Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 2
Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems - Volume 1
Abstraction pathologies in extensive games
Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems - Volume 2
AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
Methods for empirical game-theoretic analysis
AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
Approximating game-theoretic optimal strategies for full-scale poker
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Probabilistic state translation in extensive games with large action sets
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Smoothing Techniques for Computing Nash Equilibria of Sequential Games
Mathematics of Operations Research
Strategy purification and thresholding: effective non-equilibrium approaches for playing large games
Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems - Volume 2
Case-based strategies in computer poker
AI Communications
Hi-index | 0.00 |
When solving extensive-form games with large action spaces, typically significant abstraction is needed to make the problem manageable from a modeling or computational perspective. When this occurs, a procedure is needed to interpret actions of the opponent that fall outside of our abstraction (by mapping them to actions in our abstraction). This is called an action translation mapping. Prior action translation mappings have been based on heuristics without theoretical justification. We show that the prior mappings are highly exploitable and that most of them violate certain natural desiderata. We present a new mapping that satisfies these desiderata and has significantly lower exploitability than the prior mappings. Furthermore, we observe that the cost of this worst-case performance benefit (low exploitability) is not high in practice; our mapping performs competitively with the prior mappings against no-limit Texas Hold'em agents submitted to the 2012 Annual Computer Poker Competition. We also observe several paradoxes that can arise when performing action abstraction and translation; for example, we show that it is possible to improve performance by including suboptimal actions in our abstraction and excluding optimal actions.