AINeutralarXiv – CS AI · 5h ago6/10
🧠
Outbidding and Outbluffing Elite Humans: Mastering Liar's Poker via Self-Play and Reinforcement Learning
Researchers have developed Solly, an AI agent that achieved elite human-level performance in Liar's Poker through self-play reinforcement learning, winning over 50% of hands against top players. This breakthrough extends AI capabilities beyond two-player games to complex multi-player scenarios with imperfect information, demonstrating novel strategic behaviors that resist exploitation by world-class competitors.