

Major Papers

Major Misc.

Major Presentations

Professional Memberships

Major Research Projects

Industrial Property Rights

Menu

Coauthors