Reference

Sources and reading guide

SourceWhat it contributesBoundary of the evidence
Sokota, Vinitsky, Hu, Kolter and Farina, Superhuman AI for Stratego Using Self-Play Reinforcement Learning and Test-Time Search, 2025The Ataraxos method: setup, move and belief transformers, dynamically damped self-play, test-time search by update equivalence, the GPU simulator, and the 15-1-4 series against Pim NiemeijerIts numbers come from 16 H100s for a week plus 4 H100s for 4 days; nothing in this notebook has reproduced them yet
Perolat et al., Mastering the game of Stratego with model-free multiagent reinforcement learning, Science 2022DeepNash: Regularised Nash Dynamics with a reward transformation and replicator dynamics, the 10^535 state count, 84% on Gravon and top-3 rankingsTrained on 1024 TPU nodes according to the Ataraxos authors; the code is no longer functional, so no direct comparison exists
International Stratego Federation rules, chapter 10 (extract in Han Wolf, A model for capture by the two-squares rule, 2012)The two-square rule as three non-stop moves between the same two squares, and its extension to Scouts by the squares they pass overA static look-ahead model of captures under the rule, not a general engine
Strategus rulesThe online platform's wording of the two-square, continuous-chase and 200-move rules used for the Ataraxos evaluationThe chase rule text is informal; the engine implements the paper's formal definition
Gravon rulesClassic rules and the platform DeepNash was evaluated onIts two-square wording (five consecutive turns) differs from the ISF wording the engine follows
Cowling, Powley and Whitehouse, Information Set Monte Carlo Tree Search, 2012Determinization and its known weakness, strategy fusion, which the expectimax rung inheritsResults in other games do not transfer to this implementation
Zhang and Sandholm, General search techniques without common knowledge for imperfect-information games, and application to superhuman Fog of War chess, 2025Obscuro: knowledge-limited unfrozen subgame solving over a sampled information set, one-sided GT-CFR, predictive CFR+ on the last iterate, purification; 80% against the top humanFog of War chess enumerates its information set (up to a million positions); Stratego's must be sampled, which is the open question of the subgame-solving approach
Liu, Fu, Fu and Yang, Opponent-Limited Online Search for Imperfect Information Games, ICML 2023Safe-1-KLSS and the internal gift; OLSS-I and OLSS-II, which limit the opponent's reach and strategy set to shrink the subgameEvaluated in poker variants and two-player Mahjong with tabular blueprints; no result in a game of Stratego's size
Holeček, NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games, 2026A centralised recurrent state-space world model with per-player infoset models and R-NaD in imagination; sample efficiency in Goofspiel and BattleshipGames of a few dozen plies with full unrolls from the first move; the notebook's environment is nearly free, so only the infoset model is tested here

Read the Ataraxos paper alongside the concept pages from self-play reinforcement learning to test-time search, and DeepNash alongside DeepNash and regularised Nash dynamics. The engine's rule choices are in rules and anti-chase. The PDFs are vendored under paper/. Sources were checked on September 18, 2026.