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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Brian Hu, Sandholm, Tuomas
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915824995926016
author Zhang, Brian Hu
Sandholm, Tuomas
author_facet Zhang, Brian Hu
Sandholm, Tuomas
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_01242
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle General search techniques without common knowledge for imperfect-information games, and application to superhuman Fog of War chess
Zhang, Brian Hu
Sandholm, Tuomas
Computer Science and Game Theory
Artificial Intelligence
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.
title General search techniques without common knowledge for imperfect-information games, and application to superhuman Fog of War chess
topic Computer Science and Game Theory
Artificial Intelligence
url https://arxiv.org/abs/2506.01242