Eiji Uchibe

Research Topics

Robotics
Reinforcement Learning

Awards

ICONIP2007 best paper award
SAB2004 best philosophical paper award
1997 JSAI Incentive Award

Selected Publications

S. Elfwing, E. Uchibe, K. Doya, and H. I. Christensen. Co-evolution of Shaping Rewards and Meta-Parameters in Reinforcement Learning. Adaptive Behavior, Vol. 16, No. 6, pages 400--412, 2008.
E. Uchibe and K. Doya. Finding Intrinsic Rewards by Embodied Evolution and Constrained Reinforcement Learning. Neural Networks. Vol. 21, Issue 10, December 2008, Pages 1447--1455.
T. Morimura, E. Uchibe, J. Yoshimoto, and K. Doya. A new natural policy gradient by stationary distribution metric. In Proc. of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD2008), 2008.
T. Sato, E. Uchibe, and K. Doya. Learning how, what, and whether to communicate: emergence of protocommunication in reinforcement learning agents. Artificial Life and Robotics. vol. 12, number 1-2, pages 70--74, 2008.
S. Elfwing, E. Uchibe, K. Doya, and H. I. Christensen. Evolutionary Development of Hierarchical Learning Structures. IEEE Transactions on Evolutionary Computations. Vol. 11, Issue 2, pages 249--264, 2007.
E. Uchibe and M. Asada. Incremental coevolution with competitive and cooperative tasks in a multi-robot environment. Proceedings of the IEEE, Vol. 94, Issue 7, pages 1412--1424, 2006.
K. Doya and E. Uchibe. The Cyber Rodent Project: Exploration of Adaptive Mechanisms for Self-Preservation and Self-Reproduction. Adaptive Behavior, vol. 13, no. 2, pages 149--160, 2005.
E. Uchibe, M. Yanase, and M. Asada. Behavior Generation for a Mobile Robot Based on the Adaptive Fitness Function. Robotics and Autonomous Systems, Vol.40, Issues 2-3, pages 69--77, 2002.
M. Asada and E. Uchibe. Multiagent Learning towards RoboCup. New Generation Computing, 19, pp. 103--120, 2001.
M. Asada, E. Uchibe and K. Hosoda. Cooperative behavior acquisition for mobile robots in dynamically changing real worlds via vision-based reinforcement learning and development. Artificial Intelligence, 110, pp. 275--292, 1999.

Curriculum Vitae

Academic Background

- 1999: Ph.D. in mechanical engineering from Osaka University.

Professional Experience

1999-: Researcher of Cooperative Distributed Vision for Dynamic Three Dimensional Scene Understanding, JSPS.
2001-: Researcher of Computational Learning Group, Kawato Dynamic Brain Project, ERATO, JST.
2001-: Researcher of Cyberhuman project, ATR Human Information Science Laboratories, Department 3, ATR International.
2002-: Researcher of Neuroinformatics project, Human Information Science Laboratories, ATR International.
2003-: Researcher of Department of Computational Neurobiology, Computational Neuroscience Laboratories, ATR International.
2004-: Researcher of Neural Computation Unit, Initial Research Project, Okinawa Institute of Science and Technology, Japan Science and Technology Agency.
2005-: Researcher of Neural Computation Unit, Initial Research Project, Okinawa Institute of Science and Technology Promotion Corporation.

back