Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning

About

We introduce DeepNash, an autonomous agent capable of learning to play the imperfect information game Stratego from scratch, up to a human expert level. Stratego is one of the few iconic board games that Artificial Intelligence (AI) has not yet mastered. This popular game has an enormous game tree on the order of $10^{535}$ nodes, i.e., $10^{175}$ times larger than that of Go. It has the additional complexity of requiring decision-making under imperfect information, similar to Texas hold'em poker, which has a significantly smaller game tree (on the order of $10^{164}$ nodes). Decisions in Stratego are made over a large number of discrete actions with no obvious link between action and outcome. Episodes are long, with often hundreds of moves before a player wins, and situations in Stratego can not easily be broken down into manageably-sized sub-problems as in poker. For these reasons, Stratego has been a grand challenge for the field of AI for decades, and existing AI methods barely reach an amateur level of play. DeepNash uses a game-theoretic, model-free deep reinforcement learning method, without search, that learns to master Stratego via self-play. The Regularised Nash Dynamics (R-NaD) algorithm, a key component of DeepNash, converges to an approximate Nash equilibrium, instead of 'cycling' around it, by directly modifying the underlying multi-agent learning dynamics. DeepNash beats existing state-of-the-art AI methods in Stratego and achieved a yearly (2022) and all-time top-3 rank on the Gravon games platform, competing with human expert players.

Julien Perolat, Bart de Vylder, Daniel Hennes, Eugene Tarassov, Florian Strub, Vincent de Boer, Paul Muller, Jerome T. Connor, Neil Burch, Thomas Anthony, Stephen McAleer, Romuald Elie, Sarah H. Cen, Zhe Wang, Audrunas Gruslys, Aleksandra Malysheva, Mina Khan, Sherjil Ozair, Finbarr Timbers, Toby Pohlen, Tom Eccles, Mark Rowland, Marc Lanctot, Jean-Baptiste Lespiau, Bilal Piot, Shayegan Omidshafiei, Edward Lockhart, Laurent Sifre, Nathalie Beauguerlange, Remi Munos, David Silver, Satinder Singh, Demis Hassabis, Karl Tuyls• 2022

Related benchmarks

TaskDatasetResultRank
Matrix Game Strategy LearningMatching pennies
Last Iterate Exploitability0.00e+0
6
Matrix Game Strategy LearningRock-Paper-Scissors (RPS)
Exploitability0.0012
6
Matrix Game Strategy LearningRandom 10 x 10 Matrix Game
Exploitability (Last Iterate)0.0944
6
Matrix Game Strategy LearningRandom 12 x 6 Matrix Game
Exploitability (Last Iterate)0.0617
6
Board-game self-playAnimal Shogi
Best-Response Win Rate52
5
Equilibrium findingLeduc Hold’em
Exploitability0.227
5
ExploitabilityNeural Kuhn poker
Exploitability30.1
5
Board-game self-playConnect Four
Best-Response Win Rate44
5
Board-game self-playOthello
Best-Response Win Rate67
5
Board-game self-playHex 10k
Best-Response Win Rate89
5
Showing 10 of 10 rows

Other info

Follow for update