Mastering complex card games like GuanDan (掼蛋) and DouDiZhu (斗地主) using self-play RL and sequence modeling with zero domain knowledge
reinforcement-learning deep-learning q-learning pytorch transformer card-game reinforcement-learning-algorithms representation-learning language-model game-ai doudizhu reinforcement-learning-agent self-play sequence-modeling q-learning-algorithm doudizhu-ai guandan guandan-ai
-
Updated
May 1, 2026 - Python