Data Biased Robust Counter Strategies

Michael Johanson, Michael Bowling
; Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics, PMLR 5:264-271, 2009.

Abstract

The problem of exploiting information about the environment while still being robust to inaccurate or incomplete information arises in many domains. Competitive imperfect information games where the goal is to maximally exploit an unknown opponent’s weaknesses are an example of this problem. Agents for these games must balance two objectives. First, they should aim to exploit data from past interactions with the opponent, seeking a best-response counter strategy. Second, they should aim to minimize losses since the limited data may be misleading or the opponent’s strategy may have changed, suggesting an opponent-agnostic Nash equilibrium strategy. In this paper, we show how to partially satisfy both of these objectives at the same time, producing strategies with favorable tradeoffs between the ability to exploit an opponent and the capacity to be exploited. Like a recently published technique, our approach involves solving a modified game; however the result is more generally applicable and even performs well in situations with very limited data. We evaluate our technique in the game of two-player, Limit Texas Hold’em.

Cite this Paper


BibTeX
@InProceedings{pmlr-v5-johanson09a, title = {Data Biased Robust Counter Strategies}, author = {Michael Johanson and Michael Bowling}, booktitle = {Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics}, pages = {264--271}, year = {2009}, editor = {David van Dyk and Max Welling}, volume = {5}, series = {Proceedings of Machine Learning Research}, address = {Hilton Clearwater Beach Resort, Clearwater Beach, Florida USA}, month = {16--18 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v5/johanson09a/johanson09a.pdf}, url = {http://proceedings.mlr.press/v5/johanson09a.html}, abstract = {The problem of exploiting information about the environment while still being robust to inaccurate or incomplete information arises in many domains. Competitive imperfect information games where the goal is to maximally exploit an unknown opponent’s weaknesses are an example of this problem. Agents for these games must balance two objectives. First, they should aim to exploit data from past interactions with the opponent, seeking a best-response counter strategy. Second, they should aim to minimize losses since the limited data may be misleading or the opponent’s strategy may have changed, suggesting an opponent-agnostic Nash equilibrium strategy. In this paper, we show how to partially satisfy both of these objectives at the same time, producing strategies with favorable tradeoffs between the ability to exploit an opponent and the capacity to be exploited. Like a recently published technique, our approach involves solving a modified game; however the result is more generally applicable and even performs well in situations with very limited data. We evaluate our technique in the game of two-player, Limit Texas Hold’em.} }
Endnote
%0 Conference Paper %T Data Biased Robust Counter Strategies %A Michael Johanson %A Michael Bowling %B Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2009 %E David van Dyk %E Max Welling %F pmlr-v5-johanson09a %I PMLR %J Proceedings of Machine Learning Research %P 264--271 %U http://proceedings.mlr.press %V 5 %W PMLR %X The problem of exploiting information about the environment while still being robust to inaccurate or incomplete information arises in many domains. Competitive imperfect information games where the goal is to maximally exploit an unknown opponent’s weaknesses are an example of this problem. Agents for these games must balance two objectives. First, they should aim to exploit data from past interactions with the opponent, seeking a best-response counter strategy. Second, they should aim to minimize losses since the limited data may be misleading or the opponent’s strategy may have changed, suggesting an opponent-agnostic Nash equilibrium strategy. In this paper, we show how to partially satisfy both of these objectives at the same time, producing strategies with favorable tradeoffs between the ability to exploit an opponent and the capacity to be exploited. Like a recently published technique, our approach involves solving a modified game; however the result is more generally applicable and even performs well in situations with very limited data. We evaluate our technique in the game of two-player, Limit Texas Hold’em.
RIS
TY - CPAPER TI - Data Biased Robust Counter Strategies AU - Michael Johanson AU - Michael Bowling BT - Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics PY - 2009/04/15 DA - 2009/04/15 ED - David van Dyk ED - Max Welling ID - pmlr-v5-johanson09a PB - PMLR SP - 264 DP - PMLR EP - 271 L1 - http://proceedings.mlr.press/v5/johanson09a/johanson09a.pdf UR - http://proceedings.mlr.press/v5/johanson09a.html AB - The problem of exploiting information about the environment while still being robust to inaccurate or incomplete information arises in many domains. Competitive imperfect information games where the goal is to maximally exploit an unknown opponent’s weaknesses are an example of this problem. Agents for these games must balance two objectives. First, they should aim to exploit data from past interactions with the opponent, seeking a best-response counter strategy. Second, they should aim to minimize losses since the limited data may be misleading or the opponent’s strategy may have changed, suggesting an opponent-agnostic Nash equilibrium strategy. In this paper, we show how to partially satisfy both of these objectives at the same time, producing strategies with favorable tradeoffs between the ability to exploit an opponent and the capacity to be exploited. Like a recently published technique, our approach involves solving a modified game; however the result is more generally applicable and even performs well in situations with very limited data. We evaluate our technique in the game of two-player, Limit Texas Hold’em. ER -
APA
Johanson, M. & Bowling, M.. (2009). Data Biased Robust Counter Strategies. Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics, in PMLR 5:264-271

Related Material