Towards a Competitive 3-Player Mahjong AI using Deep Reinforcement Learning
View / Open Files
Conference Name
2022 IEEE Conference on Games
Type
Conference Object
This Version
AM
Metadata
Show full item recordCitation
Zhao, X., & Holden, S. Towards a Competitive 3-Player Mahjong AI using Deep Reinforcement Learning. 2022 IEEE Conference on Games. https://doi.org/10.17863/CAM.86627
Abstract
Mahjong is a multi-player imperfect-information game with challenging features for AI research. Sanma, being a 3-player variant of Japanese Riichi Mahjong, possesses unique characteristics and a more aggressive playing style than the 4- player game. It is thus challenging and of research interest in its own right, but has not been explored. We present Meowjong, the first ever AI for Sanma using deep reinforcement learning (RL). We define a 2-dimensional data structure for encoding the observable information in a game. We pre-train 5 convolutional neural networks (CNNs) for Sanma’s 5 actions—discard, Pon, Kan, Kita and Riichi, and enhance the major (discard) action’s model via self-play reinforcement learning. Meowjong demon- strates potential for becoming the state-of-the-art in Sanma, by achieving test accuracies comparable with AIs for 4-player Mahjong through supervised learning, and gaining a significant further enhancement from reinforcement learning.
Identifiers
External DOI: https://doi.org/10.17863/CAM.86627
This record's URL: https://www.repository.cam.ac.uk/handle/1810/339217
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.