Yudong Lu, Jian Zhao, Youpeng Zhao, Wengang Zhou, Houqiang Li
TL;DR本文介绍了一种基于加强学习技术的 AI 程序 DanZero,使用分布式框架训练其在类似于斗地主但更复杂的关打游戏中的表现,表现出出色的性能。
Abstract
card game ai has always been a hot topic in the research of artificial
intelligence. In recent years, complex card games such as Mahjong, DouDizhu and
Texas Hold'em have been solved and the corresponding AI programs have reached
the level of human experts. In this paper, we are devoted