Bloody Mahjong playing strategy based on the integration of deep learning and XGBoost  

作　　者：Shijing Gao Shuqin Li 

机构地区：[1]School of Computer,Beijing Information Science and Technology University,Beijing,China [2]Sensing&Computational Intelligence Joint Lab,Beijing Information Science&Technology University,Beijing,China

出　　处：《CAAI Transactions on Intelligence Technology》2022年第1期95-106,共12页智能技术学报（英文）

基　　金：Promoting Research Level Program,Beijing Information Science and Technology University,Grant/Award Number:5211910927;General Science and Technology Research program,Grant/Award Number:KM201911232002;Graduated Education Program at Beijing Information Science and Technology University。

摘　　要：Bloody Mahjong is a kind of mahjong.It is very popular in China in recent years.It not only has the characteristics of mahjong's conventional state space,huge hidden information,complicated rules,and large randomness of hand cards but also has special rules such as Change three,Hu must lack at least one suit,and Continue playing after Hu.These rules increase the difficulty of research.These special rules are used as the input of the deep learning DenseNet model.DenseNet is used to extract the Mahjong situation features.The learned features are used as the input of the classification algorithm XGBoost,and then the XGBoost algorithm is used to derive the card strategy.Experiments show that the fusion model of deep learning and XGBoost proposed in this paper has higher accuracy than the single model using only one of them in the case of highdimensional sparse features.In the case of fewer training rounds,accuracy of the model can still reach 83%.In the games against real people,it plays like human.

关 键 词：BLOOD learning INTEGRATION 

分 类 号：H31[语言文字—英语]