`

Timezone: »

 
Poster
Computing Robust Counter-Strategies
Michael Johanson · Martin A Zinkevich · Michael Bowling

Mon Dec 03 10:30 AM -- 10:40 AM (PST) @ None #None

Adaptation to other initially unknown agents often requires computing an effective 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 substantially more robust than best response counter-strategies, while still exploiting a suspected tendency. We also compose the generated strategies in an experts algorithm showing a dramatic improvement in performance over using simple best responses.

Author Information

Michael Johanson (University of Alberta)
Martin A Zinkevich (Yahoo! Inc.)
Michael Bowling (DeepMind / University of Alberta)

More from the Same Authors