论文信息 - Behavior Acquisition Based on Multi-module Learning System in Multi-agent Environment

Behavior Acquisition Based on Multi-module Learning System in Multi-agent Environment

The conventional reinforcement learning approaches have difficulties to handle the policy alternation of the opponents because it may cause dynamic changes of state transition probabilities of which stability is necessary for the learning to converge. This paper presents a method of multi-module reinforcement learning in a multiagent environment, by which the learning agent can adapt itself to the policy changes of the opponents. We show a preliminary result of a simple soccer situation in the context of RoboCup.

Minoru Asada | Yasutake Takahashi | Kazuhiro Edazawa

[1] Satinder Singh. Transfer of Learning by Composing Solutions of Elemental Sequential Tasks , 1992, Mach. Learn..

[2] Minoru Asada,et al. Cooperative Behavior Acquisition for Mobile Robots in Dynamically Changing Real Worlds Via Vision-Based Reinforcement Learning and Development , 1999, Artif. Intell..

[3] Mitsuo Kawato,et al. Multiple Model-Based Reinforcement Learning , 2002, Neural Computation.

[4] Satinder P. Singh,et al. Reinforcement Learning with a Hierarchy of Abstract Models , 1992, AAAI.

[5] Mitsuo Kawato,et al. MOSAIC Model for Sensorimotor Learning and Control , 2001, Neural Computation.

[6] Satinder P. Singh,et al. The Efficient Learning of Multiple Task Sequences , 1991, NIPS.

[7] Mitsuo Kawato,et al. Multiple Paired Forward-Inverse Models for Human Motor Learning and Control , 1998, NIPS.

[8] Stefano Nolfi,et al. Self-Organization of Modules and Their Hierarchy in Robot Learning Problems: A Dynamical Systems App , 1997 .

[9] Richard S. Sutton,et al. Integrated Modeling and Control Based on Reinforcement Learning and Dynamic Programming , 1990, NIPS 1990.

[10] Minoru Asada,et al. Vision-guided behavior acquisition of a mobile robot by multi-layered reinforcement learning , 2000, Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113).