Effective learning in the presence of adaptive counterparts

Journal of Algorithms

Volumn 64, Issue 4, 2009, Pages 127-138

  Burkov, Andriy ^a   Chaib draa, Brahim ^a  

^a UNIVERSITÉ LAVAL   (Canada)

Author keywords

Adaptive learning algorithms; Matrix games; Multiagent learning

Indexed keywords

ADAPTIVE DYNAMICS; ADAPTIVE LEARNING ALGORITHM; ADAPTIVE LEARNING ALGORITHMS; EFFECTIVE LEARNING; EQUILIBRIUM SOLUTIONS; FICTITIOUS PLAY; GRADIENT ASCENT; HILL CLIMBING; INTERACTION HISTORY; MATRIX GAME; MATRIX GAMES; MULTIAGENT LEARNING; Q-LEARNING; Q-VALUES; SELF-PLAY;

ADAPTIVE ALGORITHMS; EDUCATION; GAME THEORY; LEARNING SYSTEMS;

LEARNING ALGORITHMS;

EID: 70350566689     PISSN: 01966774     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.jalgor.2009.04.003     Document Type: Article

References (23)

1. Nash J. Equilibrium points in n-person games. Proc. Natl. Acad. Sci. USA 36 1 (1950)
2. Claus C., and Boutilier C. The dynamics of reinforcement learning in cooperative multiagent systems. Proceedings of the Fifteenth National Conference on Artificial Intelligence, AAAI'98 (1998), AAAI Press, Menlo Park, CA 746-752
3. Gies O., and Chaib-draa B. Apprentissage de la coordination multiagent: une méthode basée sur le Q-learning par jeu adaptatif. Rev. Intelligence Artif. 20 2-3 (2006) 385-412
4. Singh S., Kearns M., and Mansour Y. Nash convergence of gradient dynamics in general-sum games. Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence, UAI'00 (2000), Morgan Kaufmann, San Francisco, CA 541-548
5. Hu J., and Wellman M. Nash Q-learning for general-sum stochastic games. J. Mach. Learn. Res. 4 (2003) 1039-1069
6. Banerjee B., and Peng J. Generalized multiagent learning with performance bound. Autonomous Agents Multi-Agent Syst., 1387-2532 15 3 (2007) 281-312
7. Bowling M., and Veloso M. Multiagent learning using a variable learning rate. Artificial Intelligence 136 2 (2002) 215-250
8. M. Bowling, Multiagent learning in the presence of agents with limitations, PhD thesis, Carnegie Mellon University, Pittsburgh, PA, USA, 2003
9. Chang Y., and Kaelbling L.P. Playing is believing: The role of beliefs in multi-agent learning. NIPS'01. Vancouver, Canada, 2001. Adv. Neural Inf. Process. Syst. vol. 14 (2002), MIT Press, Cambridge, MA 1483-1490
10. Tesauro G. Extending Q-learning to general adaptive multi-agent systems. In: Thrun S., Saul L., and Scholkopf B. (Eds). NIPS'04. Adv. Neural Inf. Process. Syst. vol. 16 (2004), MIT Press, Cambridge, MA
11. Shoham Y., Powers R., and Grenager T. If multi-agent learning is the answer, what is the question?. Artificial Intelligence 171 7 (2007) 365-377
12. Crandall J.W., and Goodrich M.A. Learning to compete, compromise, and cooperate in repeated general-sum games. Proceedings of the Twenty Second International Conference on Machine Learning, ICML'05 (2005), ACM Press 161-168
13. Fudenberg D., and Levine D. The Theory of Learning in Games (1998), MIT Press, Cambridge, MA
14. Watkins C., and Dayan P. Q-learning. Mach. Learn. 8 3 (1992) 279-292
15. Young H.P. Individual Strategy and Social Structure: An Evolutionary Theory of Institutions (1998), Princeton University Press, Princeton, NJ
16. Shapley L. Stochastic games. Proc. Natl. Acad. Sci. 39 (1953) 1095-1100
17. Sutton R.S., and Barto A.G. Reinforcement Learning: An Introduction (1998), MIT Press, Cambridge, MA
18. E. Nudelman, J. Wortman, Y. Shoham, K. Leyton-brown, Run the gamut: A comprehensive approach to evaluating game-theoretic algorithms, in: Proceedings of the 3rd International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS'04, 2004, pp. 880-887
19. Darken C., and Moody J. Note on learning rate schedule for stochastic optimisation. NIPS'91. Adv. Neural Inf. Process. Syst. vol. 3 (1991), Morgan Kaufmann, San Mateo, CA 832-838
20. S. Thrun, Efficient exploration in reinforcement learning, PhD thesis, Carnegie Mellon University, Pittsburgh, PA, USA, 1992
21. Chakraborty D., and Sen S. MB-AIM-FSI: A model based framework for exploiting gradient ascent multiagent learners in strategic interactions. Proceedings of the 7th International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS'08 (2008), International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC 371-378
22. R. Powers, Y. Shoham, Learning against opponents with bounded memory, in: Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI'05, Edinburgh, UK, 2005
23. Powers R., and Shoham Y. New criteria and a new algorithm for learning in multi-agent systems. In: Saul L.K., Weiss Y., and Bottou L. (Eds). NIPS'05. Adv. Neural Inf. Process. Syst. vol. 17 (2005), MIT Press, Cambridge, MA