Interpretability for Conditional Coordinated Behavior in Multi-Agent Reinforcement Learning

被引:0
|
作者
Motokawa, Yoshinari [1 ]
Sugawara, Toshiharu [1 ]
机构
[1] Waseda Univ, Dept Comp Sci, Tokyo, Japan
关键词
Multi-agent deep reinforcement learning; XRL; Distributed system; Attentional mechanism; Coordination; Cooperation;
D O I
10.1109/IJCNN54540.2023.10191825
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose a model-free reinforcement learning architecture, called distributed attentional actor architecture after conditional attention (DA6-X), to provide better interpretability of conditional coordinated behaviors. The underlying principle involves reusing the saliency vector, which represents the conditional states of the environment, such as the global position of agents. Hence, agents with DA6-X flexibility built into their policy exhibit superior performance by considering the additional information in the conditional states during the decision-making process. The effectiveness of the proposed method was experimentally evaluated by comparing it with conventional methods in an objects collection game. By visualizing the attention weights from DA6-X, we confirmed that agents successfully learn situation-dependent coordinated behaviors by correctly identifying various conditional states, leading to improved interpretability of agents along with superior performance.
引用
收藏
页数:8
相关论文
共 50 条
  • [1] Analysis of coordinated behavior structures with multi-agent deep reinforcement learning
    Miyashita, Yuki
    Sugawara, Toshiharu
    [J]. APPLIED INTELLIGENCE, 2021, 51 (02) : 1069 - 1085
  • [2] Analysis of coordinated behavior structures with multi-agent deep reinforcement learning
    Yuki Miyashita
    Toshiharu Sugawara
    [J]. Applied Intelligence, 2021, 51 : 1069 - 1085
  • [3] Coordinated Reinforcement Learning Agents in a Multi-Agent Virtual Environment
    Sause, William
    [J]. 2013 12TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2013), VOL 1, 2013, : 227 - 230
  • [4] Coordinated Multi-Agent Reinforcement Learning for Swarm Battery Control
    Ebell, Niklas
    Pruckner, Marco
    [J]. 2018 IEEE CANADIAN CONFERENCE ON ELECTRICAL & COMPUTER ENGINEERING (CCECE), 2018,
  • [5] Learning Distributed Coordinated Policy in Catching Game with Multi-Agent Reinforcement Learning
    Liu, Xiangyu
    Tan, Ying
    [J]. 2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
  • [6] Coordinated Ramp Metering Control Based on Multi-Agent Reinforcement Learning
    Tan, Jiyuan
    Qiu, Qianqian
    Guo, Weiwei
    [J]. 2020 35TH YOUTH ACADEMIC ANNUAL CONFERENCE OF CHINESE ASSOCIATION OF AUTOMATION (YAC), 2020, : 492 - 498
  • [7] Dynamic Arterial Coordinated Control Based on Multi-agent Reinforcement Learning
    Fang, Liangliang
    Zhang, Weibin
    [J]. PROCEEDINGS OF THE 33RD CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2021), 2021, : 2716 - 2721
  • [8] Feudal Latent Space Exploration for Coordinated Multi-Agent Reinforcement Learning
    Liu, Xiangyu
    Tan, Ying
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (10) : 7775 - 7783
  • [9] Multi-Agent Deep Reinforcement Learning for Coordinated Multipoint in Mobile Networks
    Schneider, Stefan
    Karl, Holger
    Khalili, Ramin
    Hecker, Artur
    [J]. IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 2024, 21 (01): : 908 - 924
  • [10] Scalable Multi-Agent Reinforcement Learning for Dynamic Coordinated Multipoint Clustering
    Hu, Fenghe
    Deng, Yansha
    Hamid Aghvami, A.
    [J]. IEEE TRANSACTIONS ON COMMUNICATIONS, 2023, 71 (01) : 101 - 114