Multi-Agent Game Abstraction via Graph Attention Neural Network

被引:0
|
作者
Liu, Yong [1 ]
Wang, Weixun [2 ]
Hu, Yujing [3 ]
Hao, Jianye [2 ,4 ]
Chen, Xingguo [5 ]
Gao, Yang [1 ]
机构
[1] Nanjing Univ, Natl Key Lab Novel Software Technol, Nanjing, Peoples R China
[2] Tianjin Univ, Tianjin, Peoples R China
[3] NetEase Fuxi AI Lab, Beijing, Peoples R China
[4] Huawei, Noahs Ark Lab, Shenzhen, Peoples R China
[5] Nanjing Univ Posts & Telecommun, Jiangsu Key Lab Big Data Secur & Intelligent Proc, Nanjing, Peoples R China
基金
中国国家自然科学基金;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In large-scale multi-agent systems, the large number of agents and complex game relationship cause great difficulty for policy learning. Therefore, simplifying the learning process is an important research issue. In many multi-agent systems, the interactions between agents often happen locally, which means that agents neither need to coordinate with all other agents nor need to coordinate with others all the time. Traditional methods attempt to use pre-defined rules to capture the interaction relationship between agents. However, the methods cannot be directly used in a large-scale environment due to the difficulty of transforming the complex interactions between agents into rules. In this paper, we model the relationship between agents by a complete graph and propose a novel game abstraction mechanism based on two-stage attention network (G2ANet), which can indicate whether there is an interaction between two agents and the importance of the interaction. We integrate this detection mechanism into graph neural network-based multi-agent reinforcement learning for conducting game abstraction and propose two novel learning algorithms GA-Comm and GA-AC. We conduct experiments in Traffic Junction and Predator-Prey. The results indicate that the proposed methods can simplify the learning process and meanwhile get better asymptotic performance compared with state-of-the-art algorithms.
引用
收藏
页码:7211 / 7218
页数:8
相关论文
共 50 条
  • [1] Multi-Agent Trajectory Prediction with Graph Attention Isomorphism Neural Network
    Liu, Yongkang
    Qi, Xuewei
    Sisbot, Emrah Akin
    Oguchi, Kentaro
    [J]. 2022 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), 2022, : 273 - 279
  • [2] Multi-Agent Actor-Critic with Hierarchical Graph Attention Network
    Ryu, Heechang
    Shin, Hayong
    Park, Jinkyoo
    [J]. THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 7236 - 7243
  • [3] Multi-Agent Transformer Networks With Graph Attention
    Jin, Woobeen
    Lee, Hyukjoon
    [J]. IEEE Access, 2024, 12 : 144982 - 144991
  • [4] MAGNet: Multi-agent Graph Network for Deep Multi-agent Reinforcement Learning
    Malysheva, Aleksandra
    Kudenko, Daniel
    Shpilman, Aleksei
    [J]. 2019 XVI INTERNATIONAL SYMPOSIUM PROBLEMS OF REDUNDANCY IN INFORMATION AND CONTROL SYSTEMS (REDUNDANCY), 2019, : 171 - 176
  • [5] Distributed Formation Control of Multi-Agent via Abstraction
    Li, Huanhuan
    Liu, Tengfei
    Jiang, Zhong-Ping
    [J]. 2021 PROCEEDINGS OF THE 40TH CHINESE CONTROL CONFERENCE (CCC), 2021, : 5598 - 5603
  • [6] GRAPHCOMM: A GRAPH NEURAL NETWORK BASED METHOD FOR MULTI-AGENT REINFORCEMENT LEARNING
    Shen, Siqi
    Fu, Yongquan
    Su, Huayou
    Pan, Hengyue
    Qiao, Peng
    Dou, Yong
    Wang, Cheng
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 3510 - 3514
  • [7] Multi-Agent Trajectory Prediction With Heterogeneous Edge-Enhanced Graph Attention Network
    Mo, Xiaoyu
    Huang, Zhiyu
    Xing, Yang
    Lv, Chen
    [J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (07) : 9554 - 9567
  • [8] Multi-Agent Task Allocation with Multiple Depots Using Graph Attention Pointer Network
    Shi, Wen
    Yu, Chengpu
    [J]. ELECTRONICS, 2023, 12 (16)
  • [9] MAKE:Knowledge Graph Embedding via Multi-Attention neural network
    Liu, Denghui
    Wang, Yanna
    Zhou, Zili
    Dong, Zhaoan
    [J]. 2022 5TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND NATURAL LANGUAGE PROCESSING, MLNLP 2022, 2022, : 347 - 352
  • [10] A Soft Graph Attention Reinforcement Learning for Multi-Agent Cooperation
    Wang, Huimu
    Pu, Zhiqiang
    Liu, Zhen
    Yi, Jianqiang
    Qiu, Tenghai
    [J]. 2020 IEEE 16TH INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING (CASE), 2020, : 1257 - 1262