Multi-agent learning experiments on repeated matrix games

ICML 2010 - Proceedings, 27th International Conference on Machine Learning

Volumn , Issue , 2010, Pages 119-126

  Bouzy, Bruno ^a   Métivier, Marc ^a  

^a Huawei Technologies Co   (France)

Author keywords

[No Author keywords available]

Indexed keywords

COOPERATIVE GAME; MATRIX GAME; MULTI-AGENT LEARNING; Q-LEARNING; STATE OF THE ART; ZERO-SUM GAME;

EXPERIMENTS; LEARNING SYSTEMS;

LEARNING ALGORITHMS;

EID: 77956556555     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (26)

1. Airiau, S., Saha, S., and Sen, S. Evolutionary tournament-based comparison of learning and non-learning algorithm for iterated games. Journal of Artificial Societies and Social Simulation, 10(3):7, 2007. ISSN 1460-7425.
2. Auer, P., Cesa-Bianchi, N., and Fischer, P. Finite-time analysis of the multi-armed bandit problem. Machine Learning, 47(2-3):235-256, 2002a.
3. Auer, P., Cesa-Bianchi, N., Freund, Y., and Schapire, R.E. The non stochastic multi-armed bandit problem. SIAM Journal, 32(1):48-77, 2002b.
4. Banerjee, B. and Peng, J. Performance bounded reinforcement learning in strategic interactions. In AAAI, pp. 2-7, 2004.
5. Bowling, M. Multiagent Learning in the Presence of Agents with Limitations. PhD thesis, CMU, 2003.
6. Brams, S. J. Theory of Moves. Cambridge University Press, 1994.
7. Brown, G.W. Iterative solution of games by fictitious play. Activity Analysis of Production and Allocation, pp. 374-376, 1951.
8. Chang, Y.H. and Kaelbling, L.P. Hedged learning: regret-minimization with learning experts. In ICML, pp. 121-128, 2005.
9. Claus, C. and Boutilier, C. The dynamics of reinforcement learning in cooperative multi-agent systems. In AAAI, pp. 746-752, 1998.
10. Conitzer, V. and Sandholm, T. AWESOME: A general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents. In ICML, pp. 83-90, 2003.
11. Crandall, J.W. and Goodrich, M.A. Learning to compete, compromise, and cooperate in repeated general-sum games. In ICML, pp. 161-168, 2005.
12. Hart, S. and Mas-Colell, A. A simple adaptive procedure leading to correlated equilibrium. Econometrica, 68(5):1127-1150, September 2000.
13. Littman, M. Markov games as a framework for multi-agent reinforcement learning. In ICML, pp. 157-163, 1994.
14. Littman, M. Friend-or-foe Q-learning in general-sum games. In ICML, pp. 322-328, 2001.
15. Nudelman, E., Wortman, J., Shoham, Y., and Leyton-Brown, K. Run the GAMUT: a comprehensive approach to evaluating game-theoretic algorithms. In AMAAS, pp. 880-887, 2004.
16. Powers, R. and Shoham, Y. New criteria and a new algorithm for learning in multiagent systems. In NIPS, 2004.
17. Powers, R. and Shoham, Y. Learning against opponents with bounded memory. In IJCAI, pp. 817-822, 2005.
18. Powers, R., Shoham, Y., and Vu, T. A general criterion and an algorithmic framework for learning in multi-agent systems. Machine Learning, 67(1-2):45-76, 2007.
19. Robinson, J. An iterative method of solving a game. Annals of Mathematics, 44:296-301, 1951.
20. Sandholm, T. and Crites, R. Multiagent reinforcement learning in the iterated prisoner's dilemma. Biosystems, 37(1-2):147-166, 1996.
21. Shoham, Y., Powers, R., and Grenager, T. If multi-agent learning is the answer, what is the question? Artificial Intelligence, 171:365-377, 2007.
22. Singh, S., Kearns, M., and Mansour, Y. Nash convergence of gradient dynamics in general-sum games. In UAI, pp. 541-548, 2000.
23. Stimpson, J.L. and Goodrich, M.A. Learning to cooperate in a social dilemma: a satisficing approach to bargaining. In ICML, pp. 728-735, 2003.
24. Stone, P. and Littman, M. Implicit negotiation in repeated games. In Meyer, John-Jules and Tambe, Milind (eds.), ATAL, pp. 96-105, 2001.
25. Watkins, C. and Dayan, P. Q-learning. Machine Learning, 8:279-292, 1992.
26. Zawadzki, E. Multiagent learning and empirical methods. Master's thesis, University of British Columbia, 2005.