AI Solly outbluffs elite humans at Liar’s Poker
AI that thrives on bluffing
Researchers built Solly, an AI that learns Liar’s Poker—a fast, bluff-heavy game with many players and hidden info.
Instead of studying only two-player poker, Solly tackles truly multi-player dynamics. Trained via self-play with a model-free, actor-critic deep reinforcement learning approach, it taught itself when to bid, call, or bluff.
- Performance: Won over 50% of hands and earned positive equity in both heads-up and multi-player matches.
- Against people: Played at elite human level and wasn’t easily exploitable by world-class players.
- Against AI: Outperformed large language models, even those designed for reasoning.
- Strategy: Discovered novel bidding patterns and used effective randomization to stay unpredictable.
Why it matters: Liar’s Poker pushes AI beyond perfect-information games into messy, human-like uncertainty and deception—a step toward systems that can reason, negotiate, and make decisions with incomplete data.
Paper: arXiv:2511.03724
Paper: http://arxiv.org/abs/2511.03724v1
Register: https://www.AiFeta.com
#AI #ReinforcementLearning #SelfPlay #GameTheory #DeepRL #MultiAgent #LiarsPoker #Poker
