Automated Action Abstraction of Imperfect Information Extensive-Form Games

Proceedings of the 25th AAAI Conference on Artificial Intelligence, AAAI 2011

Volumn , Issue , 2011, Pages 681-687

  Hawkin, John ^a   Holte, Robert ^a   Szafron, Duane ^a  

^a UNIVERSITY OF ALBERTA   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

ABSTRACTING; FINANCIAL MARKETS;

ACTION SPACES; DECISION POINTS; DECISION PROBLEMS; EXTENSIVE-FORM GAMES; IMPERFECT INFORMATION; MULTI AGENT; NASH EQUILIBRIUM STRATEGIES; STOCK TRADING; TEXAS HOLD'EM; TRADING AGENT;

MULTI AGENT SYSTEMS;

EID: 84876942189     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. Antos, A.; Munos, R.; and Szepesvari, C. 2007. Fitted Q-iteration in continuous action-space MDPs. In NIPS, 9-16.
2. Chen, B., and Ankenman, J. 2007. The mathematics of poker. ConJelCo publishing company.
3. Dean, T.; Kim, K.; and Givan, R. 1998. Solving stochastic planning problems with large state and action spaces. In Proc. Fourth International Conf. on Artificial Intelligence Planning Systems, 102-110. AAAI Press.
4. Gilpin, A., and Sandholm, T. 2007a. Better automated abstraction techniques for imperfect information games, with application to Texas Hold'em poker. In AAMAS, 1168-1175.
5. Gilpin, A., and Sandholm, T. 2007b. Gradient-based algorithms for finding Nash equilibria in extensive form games. In WINE, 57-69.
6. Gilpin, A.; Sandholm, T.; and Sorensen, T. B. 2007. Potential-aware automated abstraction of sequential games, and holistic equilibrium analysis of Texas Hold'em poker. In AAAI, 50-57.
7. Gilpin, A.; Sandholm, T.; and Sorensen, T. B. 2008. A heads-up no-limit Texas Hold'em poker player: Discretized betting models and automatically generated equilibrium-finding programs. In AAMAS, 911-918.
8. Kuhn, H. W. 1950. Simplified two-person poker. Contributions to the Theory of Games 1:97-103.
9. Lazaric, A.; Restelli, M.; and Bonarini, A. 2008. Reinforcement learning in continuous action spaces through sequential Monte Carlo methods. In NIPS, 833-840.
10. Madeira, C. A. G.; Corruble, V.; and Ramalho, G. 2006. Designing a reinforcement learning-based adaptive AI for large-scale strategy games. In AIIDE, 121-123.
11. Schnizlein, D.; Bowling, M.; and Szafron, D. 2009. Probabilistic state translation in extensive games with large action sets. In IJCAI.
12. Schnizlein, D. 2009. State translation in no-limit poker. Master's thesis, University of Alberta.
13. Tijs, S. 1980. Stochastic games with one big action space in each state. Methods of Operations Research 38:161-173.
14. van Hasselt, H., and Wiering, M. 2007. Reinforcement learning in continuous action spaces. In IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning, 272-279.
15. Waugh, K.; Bard, N.; and Bowling, M. 2009. Strategy grafting in extensive games. In NIPS, 2026-2034.
16. Waugh, K.; Schnizlein, D.; Bowling, M.; and Szafron, D. 2009a. Abstraction pathologies in extensive games. In AAMAS, 781-788.
17. Waugh, K.; Zinkevich, M.; Johanson, M.; Kan, M.; Schnizlein, D.; and Bowling, M. 2009b. A practical use of imperfect recall. In Proceedings of the Eighth Symposium on Abstraction, Reformulation and Approximation (SARA), 175-182.
18. Zinkevich, M.; Johanson, M.; Bowling, M.; and Piccione, C. 2008. Regret minimization in games with incomplete information. In NIPS, 1729-1736.