Artificial Intelligence - Chips challenging champions: games, computers and Artificial Intelligence
Lossless abstraction of imperfect information games
Journal of the ACM (JACM)
Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems
Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 2
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 1
A new algorithm for generating equilibria in massive zero-sum games
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 1
First-order algorithm with O(ln(1/ε )) convergence for ε -equilibrium in two-person zero-sum games
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 1
Gradient-based algorithms for finding Nash equilibria in extensive form games
WINE'07 Proceedings of the 3rd international conference on Internet and network economics
Artificial Intelligence
Lossy stochastic game abstraction with bounds
Proceedings of the 13th ACM Conference on Electronic Commerce
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
Evaluating state-space abstractions in extensive-form games
Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems
Hi-index | 0.00 |
Automated abstraction algorithms for sequential imperfect information games have recently emerged as a key component in developing competitive game theory-based agents. The existing literature has not investigated the relative performance of different abstraction algorithms. Instead, agents whose construction has used automated abstraction have only been compared under confounding effects: different granularities of abstraction and equilibrium-finding algorithms that yield different accuracies when solving the abstracted game. This paper provides the first systematic evaluation of abstraction algorithms. Two families of algorithms have been proposed. The distinguishing feature is the measure used to evaluate the strategic similarity between game states. One algorithm uses the probability of winning as the similarity measure. The other uses a potential-aware similarity measure based on probability distributions over future states. We conduct experiments on Rhode Island Hold'em poker. We compare the algorithms against each other, against optimal play, and against each agent's nemesis. We also compare them based on the resulting game's value. Interestingly, for very coarse abstractions the expectation-based algorithm is better, but for moderately coarse and fine abstractions the potential-aware approach is superior. Furthermore, agents constructed using the expectation-based approach are highly exploitable beyond what their performance against the game's optimal strategy would suggest.