2019/06/05 by Jack Serrino, Max Kleiman-Weiner, Serrino, Jack +6 · 3 voices · 18 citations
Computer Science · Economics, Econometrics and Finance · Mathematics · Psychology · #Artificial Intelligence in Games #Artificial intelligence #Computer science #Computer security #Contrast (vision) #Counterfactual thinking #Key (lock) #Machine learning #Psychology #Regret #Reinforcement Learning in Robotics #Reinforcement learning #Social psychology #Sports Analytics and Performance #Value (mathematics) #cs.LG #cs.MA #stat.ML
paper · pdf · doi:10.48550/arxiv.1906.02330
published in arXiv (Cornell University) (Cornell University) · Jack Serrino and Max Kleiman-Weiner contributed equally
arxiv created 2019/06/05 · openalex publication_date 2019/06/05 · arxiv updated 2019/06/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent breakthroughs in AI for multi-agent games like Go, Poker, and Dota, have seen great strides in recent years. Yet none of these games address the real-life challenge of cooperation in the presence of unknown and uncertain teammates. This challenge is a key game mechanism in hidden role games. Here we develop the DeepRole algorithm, a multi-agent reinforcement learning agent that we test on The Resistance: Avalon, the most popular hidden role game. DeepRole combines counterfactual regret minimization (CFR) with deep value networks trained through self-play. Our algorithm integrates deductive reasoning into vector-form CFR to reason about joint beliefs and deduce partially observable actions. We augment deep value networks with constraints that yield interpretable representations of win probabilities. These innovations enable DeepRole to scale to the full Avalon game. Empirical game-theoretic methods show that DeepRole outperforms other hand-crafted and learned agents in five-player Avalon. DeepRole played with and against human players on the web in hybrid human-agent teams. We find that DeepRole outperforms human players as both a cooperator and a competitor.