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

2025-06-02

AI Summary

This paper addresses Fog-of-War Chess (FoW Chess), a highly challenging turn-based imperfect-information game characterized by severe information asymmetry and absence of common knowledge. We propose the first general-purpose imperfect-information search framework that dispenses with the common-knowledge assumption. Methodologically, it integrates an enhanced asynchronous counterfactual regret minimization (CFR) operating over belief spaces, dynamic signal modeling, opponent knowledge inference, and information-value assessment—enabling scalable belief updating and opponent strategy reasoning. Contributions include: (1) achieving superhuman performance in the largest-scale turn-based imperfect-information game to date; (2) substantially outperforming prior state-of-the-art AI agents and top human players; and (3) establishing the largest, most uncertain, and fully deployed imperfect-information search system demonstrating superhuman gameplay.

Technology Category

• Search and Optimization: Adversarial Search
• Game Theory and Economic Paradigms: Imperfect Information
• Multiagent Systems: Adversarial Agents

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation

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 significant 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 (aka. dark chess) is a recognized challenge problem in AI after 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 game in which superhuman performance has been achieved and the largest game in which imperfect-information search has been successfully applied.

Problem

• Developing superhuman AI for imperfect-information Fog of War chess
• Advancing search techniques for reasoning under uncertainty in games
• Achieving scalable performance in large turn-based imperfect-information games

Innovation

• Superhuman AI for Fog of War chess
• Advances in imperfect-information game search
• Scalable reasoning for large turn-based games