General search techniques without common knowledge for imperfect-information games, and application to superhuman Fog of War chess

TL;DR

This paper introduces Obscuro, a superhuman AI for Fog of War chess, demonstrating advanced search techniques for imperfect-information games and outperforming previous AI and human players, including the best in the world.

Contribution

The paper presents novel search methods enabling strong, scalable reasoning in imperfect-information games, specifically applied to Fog of War chess, achieving superhuman performance.

Findings

Obscuro outperforms prior AI and human players.

FoW chess is the largest imperfect-information turn-based game with superhuman AI.

Successful application of imperfect-information search techniques.

Abstract

Since the advent of AI, games have served as progress benchmarks. Meanwhile, imperfect-information variants of chess have existed for over a century, present extreme challenges, and have been the focus of decades of AI research. Beyond calculation needed in regular chess, they require reasoning about information gathering, the opponent's knowledge, signaling, etc. The most popular variant, Fog of War (FoW) chess (a.k.a. dark chess), has been a major challenge problem in imperfect-information game solving since superhuman performance was reached in no-limit Texas hold'em poker. We present Obscuro, the first superhuman AI for FoW chess. It introduces advances to search in imperfect-information games, enabling strong, scalable reasoning. Experiments against the prior state-of-the-art AI and human players -- including the world's best -- show that Obscuro is significantly stronger. FoW chess is the largest (by amount of imperfect information) turn-based zero-sum game in which superhuman performance has been achieved and the largest zero-sum game in which imperfect-information search has been successfully applied.