Jinqiu Li, Shuang Wu, Haobo Fu, Qiang Fu, Enmin Zhao, Junliang Xing. Speedup Training Artificial Intelligence for Mahjong via Reward Variance Reduction. In IEEE Conference on Games, CoG 2022, Beijing, China, August 21-24, 2022. pages 345-352, IEEE, 2022. [doi]
Abstract is missing.