Stochastic Regret Minimization in Extensive-Form Games
This work provides a more flexible and theoretically robust approach for game-solving algorithms, benefiting researchers and practitioners in AI and game theory, though it is incremental as it builds on MCCFR.
The authors tackled the problem of solving large sequential games by developing a new framework for stochastic regret minimization, which generalizes existing methods like MCCFR and yields stronger theoretical convergence results and improved performance in experiments on three games.
Monte-Carlo counterfactual regret minimization (MCCFR) is the state-of-the-art algorithm for solving sequential games that are too large for full tree traversals. It works by using gradient estimates that can be computed via sampling. However, stochastic methods for sequential games have not been investigated extensively beyond MCCFR. In this paper we develop a new framework for developing stochastic regret minimization methods. This framework allows us to use any regret-minimization algorithm, coupled with any gradient estimator. The MCCFR algorithm can be analyzed as a special case of our framework, and this analysis leads to significantly-stronger theoretical on convergence, while simultaneously yielding a simplified proof. Our framework allows us to instantiate several new stochastic methods for solving sequential games. We show extensive experiments on three games, where some variants of our methods outperform MCCFR.