Timezone: »

 
Poster
Depth-Limited Solving for Imperfect-Information Games
Noam Brown · Tuomas Sandholm · Brandon Amos

Wed Dec 05 02:00 PM -- 04:00 PM (PST) @ Room 210 #84
in Wed Poster Session B »

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.

Keywords: Multi-Agent RL · Game Theory and Computational Economics · Game Playing

Author Information

Noam Brown (Carnegie Mellon University)
Tuomas Sandholm (Carnegie Mellon University)
Brandon Amos (Carnegie Mellon University)

More from the Same Authors