Solving Imperfect-Information Games via Discounted Regret Minimization
This work addresses the challenge of efficiently solving complex imperfect-information games, which is crucial for applications like AI in poker or strategic decision-making, representing a strong incremental advance over existing methods.
The paper tackles the problem of solving large imperfect-information games by introducing novel variants of counterfactual regret minimization (CFR) that discount regrets and reweight iterations, leading to dramatically improved performance. For example, one variant outperforms the prior state-of-the-art algorithm CFR+ in every game tested, including large-scale realistic settings.
Counterfactual regret minimization (CFR) is a family of iterative algorithms that are the most popular and, in practice, fastest approach to approximately solving large imperfect-information games. In this paper we introduce novel CFR variants that 1) discount regrets from earlier iterations in various ways (in some cases differently for positive and negative regrets), 2) reweight iterations in various ways to obtain the output strategies, 3) use a non-standard regret minimizer and/or 4) leverage "optimistic regret matching". They lead to dramatically improved performance in many settings. For one, we introduce a variant that outperforms CFR+, the prior state-of-the-art algorithm, in every game tested, including large-scale realistic settings. CFR+ is a formidable benchmark: no other algorithm has been able to outperform it. Finally, we show that, unlike CFR+, many of the important new variants are compatible with modern imperfect-information-game pruning techniques and one is also compatible with sampling in the game tree.