DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learning
This work addresses the challenge of developing more effective AI for DouDizhu, a complex imperfect-information card game, representing an incremental improvement over prior methods.
The paper tackled improving the DouDizhu AI system DouZero by integrating opponent modeling and a coach network, resulting in enhanced performance that ranks top on the Botzone leaderboard among over 400 AI agents, including DouZero.
Recent years have witnessed the great breakthrough of deep reinforcement learning (DRL) in various perfect and imperfect information games. Among these games, DouDizhu, a popular card game in China, is very challenging due to the imperfect information, large state space, elements of collaboration and a massive number of possible moves from turn to turn. Recently, a DouDizhu AI system called DouZero has been proposed. Trained using traditional Monte Carlo method with deep neural networks and self-play procedure without the abstraction of human prior knowledge, DouZero has outperformed all the existing DouDizhu AI programs. In this work, we propose to enhance DouZero by introducing opponent modeling into DouZero. Besides, we propose a novel coach network to further boost the performance of DouZero and accelerate its training process. With the integration of the above two techniques into DouZero, our DouDizhu AI system achieves better performance and ranks top in the Botzone leaderboard among more than 400 AI agents, including DouZero.