Depth-Limited Solving for Imperfect-Information Games

TL;DR

This paper presents a novel depth-limited solving method for imperfect-information games, enabling the creation of a strong poker AI that is computationally efficient and robust against various opponent strategies.

Contribution

It introduces a new approach allowing depth-limited search in imperfect-information games by considering multiple opponent strategies at the depth limit.

Findings

The poker AI defeats previous top agents.

The approach is computationally efficient, using only a 4-core CPU.

It demonstrates robustness to different opponent strategies.

Abstract

A fundamental challenge in imperfect-information games is that states do not have well-defined values. As a result, depth-limited search algorithms used in single-agent settings and perfect-information games do not apply. This paper introduces a principled way to conduct depth-limited solving in imperfect-information games by allowing the opponent to choose among a number of strategies for the remainder of the game at the depth limit. Each one of these strategies results in a different set of values for leaf nodes. This forces an agent to be robust to the different strategies an opponent may employ. We demonstrate the effectiveness of this approach by building a master-level heads-up no-limit Texas hold'em poker AI that defeats two prior top agents using only a 4-core CPU and 16 GB of memory. Developing such a powerful agent would have previously required a supercomputer.