Abstract | ||
---|---|---|
Adaptation to other initially unknown agents often requires computing an effec- tive counter-strategy. In the Bayesian paradigm, one must find a good counter- strategy to the inferred posterior of the other agents' behavior. In the experts paradigm, one may want to choose experts that are good counter-strategies to the other agents' expected behavior. In this paper we introduce a technique for computing robust counter-strategies for adaptation in multiagent scenarios under a variety of paradigms. The strategies can take advantage of a suspected tendency in the decisions of the other agents, while bounding the worst-case performance when the tendency is not observed. The technique involves solving a modified game, and therefore can make use of recently developed algorithms for solving very large extensive games. We demonstrate the effectiveness of the technique in two-player Texas Hold'em. We show that the computed poker strategies are sub- stantially more robust than best response counter-strategies, while still exploiting a suspected tendency. We also compose the generated strategies in an experts al- gorithm showing a dramatic improvement in performance over using simple best responses. |
Year | Venue | Field |
---|---|---|
2007 | NIPS | Computer science,Best response,Artificial intelligence,Machine learning,Bayesian probability,Bounding overwatch |
DocType | Citations | PageRank |
Conference | 39 | 3.33 |
References | Authors | |
10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael Johanson | 1 | 367 | 25.69 |
Martin Zinkevich | 2 | 1893 | 160.99 |
Michael H. Bowling | 3 | 2460 | 205.07 |