PerfectDou: Dominating DouDizhu with Perfect Information Distillation

Guan Yang, Minghuan Liu, Weijun Hong, Weinan Zhang, Fei Fang, Guangjun Zeng, Yue Lin

Keywords: reinforcement learning, poker games, card games, game AI

TL;DR: We propose PerfectDou, a SoTA DouDizhu AI system that dominates the game.

Abstract:

As a challenging multi-player card game, DouDizhu has recently drawn much attention for analyzing competition and collaboration in imperfect-information games. In this paper, we propose PerfectDou, a state-of-the-art Doudizhu AI system that summits the game, in an actor-critic framework with a proposed technique named perfect information distillation.
In detail, we adopt a perfect-training-imperfection-execution framework that allows the agents to utilize the global information to guide the training of the policies as if it is a perfect information game and the trained policies can be used to play the imperfect information game during the actual gameplay. Correspondingly, we characterize card and game features for DouDizhu to represent the perfect and imperfect information. To train our system, we adopt proximal policy optimization with generalized advantage estimation in a parallel training paradigm. In experiments we show how and why PerfectDou beats all existing programs, and achieves state-of-the-art performance.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2203.16406/code)