Reduced Space and Faster Convergence in Imperfect-Information Games via Regret-Based Pruning

TL;DR

This paper introduces Total RBP, an enhancement to Regret-Based Pruning in CFR algorithms, which reduces space and accelerates convergence in solving large zero-sum imperfect-information games.

Contribution

It presents Total RBP, a novel pruning method that asymptotically eliminates suboptimal actions, leading to faster convergence and significant space savings in game-solving.

Findings

Achieves an order of magnitude reduction in space usage.

Provably prunes non-essential actions in zero-sum games.

Results improve with larger game sizes.

Abstract

Counterfactual Regret Minimization (CFR) is the most popular iterative algorithm for solving zero-sum imperfect-information games. Regret-Based Pruning (RBP) is an improvement that allows poorly-performing actions to be temporarily pruned, thus speeding up CFR. We introduce Total RBP, a new form of RBP that reduces the space requirements of CFR as actions are pruned. We prove that in zero-sum games it asymptotically prunes any action that is not part of a best response to some Nash equilibrium. This leads to provably faster convergence and lower space requirements. Experiments show that Total RBP results in an order of magnitude reduction in space, and the reduction factor increases with game size.