ScrofaZero: Mastering Trick-taking Poker Game Gongzhu by Deep Reinforcement Learning

TL;DR

This paper introduces ScrofaZero, a deep reinforcement learning AI that masters the trick-taking game Gongzhu, demonstrating human-level performance and novel techniques for imperfect information games.

Contribution

It presents a neural network-based reinforcement learning approach for Gongzhu, incorporating new methods like stratified sampling and Bayesian inference for imperfect information.

Findings

Achieves human expert level performance in Gongzhu

Introduces novel techniques for imperfect information game AI

Methodology transferable to other trick-taking games

Abstract

People have made remarkable progress in game AIs, especially in domain of perfect information game. However, trick-taking poker game, as a popular form of imperfect information game, has been regarded as a challenge for a long time. Since trick-taking game requires high level of not only reasoning, but also inference to excel, it can be a new milestone for imperfect information game AI. We study Gongzhu, a trick-taking game analogous to, but slightly simpler than contract bridge. Nonetheless, the strategies of Gongzhu are complex enough for both human and computer players. We train a strong Gongzhu AI ScrofaZero from \textit{tabula rasa} by deep reinforcement learning, while few previous efforts on solving trick-taking poker game utilize the representation power of neural networks. Also, we introduce new techniques for imperfect information game including stratified sampling, importance weighting, integral over equivalent class, Bayesian inference, etc. Our AI can achieve human expert level performance. The methodologies in building our program can be easily transferred into a wide range of trick-taking games.