Abstract
Multi-agent systems form a particular type of distributed artificial intelligence systems. As an important character of players in game, autonomous agents’ learning has become the main direction of researchers. In this paper, based on basic reinforcement learning, multi-agent reinforcement learning with specific context is proposed. The method is applied to RoboCup to learn coordination among agents. In the learning, the game field is divided into different areas, and the action choice is made dependent on the area in which the ball is currently located. This makes the state space and the action space decrease. After learning the optimal joint policy is determined. Comparison experiment between stochastic policy and this optimal policy shows the effectiveness of our approach.
This paper is supported by the National Science Foundation of China (60375017).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Wooldridge, M.: An Introduction to Multiagent Systems. John Wiley and Sons Ltd., Chichester (2002)
Kitano, H., Tambe, M., Stone, P., et al.: The RoboCup Synthetic Agent Challenge 97. In: Kitano, H. (ed.) RoboCup 1997. LNCS, vol. 1395, pp. 62–73. Springer, Heidelberg (1998)
Kitano, H., Asada, M., Noda, I., Matsubara, H.: RoboCup: Robot World Cup. IEEE Robotics & Automation Magazine 5(3), 30–36 (1998)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Mitchell, T.M.: Machine Learning. McGraw-Hill Companies. Inc., New York (1997)
Abul, O., Polat, F., Alhajj, R.: Multiagent Reinforcement Learning Using Function Approximation. IEEE Transactions on Systems, Man, and Cybernetics-Partc. Application and Reviews 30 (November 2000)
Meng, W., Hong, B., Han, X.: Application of Reinforcement Learning to Robot Soccer. Application Research of Computers, 79–81 (2002)
Cheng, X., Yuan, X., Pan, L., **a, D.: Reinforcement Learning in Simulation RoboCup Soccer. In: Proceedings of the Third International Conference on Machine Learning and Cybernetics, Shanghai, August 26-29, vol. 1, pp. 244–248 (2004)
Wang, G., Yu, H.: Multi-Agent Reinforcement Learning: An Approach Based on Agents’ Cooperation for A Common Goal. In: The 8th International Conference on Computer Supported Cooperative Work in Design Proceedings, May 26-28, vol. 1, pp. 336–339 (2004)
de Boer, R., Kok, J.R.: The Incremental Development of A Synthetic Multi-Agent System. The UvA Trilearn 2001 Robotic Soccer Simulation Team. Master’s thesis. University of Amsterdam. The Netherlands (February 2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, W., Li, J., Ruan, X. (2005). Reinforcement Learning Based on Multi-agent in RoboCup. In: Huang, DS., Zhang, XP., Huang, GB. (eds) Advances in Intelligent Computing. ICIC 2005. Lecture Notes in Computer Science, vol 3644. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11538059_100
Download citation
DOI: https://doi.org/10.1007/11538059_100
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28226-6
Online ISBN: 978-3-540-31902-3
eBook Packages: Computer ScienceComputer Science (R0)