DeltaDou: Expert-level Doudizhu AI through Self-play

Artificial Intelligence has seen several breakthroughs in two-player perfect information game. Nevertheless, Doudizhu, a three-player imperfect information game, is still quite challenging. In this paper, we present a Doudizhu AI by applying deep reinforcement learning from games of self-play. The algorithm combines an asymmetric MCTS on nodes of information set of each player, a policy-value network that approximates the policy and value on each decision node, and inference on unobserved hands of other players by given policy. Our results show that self-play can significantly improve the performance of our agent in this multi-agent imperfect information game. Even starting with a weak AI, our agent can achieve human expert level after days of self-play and training.