Mastering complex card games like GuanDan (掼蛋) and DouDiZhu (斗地主) using self-play RL and causal sequence modeling with zero domain knowledge
reinforcement-learning transformer card-game reinforcement-learning-algorithms representation-learning language-model game-ai doudizhu reinforcement-learning-agent self-play world-models sequence-modeling world-models-rl doudizhu-ai guandan guandan-ai
-
Updated
Jul 12, 2026 - Python