Paper
Mastering the game of Stratego with model-free multiagent reinforcement learning
We introduce DeepNash, an autonomous agent that plays the imperfect information game Stratego at a human expert level. Stratego is one of the few iconic board games that artificial intelligence (AI) has not yet mastered. It is a game characterized by a twin challenge: It requires long-term strategic thinking as in chess, but it also requires dealing with imperfect information as in poker. The technique underpinning DeepNash uses a game-theoretic, model-free deep reinforcement learning method, without search, that learns to master Stratego through self-play from scratch. DeepNash beat existing state-of-the-art AI methods in Stratego and achieved a year-to-date (2022) and all-time top-three ranking on the Gravon games platform, competing with human expert players.
Authors: 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