Multiagent reinforcement learning with the partly high-dimensional state space

Systems and Computers in Japan

Volumn 37, Issue 9, 2006, Pages 22-31

  Fujita, Kazuyuki ^a   Matsuo, Hiroshi ^a  

^a NAGOYA INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Modular Q learning; Multiagent; Reinforcement learning; State space

Indexed keywords

DATA STORAGE EQUIPMENT; INTELLIGENT AGENTS; MULTI AGENT SYSTEMS; PERFORMANCE; STATE SPACE METHODS;

MODULAR Q-LEARNING; MULTIAGENT; REINFORCEMENT LEARNING; STATE SPACE;

LEARNING SYSTEMS;

EID: 33746156507     PISSN: 08821666     EISSN: 1520684X     Source Type: Journal    
DOI: 10.1002/scj.20526     Document Type: Article

References (14)

1. Sutton RS, Barto AG. Reinforcement learning: An introduction. MIT Press; 1998.
2. Arai S. Multiagent reinforcement learning - Uniting planning, theory, and various techniques for implementation. J Japan Soc Artif Intell 2001;16:476-481.
3. Crites RH, Barto AG. Improving elevator performance using reinforcement learning. Adv Neural Inf Process Syst 1996;8:1017-1023.
4. Wolpert DH, Sill J, Turner K. Reinforcement learning in distributed domains: Beyond team games. Proc 17th National Conference on Artificial Intelligence, p 819-824, Seattle, WA, 2001.
5. Kurumatani K. Perspective of multiagent social simulation. ISCIE J Syst Control Inf 2002;46:518-523.
6. Uchibe E, Asada M, Hosoda K. State space construction for cooperative behavior acquisition in the environments including multiple learning robots. J Robot Soc Japan 2002;20:281-289.
7. Edazawa K, Takahashi Y, Asada M. Behavior acquisition in a multi-agent environment using multiple learning modules. 20th Annual Conference of the Robotics Society of Japan, 3H33, 2002.
8. Goto R, Matsui T, Matsuo H. State generalization with support vector machines in reinforcement learning. 4th Asia-Pacific Conference on Simulated Evolution and Learning 2002;I:51-55.
9. Takahashi Y, Asada M. State-action space construction for multi-layered learning system. J Robot Soc Japan 2003;21:164-171.
10. Gultekin I, Arslan A. Modular-fuzzy cooperation algorithm for multi-agent systems. Advances in Information Systems: 2nd International Conference, p 255-263, 2002.
11. Ito A, Kanabuchi M. Speeding up multiagent reinforcement learning by coarse-graining of perception: The hunter game. Trans IEICE 2001;J84-D-I:285- 293.
12. Ono N, Fukumoto K. Multi-agent reinforcement learning: A modular approach. Proc 2nd International Conference on Multi-agent Systems (ICMAS-96), p 252-258, AAAI Press.
13. Whitehead S, Karlsson J, Tenenberg J. Learning multiple goal behavior via task decomposition and dynamic policy merging. In: Robot learning. Kluwer Academic Publishers; 1993. p 45-78.
14. Nagayuki Y, Ito M. Reinforcement learning using a policy estimate of the other agent in a two-agent stochastic game. Trans IEICE 2003;J86-D-I:821-829.