DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learning

TL;DR

This paper enhances the DouZero AI for DouDizhu by integrating opponent modeling and a coach network, leading to superior performance and top leaderboard ranking among over 400 agents.

Contribution

It introduces opponent modeling and a coach network to improve DouZero's performance and training efficiency in DouDizhu.

Findings

Achieved top ranking on Botzone leaderboard.

Improved performance over original DouZero.

Enhanced training speed and effectiveness.

Abstract

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.