Lazy-CFR: fast and near optimal regret minimization for extensive games with imperfect information
This work addresses computational bottlenecks for researchers and practitioners in game theory and AI, offering a more efficient algorithm for solving imperfect information games, though it is incremental as it builds on existing CFR methods.
The paper tackles the inefficiency of Counterfactual Regret Minimization (CFR) in large extensive games by introducing a lazy update technique, resulting in Lazy-CFR which reduces traversal from O(|I|) to O(√|I|) information sets per round while maintaining similar regret bounds and showing significant performance improvements in experiments.
Counterfactual regret minimization (CFR) is the most popular algorithm on solving two-player zero-sum extensive games with imperfect information and achieves state-of-the-art performance in practice. However, the performance of CFR is not fully understood, since empirical results on the regret are much better than the upper bound proved in \cite{zinkevich2008regret}. Another issue is that CFR has to traverse the whole game tree in each round, which is time-consuming in large scale games. In this paper, we present a novel technique, lazy update, which can avoid traversing the whole game tree in CFR, as well as a novel analysis on the regret of CFR with lazy update. Our analysis can also be applied to the vanilla CFR, resulting in a much tighter regret bound than that in \cite{zinkevich2008regret}. Inspired by lazy update, we further present a novel CFR variant, named Lazy-CFR. Compared to traversing $O(|\mathcal{I}|)$ information sets in vanilla CFR, Lazy-CFR needs only to traverse $O(\sqrt{|\mathcal{I}|})$ information sets per round while keeping the regret bound almost the same, where $\mathcal{I}$ is the class of all information sets. As a result, Lazy-CFR shows better convergence result compared with vanilla CFR. Experimental results consistently show that Lazy-CFR outperforms the vanilla CFR significantly.