No regrets about no-regret

Artificial Intelligence

Volumn 171, Issue 7, 2007, Pages 434-439

  Chang, Yu Han ^a  

^a UNIVERSITY OF SOUTHERN CALIFORNIA   (United States)

Author keywords

Game theory; Multi agent learning; Regret minimization

Indexed keywords

LEARNING ALGORITHMS; LEARNING SYSTEMS; MULTI AGENT SYSTEMS; SAFETY FACTOR;

MULTI-AGENT LEARNING; REGRET-MINIMIZATION;

GAME THEORY;

EID: 34249074707     PISSN: 00043702     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.artint.2006.12.007     Document Type: Article

References (9)

1. P. Auer, N. Cesa-Bianchi, Y. Freund, R.E. Schapire, Gambling in a rigged casino: the adversarial multi-armed bandit problem, in: Proceedings of the 36th Symposium on Foundations of Computer Science, 1995
2. Y. Chang, P.R. Cohen, C.T. Morrison, W. Kerr, R.S. Amant, The Jean system, in: Proceedings of the International Conference on Development and Learning, 2006
3. Y. Chang, L.P. Kaelbling, Playing is believing: The role of beliefs in multi-agent learning, in: Advances in Neural Information Processing Systems, 2001
4. Y. Chang, L.P. Kaelbling, Hedged learning: Regret-minimization with learning experts, in: International Conference on Machine Learning, 2005
5. D.P. de Farias, N. Meggido, How to combine expert (or novice) advice when actions impact the environment, in: Advances in Neural Information Processing Systems, 2004
6. Freund Y., and Schapire R.E. Adaptive game playing using multiplicative weights. Games and Economic Behavior 29 (1999) 79-103
7. M. Kearns, S. Singh, Near-optimal reinforcement learning in polynomial time, in: Proceedings of the International Conference on Machine Learning, 1998
8. S. Mannor, N. Shimkin, The empirical Bayes envelope approach to regret minimization, Technion Technical Report EE-No1261, 2000
9. A. Strehl, C. Mesterharm, M.L. Littman, H. Hirsh, Experience-efficient learning in associative bandit problems, in: Proceedings of the International Conference on Machine Learning, 2006