arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.12847cs.AIcs.LG
收藏

使用深度强化学习构建3人麻将AI

Building a 3-Player Mahjong AI using Deep Reinforcement Learning

University of Cambridge(剑桥大学)

Xiangyu Zhao, Sean B. Holden

摘要:

麻将是19世纪末在中国开发的一种流行的多人信息游戏,具有一些对人工智能研究非常具有挑战性的特征。Sanma是日本Riichi麻将的3人版本,具有独特的特点,包括较少的瓷砖,因此,更具侵略性的游戏风格。因此,它本身具有挑战性和巨大的研究兴趣,但尚未进行探索。在本文中,我们介绍了Meowjong,一个使用深度强化学习的Sanma AI。我们定义了一个信息丰富和紧凑的2维数据结构编码的可观察的信息在一个三马游戏。我们为Sanma的5个动作--丢弃、Pon、Kan、Kita和Riichi预训练了5个卷积神经网络(CNN),并使用Monte Carlo策略梯度方法通过自我强化学习增强了主要动作的模型,即丢弃模型。Meowjong的模型通过监督学习实现了与4人麻将AI相当的测试精度,并从强化学习中获得了显着的进一步增强。作为Sanma的第一个AI,我们声称Meowjong在这个游戏中是最先进的。

英文摘要:

Mahjong is a popular multi-player imperfect-information game developed in China in the late 19th-century, with some very challenging features for AI research. Sanma, being a 3-player variant of the Japanese Riichi Mahjong, possesses unique characteristics including fewer tiles and, consequently, a more aggressive playing style. It is thus challenging and of great research interest in its own right, but has not yet been explored. In this paper, we present Meowjong, an AI for Sanma using deep reinforcement learning. We define an informative and compact 2-dimensional data structure for encoding the observable information in a Sanma game. We pre-train 5 convolutional neural networks (CNNs) for Sanma's 5 actions -- discard, Pon, Kan, Kita and Riichi, and enhance the major action's model, namely the discard model, via self-play reinforcement learning using the Monte Carlo policy gradient method. Meowjong's models achieve test accuracies comparable with AIs for 4-player Mahjong through supervised learning, and gain a significant further enhancement from reinforcement learning. Being the first ever AI in Sanma, we claim that Meowjong stands as a state-of-the-art in this game.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑