Learning multiagent coordination: An adaptative Q-learning approach;Apprentissage de la coordination multiagent Une méthode basée sur le Q-learning par jeu adaptatif

Revue d'Intelligence Artificielle

Volumn 20, Issue 2-3, 2006, Pages 383-410

  Gies, Olivier ^a   Chaib Draa, Brahim ^a  

^a UNIVERSITÉ LAVAL   (Canada)

Author keywords

Adaptative game; Markovien game; MDP; Multiagent learning

Indexed keywords

ALGORITHMS; LEARNING SYSTEMS; PARETO PRINCIPLE; RANDOM PROCESSES;

ADAPTATIVE GAME; NASH EQUILIBRIA; Q-LEARNING; STOCHASTIQUE GAMES;

MULTI AGENT SYSTEMS;

EID: 34548132482     PISSN: 0992499X     EISSN: None     Source Type: Journal    
DOI: 10.3166/ria.20.383-410     Document Type: Article

References (18)

1. Banerjee B., Peng J., « Countering Deception in Multiagent Reinforcement Learning», Procee-dings of the Second International Joint Conference on Autonomous Agents and Multi Agent Systems (AAMAS-03) Workshop on Trust, Privacy, Deception and Fraud in Agent Societies, Melbourne, Australia, July, 2003.
2. Brown G. W., « Iterative Solution of Games by Fictitious Play », in T. C. Koopmans (ed.), Activity Analysis of Production and Allocation, Wiley, New York, chapter XXIV, 1951.
3. Claus C., Boutilier C., « The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems », AAAI/IAAI, p. 746-752, 1998.
4. Fudenberg D., Levine D. K., The Theory of Learning in Games, The MIT Press, Cambridge, Massaehussets, 1998.
5. Fudenberg D., Tirole J., Game Theory, MIT Press, 1994.
6. Greenwald A., Hall K., « Correlated-Q Learning », Proceedings of the Twentieth International Conference on Machine Learning, p. 242-249, 2003.
7. Hofbauer J., Sandholm W. H., « On the Global Convergence of Stochastic Fictitious Play », Econometrica, vol. 70, ň 6, p. 2265-2294, November, 2002. available at http://ideas.repec.org/a/ecm/emetrp/ v70y2002i6p2265-2294.html.
8. Hu J., Wellman M. P., « Nash Q-learning for general-sum stochastic games », J. Mach. Learn. Res., vol. 4, p. 1039-1069, 2003.
9. Kaelbling L. P., Littman M. L., Moore A. P., « Reinforcement Learning: A Survey », Journal of Artificial Intelligence Research, vol. 4, p. 237-285, 1996.
10. Littman M. L., « Markov Games as a Framework for Multi-Agent Reinforcement Learning», Proceedings of the 11th International Conference on Machine Learning (ML-94), Morgan Kaufmann, New Brunswick, NJ, p. 157-163, 1994.
11. Littman M. L., « Friend-or-foe: Q-learning in general-sum stochastic games », Proceedings of the Eighteenth International Conference on Machine Learning, p. 322-328, 2001.
12. Shapley L. S., « Stochastic Games », Proceedings of the National Academy of Science, vol. 39, p. 327-332, 1953.
13. Tesauro G., « Extending Q-Leaming to General Adaptive Multi-Agent Systems », in S. Thrun, L. Saul, B. Schülkopf (eds), Advances in Neural Information Processing Systems 16, MIT Press, Cambridge, MA, 2004.
14. Vidal J. M., Durfee E. H., « Predicting the Expected Behavior of Agents that Learn About Agents : The CLRI Framework », Autonomous Agents and Multi-Agent Systems, vol. 6, n&̌ l, p. 77-107, 2003.
15. Wang X., Sandholm T., « Reinforcement Learning to Play an Optimal Nash Equilibrium in Team Markov Games », in S. Becker, S. Thrun, K. Obermayer (eds), Advances in Neural information Processing Systems 15, MIT Press, Cambridge, MA, p. 1571-1578, 2003.
16. Watkins C. J., Dayan P., « Q-learning », Machine Learning, vol. 8, n&̌ 3/4, p. 279-292, 1992.
17. Weinberg M., Rosenschein J. S., « Best-Response Multiagent Learning in Non-Stationary Environments », Proceedings of the Third International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-04), Columbia University, New York City, July, 2004.
18. Young H. P., Individual Strategy and Social Structure : An Evolutionary Theory of Instituions, Princeton University Press, Princeton, New Jersey, 1998.