Combining Deep Reinforcement Learning and Search for Imperfect-Information Games

TL;DR

This paper introduces ReBeL, a reinforcement learning framework combining search that converges to Nash equilibrium in two-player zero-sum imperfect-information games, demonstrating superhuman poker performance with less domain knowledge.

Contribution

ReBeL is a novel general framework that extends deep reinforcement learning and search to imperfect-information games, with provable convergence to Nash equilibrium.

Findings

ReBeL converges to an approximate Nash equilibrium in imperfect-information games.

ReBeL achieves superhuman performance in heads-up no-limit Texas hold'em poker.

ReBeL requires less domain knowledge than previous poker AIs.

Abstract

The combination of deep reinforcement learning and search at both training and test time is a powerful paradigm that has led to a number of successes in single-agent settings and perfect-information games, best exemplified by AlphaZero. However, prior algorithms of this form cannot cope with imperfect-information games. This paper presents ReBeL, a general framework for self-play reinforcement learning and search that provably converges to a Nash equilibrium in any two-player zero-sum game. In the simpler setting of perfect-information games, ReBeL reduces to an algorithm similar to AlphaZero. Results in two different imperfect-information games show ReBeL converges to an approximate Nash equilibrium. We also show ReBeL achieves superhuman performance in heads-up no-limit Texas hold'em poker, while using far less domain knowledge than any prior poker AI.