LAUSR

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. Description Machine learning to play Stratego Stratego is a popular two-player imperfect information board game. Because of its complexity stemming from its enormous game tree, decision-making under imperfect information, and a piece deployment phase at the start, Stratego poses a challenge for artificial intelligence (AI). Previous computer programs only performed at an amateur level at best. Perolat et al. introduce a model-free multiagent reinforcement learning methodology and show that it can achieve human expert–level performance in Stratego. The present work not only adds to the growing list of games that AI systems can play as well or even better than humans but may also facilitate further applications of reinforcement learning methods in real-world, large-scale multiagent problems that are characterized by imperfect information and thus are currently unsolvable. —YS Reinforcement learning achieves human expert–level performance in the large-scale imperfect information board game Stratego.