Eiji Uchibe

According to our database, Eiji Uchibe authored at least 74 papers between 1994 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2023

Online Reinforcement Learning Control of Nonlinear Dynamic Systems: A State-action Value Function Based Solution.

Hamed Jabbari Asl, Eiji Uchibe

Neurocomputing, August, 2023

2022

Randomized-to-Canonical Model Predictive Control for Real-World Visual Robotic Manipulation.

Tomoya Yamanokuchi, Yuhwan Kwon, Yoshihisa Tsurumine, Eiji Uchibe, Jun Morimoto, Takamitsu Matsubara

IEEE Robotics Autom. Lett., 2022

Model-Based Imitation Learning Using Entropy Regularization of Model and Policy.

Eiji Uchibe

IEEE Robotics Autom. Lett., 2022

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, 2022

Enforcing KL Regularization in General Tsallis Entropy Reinforcement Learning via Advantage Learning.

Lingwei Zhu, Zheng Chen, Eiji Uchibe, Takamitsu Matsubara

CoRR, 2022

q-Munchausen Reinforcement Learning.

Lingwei Zhu, Zheng Chen, Eiji Uchibe, Takamitsu Matsubara

CoRR, 2022

Online Data-Driven Inverse Reinforcement Learning for Deterministic Systems.

Hamed Jabbari Asl, Eiji Uchibe

Proceedings of the IEEE Symposium Series on Computational Intelligence, 2022

2021

Modular deep reinforcement learning from reward and punishment for robot navigation.

Jiexin Wang, Stefan Elfwing, Eiji Uchibe

Neural Networks, 2021

Forward and inverse reinforcement learning sharing network weights and hyperparameters.

Eiji Uchibe, Kenji Doya

Neural Networks, 2021

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, 2021

2020

Imitation learning based on entropy-regularized forward and inverse reinforcement learning.

Eiji Uchibe, Kenji Doya

CoRR, 2020

2019

Deep reinforcement learning with smooth policy update: Application to robotic cloth manipulation.

Yoshihisa Tsurumine, Yunduan Cui, Eiji Uchibe, Takamitsu Matsubara

Robotics Auton. Syst., 2019

Constrained Deep Q-Learning Gradually Approaching Ordinary Q-Learning.

Shota Ohnishi, Eiji Uchibe, Yotaro Yamaguchi, Kosuke Nakanishi, Yuji Yasui, Shin Ishii

Frontiers Neurorobotics, 2019

Theoretical Analysis of Efficiency and Robustness of Softmax and Gap-Increasing Operators in Reinforcement Learning.

Tadashi Kozuno, Eiji Uchibe, Kenji Doya

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

Model-Free Deep Inverse Reinforcement Learning by Logistic Regression.

Eiji Uchibe

Neural Process. Lett., 2018

Sigmoid-weighted linear units for neural network function approximation in reinforcement learning.

Stefan Elfwing, Eiji Uchibe, Kenji Doya

Neural Networks, 2018

Cooperative and Competitive Reinforcement and Imitation Learning for a Mixture of Heterogeneous Learning Modules.

Eiji Uchibe

Frontiers Neurorobotics, 2018

Unbounded Output Networks for Classification.

Stefan Elfwing, Eiji Uchibe, Kenji Doya

CoRR, 2018

Robustness of linearly solvable Markov games employing inaccurate dynamics model.

Ken Kinjo, Eiji Uchibe, Kenji Doya

Artif. Life Robotics, 2018

Deep Reinforcement Learning by Parallelizing Reward and Punishment using the MaxPain Architecture.

Jiexin Wang, Stefan Elfwing, Eiji Uchibe

Proceedings of the 2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics, 2018

Efficient sample reuse in policy search by multiple importance sampling.

Eiji Uchibe

Proceedings of the Genetic and Evolutionary Computation Conference, 2018

Online meta-learning by parallel algorithm competition.

Stefan Elfwing, Eiji Uchibe, Kenji Doya

Proceedings of the Genetic and Evolutionary Computation Conference, 2018

2017

Adaptive Baseline Enhances EM-Based Policy Search: Validation in a View-Based Positioning Task of a Smartphone Balancer.

Jiexin Wang, Eiji Uchibe, Kenji Doya

Frontiers Neurorobotics, 2017

Unifying Value Iteration, Advantage Learning, and Dynamic Policy Programming.

Tadashi Kozuno, Eiji Uchibe, Kenji Doya

CoRR, 2017

Deep dynamic policy programming for robot control with raw images.

Yoshihisa Tsurumine, Yunduan Cui, Eiji Uchibe, Takamitsu Matsubara

Proceedings of the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2017

Average Reward Optimization with Multiple Discounting Reinforcement Learners.

Chris Reinke, Eiji Uchibe, Kenji Doya

Proceedings of the Neural Information Processing - 24th International Conference, 2017

2016

From free energy to expected energy: Improving energy-based value function approximation in reinforcement learning.

Stefan Elfwing, Eiji Uchibe, Kenji Doya

Neural Networks, 2016

EM-based policy hyper parameter exploration: application to standing and balancing of a two-wheeled smartphone robot.

Jiexin Wang, Eiji Uchibe, Kenji Doya

Artif. Life Robotics, 2016

Deep Inverse Reinforcement Learning by Logistic Regression.

Eiji Uchibe

Proceedings of the Neural Information Processing - 23rd International Conference, 2016

Emergence of communication among reinforcement learning agents under coordination environment.

Qiong Huang, Eiji Uchibe, Kenji Doya

Proceedings of the 2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, 2016

2015

Expected energy-based restricted Boltzmann machine for classification.

Stefan Elfwing, Eiji Uchibe, Kenji Doya

Neural Networks, 2015

2014

Combining learned controllers to achieve new goals based on linearly solvable MDPs.

Eiji Uchibe, Kenji Doya

Proceedings of the 2014 IEEE International Conference on Robotics and Automation, 2014

Inverse reinforcement learning using Dynamic Policy Programming.

Eiji Uchibe, Kenji Doya

Proceedings of the 4th International Conference on Development and Learning and on Epigenetic Robotics, 2014

2013

Evaluation of linearly solvable Markov decision process with dynamic model learning in a mobile robot navigation task.

Ken Kinjo, Eiji Uchibe, Kenji Doya

Frontiers Neurorobotics, 2013

Scaled free-energy based reinforcement learning for robust and efficient learning in high-dimensional state spaces.

Stefan Elfwing, Eiji Uchibe, Kenji Doya

Frontiers Neurorobotics, 2013

Reinforcement learning with state-dependent discount factor.

Naoto Yoshida, Eiji Uchibe, Kenji Doya

Proceedings of the 2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics, 2013

2011

Darwinian embodied evolution of the learning ability for survival.

Stefan Elfwing, Eiji Uchibe, Kenji Doya, Henrik I. Christensen

Adapt. Behav., 2011

2010

Derivatives of Logarithmic Stationary Distributions for Policy Gradient Reinforcement Learning.

Tetsuro Morimura, Eiji Uchibe, Junichiro Yoshimoto, Jan Peters, Kenji Doya

Neural Comput., 2010

Free-Energy Based Reinforcement Learning for Vision-Based Navigation with High-Dimensional Sensory Inputs.

Stefan Elfwing, Makoto Otsuka, Eiji Uchibe, Kenji Doya

Proceedings of the Neural Information Processing. Theory and Algorithms, 2010

2009

Co-evolution of Rewards and Meta-parameters in Embodied Evolution.

Stefan Elfwing, Eiji Uchibe, Kenji Doya

Proceedings of the Creating Brain-Like Intelligence: From Basic Principles to Complex Intelligent Systems, 2009

A Generalized Natural Actor-Critic Algorithm.

Tetsuro Morimura, Eiji Uchibe, Junichiro Yoshimoto, Kenji Doya

Proceedings of the Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, 2009

Emergence of Different Mating Strategies in Artificial Embodied Evolution.

Stefan Elfwing, Eiji Uchibe, Kenji Doya

Proceedings of the Neural Information Processing, 16th International Conference, 2009

2008

Finding intrinsic rewards by embodied evolution and constrained reinforcement learning.

Eiji Uchibe, Kenji Doya

Neural Networks, 2008

Learning how, what, and whether to communicate: emergence of protocommunication in reinforcement learning agents.

Takashi Sato, Eiji Uchibe, Kenji Doya

Artif. Life Robotics, 2008

Natural actor-critic with baseline adjustment for variance reduction.

Tetsuro Morimura, Eiji Uchibe, Kenji Doya

Artif. Life Robotics, 2008

Co-evolution of Shaping Rewards and Meta-Parameters in Reinforcement Learning.

Stefan Elfwing, Eiji Uchibe, Kenji Doya, Henrik I. Christensen

Adapt. Behav., 2008

A New Natural Policy Gradient by Stationary Distribution Metric.

Tetsuro Morimura, Eiji Uchibe, Junichiro Yoshimoto, Kenji Doya

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2008

NeuroEvolution Based on Reusable and Hierarchical Modular Representation.

Takumi Kamioka, Eiji Uchibe, Kenji Doya

Proceedings of the Advances in Neuro-Information Processing, 15th International Conference, 2008

2007

Evolutionary Development of Hierarchical Learning Structures.

Stefan Elfwing, Eiji Uchibe, Kenji Doya, Henrik I. Christensen

IEEE Trans. Evol. Comput., 2007

Finding Exploratory Rewards by Embodied Evolution and Constrained Reinforcement Learning in the Cyber Rodents.

Eiji Uchibe, Kenji Doya

Proceedings of the Neural Information Processing, 14th International Conference, 2007

2006

Incremental Coevolution With Competitive and Cooperative Tasks in a Multirobot Environment.

Eiji Uchibe, Minoru Asada

Proc. IEEE, 2006

2005

The Cyber Rodent Project: Exploration of Adaptive Mechanisms for Self-Preservation and Self-Reproduction.

Kenji Doya, Eiji Uchibe

Adapt. Behav., 2005

Biologically inspired embodied evolution of survival.

Stefan Elfwing, Eiji Uchibe, Kenji Doya, Henrik I. Christensen

Proceedings of the IEEE Congress on Evolutionary Computation, 2005

2004

Multi-agent reinforcement learning: using macro actions to learn a mating task.

Stefan Elfwing, Eiji Uchibe, Kenji Doya, Henrik I. Christensen

Proceedings of the 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems, Sendai, Japan, September 28, 2004

2003

An Evolutionary Approach to Automatic Construction of the Structure in Hierarchical Reinforcement Learning.

Stefan Elfwing, Eiji Uchibe, Kenji Doya

Proceedings of the Genetic and Evolutionary Computation, 2003

2002

Behavior generation for a mobile robot based on the adaptive fitness function.

Eiji Uchibe, Masakazu Yanase, Minoru Asada

Robotics Auton. Syst., 2002

2001

Multiagent Learning towards RoboCup.

Minoru Asada, Eiji Uchibe

New Gener. Comput., 2001

Evolutionary Behavior Selection with Activation/Termination Constraints.

Eiji Uchibe, Masakazu Yanase, Minoru Asada

Proceedings of the RoboCup 2001: Robot Soccer World Cup V, 2001

Dynamic Task Assignment in a Multiagent/Multitask Environment based on Module Conflict Resolution.

Eiji Uchibe, Tatsunori Kato, Koh Hosoda, Minoru Asada

Proceedings of the 2001 IEEE International Conference on Robotics and Automation, 2001

2000

Osaka University "Trackies 2000".

Yasutake Takahashi, Eiji Uchibe, Takahashi Tamura, Masakazu Yanase, Shoichi Ikenoue, Shujiro Inui, Minoru Asada

Proceedings of the RoboCup 2000: Robot Soccer World Cup IV, 2000

1999

Cooperative Behavior Acquisition for Mobile Robots in Dynamically Changing Real Worlds Via Vision-Based Reinforcement Learning and Development.

Minoru Asada, Eiji Uchibe, Koh Hosoda

Artif. Intell., 1999

Multiple Reward Criterion for Cooperative Behavior Acquisition in a Muliagent Environment.

Eiji Uchibe, Minoru Asada

Proceedings of the RoboCup-99: Robot Soccer World Cup III, 1999

The Team Description of Osaka University "Trackies-99".

Sho'ji Suzuki, Tatsunori Kato, Hiroshi Ishizuka, Hiroyoshi Kawanishi, Takashi Tamura, Masakazu Yanase, Yasutake Takahashi, Eiji Uchibe, Minoru Asada

Proceedings of the RoboCup-99: Robot Soccer World Cup III, 1999

1998

TRACKIES: RoboCup-97 Middle-Size League World Cochampion.

Minoru Asada, Sho'ji Suzuki, Yasutake Takahashi, Eiji Uchibe, Masateru Nakamura, Chizuko Mishima, Hiroshi Ishizuka, Tatsunori Kato

AI Mag., 1998

Cooperative Behavior Acquisition in a Multiple Mobile Robot Environment by Co-evolution.

Eiji Uchibe, Masateru Nakamura, Minoru Asada

Proceedings of the RoboCup-98: Robot Soccer World Cup II, 1998

An Application of Vision-Based Learning in RoboCup for a Real Robot with an Omnidirectional Vision System and the Team Description of Osaka University "Trackies".

Sho'ji Suzuki, Tatsunori Kato, Hiroshi Ishizuka, Yasutake Takahashi, Eiji Uchibe, Minoru Asada

Proceedings of the RoboCup-98: Robot Soccer World Cup II, 1998

Co-evolution for cooperative behavior acquisition in a multiple mobile robot environment.

Eiji Uchibe, Masateru Nakamura, Minoru Asada

Proceedings of the Proceedings 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems. Innovations in Theory, 1998

Environmental Complexity Control for Vision-Based Learning Mobile Robot.

Eiji Uchibe, Minoru Asada, Koh Hosoda

Proceedings of the IEEE International Conference on Robotics and Automation, 1998

Cooperative Behavior Acquisition in Multi Mobile Robots Environment by Reinforcement Learning Based on State Vector Estimation.

Eiji Uchibe, Minoru Asada, Koh Hosoda

Proceedings of the IEEE International Conference on Robotics and Automation, 1998

State Space Construction for Behavior Acquisition in Multi Agent Environments with Vision and Action.

Eiji Uchibe, Minoru Asada, Koh Hosoda

Proceedings of the Sixth International Conference on Computer Vision (ICCV-98), 1998

1997

Vision-Based Robot Learning Towards RoboCup: Osaka University "Trackies".

Sho'ji Suzuki, Yasutake Takahashi, Eiji Uchibe, Masateru Nakamura, Chizuko Mishima, Hiroshi Ishizuka, Tatsunori Kato, Minoru Asada

Proceedings of the RoboCup-97: Robot Soccer World Cup I, 1997

Vision Based State Space Construction for Learning Mobile Robots in Multi-agent Environments.

Eiji Uchibe, Minoru Asada, Koh Hosoda

Proceedings of the Learning Robots, 6th European Workshop, 1997

1996

Behavior coordination for a mobile robot using modular reinforcement learning.

Eiji Uchibe, Minoru Asada, Koh Hosoda

Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS 1996, 1996

1994

Coordination of multiple behaviors acquired by a vision-based reinforcement learning.

Minoru Asada, Eiji Uchibe, Shoichi Noda, Sukoya Tawaratsumida, Koh Hosoda

Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, 1994