Abstract
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.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Asada, M., Uchibe, E., Hosoda, K.: Cooperative behavior acquisition for mobile robots in dynamically changing real worlds via vision-based reinforcement learning and development. Artificial Intelligence 110, 275–292 (1999)
Singh, S.P.: Transfer of learning by composing solutions of elemental sequential tasks. Machine Learning 8, 323–339 (1992)
Singh, S.P.: The effeicient learnig of multiple task sequences. Neural Information Processing Systems 4, 251–258 (1992)
Takahashi, Y., Asada, M.: Vision-guided behavior acquisition of a mobile robot by multi-layered reinforcement learning. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, vol. 1, pp. 395–402 (2000)
Sutton, R.S.: Integrated modeling and control based on reinforcement learning and dynamic programming. Advances in Neural Information Processing Systems 3, 471–478 (1991)
Singh, S.P.: Reinforcement learning with a hierarchy of abstract models. National Conference on Artificial Intelligence, 202–207 (1992)
Doya, K., Samejima, K., Katagiri, K., Kawato, M.: Multiple model-based reinforcement learning. Technical report, Kawato Dynamic Brain Project Technical Report, KDB-TR-08, Japan Science and Technology Corporation (June 2000)
Haruno, M., Wolpert, D.M., Kawato, M.: Multiple paired forward-inverse models for human motor learning and control. Advances in Neural Information Processing Systems 11, 31–37 (1999)
Haruno, M., Wolpert, D.M., Kawato, M.: Mosaic model for sensorimotor learning and control. Neural Computation 13, 2201–2220 (2001)
Tani, J., Nolfi, S.: Self-organization of modules and their hierarchy in robot learning problems: A dynamical systems approach. Technical report, Technical Report: SCSL-TR-97-008 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Takahashi, Y., Edazawa, K., Asada, M. (2003). Behavior Acquisition Based on Multi-module Learning System in Multi-agent Environment. In: Kaminka, G.A., Lima, P.U., Rojas, R. (eds) RoboCup 2002: Robot Soccer World Cup VI. RoboCup 2002. Lecture Notes in Computer Science(), vol 2752. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45135-8_39
Download citation
DOI: https://doi.org/10.1007/978-3-540-45135-8_39
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40666-2
Online ISBN: 978-3-540-45135-8
eBook Packages: Springer Book Archive