Training a popular Mahjong agent with CNN and self-attention

被引：0
|
作者：
Liu, Liu [1 ]
Zhang, XiaoChuan [1 ]
He, ZeYa [1 ]
Liu, Jie [1 ]
机构：
[1] Chongqing Univ Technol, Sch Artificial Intelligence, Chongqing 401120, Peoples R China
来源：
INTERNATIONAL JOURNAL OF COMPUTING SCIENCE AND MATHEMATICS | 2024年 / 19卷 / 02期
关键词：
popular Mahjong; deep convolution network; self-attention mechanism; LSTM; long short term memory;
D O I：
10.1504/IJCSM.2024.137266
中图分类号：
T [工业技术];
学科分类号：
08 ;
摘要：
Popular Mahjong is a variety of Chinese Mahjong that is characterised by having a high likelihood of Chow and Pong. To search for the hidden information in the Popular Mahjong time series decision-making data and arrive at reasonable Discard, Chow and Pong decisions. In this paper, a hybrid decision model that combines convolutional neural network, long short term memory and self-attention mechanism is proposed. A Mahjong agent JongMaster is created in this essay. Five kinds of action models are created by fusing the aforementioned hybrid model with real-world knowledge: Discard, Chow, Pong,Kong, and Riichi. These models work together to create the JongMaster's decision-making process. Lastly, JongMaster and the three benchmark agents conducted 1000 rounds of combat tests on the professional test platform. JongMaster increased the Hu rate and the highest score of a single round by 10.5% and 9 points, respectively, and decreased the shooting rate by 5.12%.
引用
收藏
页码：157 / 166
页数：11
相关论文
共 50 条
  • [1] Self-attention CNN for retinal layer segmentation in OCT
    Cao, Guogang
    Wu, Yan
    Peng, Zeyu
    Zhou, Zhilin
    Dai, Cuixia
    [J]. BIOMEDICAL OPTICS EXPRESS, 2024, 15 (03) : 1605 - 1617
  • [2] Event detection by combining self-attention and CNN-BiGRU
    Wang K.
    Wang M.
    Liu X.
    Tian G.
    Li C.
    Liu W.
    [J]. Xi'an Dianzi Keji Daxue Xuebao/Journal of Xidian University, 2022, 49 (05): : 181 - 188
  • [3] Grasp Detection Combining Self-Attention with CNN in Complex Scenes
    Niu, Jinxing
    Liu, Shuo
    Li, Hanbing
    Zhang, Tao
    Wang, Lijun
    [J]. APPLIED SCIENCES-BASEL, 2023, 13 (17):
  • [4] Split-Attention CNN and Self-Attention with RoPE and GCN for Voice Activity Detection
    Tan, Yingwei
    Ding, Xuefeng
    [J]. IEEE Access, 2024, 12 : 156673 - 156682
  • [5] CNN-TRANSFORMER WITH SELF-ATTENTION NETWORK FOR SOUND EVENT DETECTION
    Wakayama, Keigo
    Saito, Shoichiro
    [J]. 2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 806 - 810
  • [6] Dense CNN With Self-Attention for Time-Domain Speech Enhancement
    Pandey, Ashutosh
    Wang, DeLiang
    [J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 29 (29) : 1270 - 1279
  • [7] SAT: Self-Attention Control for Diffusion Models Training
    Huang, Jing
    Zhang, Tianyi
    Shi, Wei
    [J]. PROCEEDINGS OF THE 1ST WORKSHOP ON LARGE GENERATIVE MODELS MEET MULTIMODAL APPLICATIONS, LGM3A 2023, 2023, : 15 - 22
  • [8] Efficient Lightweight Speaker Verification with Broadcasting CNN-Transformer and Knowledge Distillation Training of Self-Attention Maps
    Choi, Jeong-Hwan
    Yang, Joon-Young
    Chang, Joon-Hyuk
    [J]. IEEE/ACM Transactions on Audio Speech and Language Processing, 2024, 32 : 4580 - 4595
  • [9] Personalized News Recommendation with CNN and Multi-Head Self-Attention
    Li, Aibin
    He, Tingnian
    Guo, Yi
    Li, Zhuoran
    Rong, Yixuan
    Liu, Guoqi
    [J]. 2022 IEEE 13TH ANNUAL UBIQUITOUS COMPUTING, ELECTRONICS & MOBILE COMMUNICATION CONFERENCE (UEMCON), 2022, : 102 - 108
  • [10] Scene classification for remote sensing images with self-attention augmented CNN
    Liu, Zongyin
    Dong, Anming
    Yu, Jiguo
    Han, Yubing
    Zhou, You
    Zhao, Kai
    [J]. IET IMAGE PROCESSING, 2022, 16 (11) : 3085 - 3096
12345