A novel multi-agent Q-learning algorithm in cooperative multi-agent system

Proceedings of the World Congress on Intelligent Control and Automation (WCICA)

Volumn 1, Issue , 2000, Pages 272-276

  Ou, Haitao ^a   Zhang, Weidong ^a   Zhang, Wenyuan ^a   Xu, Xiaoming ^a  

^a NONE

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER SIMULATION; LEARNING ALGORITHMS; LEARNING SYSTEMS; OPTIMIZATION;

NASH EQUILIBRIUM;

MULTI AGENT SYSTEMS;

EID: 0034591615     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. C. Claus and C. Boutilier. The Dynamics of Reinforcement Learning in Cooperative Multi-agent Systems. AAAI-97 Work. Multi-agent Learning, 1997, pp. 13-18, Providence.
2. th intl. Conf. on Machine Learning, 1994, pp. 157-163, New Brunswick, NJ.
3. J.L. Hu and M.P. Wellman. Self-fulfilling bias in multi-agent learning. Proc. ICMAS-98, July 1998, pp. 118-125.
4. th Intl. Conf. on Machine Learning, 1993, pp. 330-337, Amherst, MA.
5. S. Sen, M. Sekaran, J. Hale. Learning to coordinate without sharing information. AAAI-98, pp. 426-431, Seattle.
6. R.M. Wheeler and K.S. Narendra. Decentralized learning in Markov chains. IEEE Trans. Aut. Control, 1998, 31:519-526, 1951
7. E. Kalai and E. Lehrer. Rational learning leads to Nash equilibrium. Econometrica, 1993, 61(5):1019-1045.