Cooperative Action Acquisition Based on Intention Estimation in a Multi-Agent Reinforcement Learning System

被引:1
|
作者
Tsubakimoto, Tatsuya [1 ]
Kobayashi, Kunikazu [1 ]
机构
[1] Aichi Prefectural Univ, Sch Informat Sci & Technol, Nagakute, Aichi, Japan
关键词
multi-agent; reinforcement learning; Q-learning; cooperation; intention estimation;
D O I
10.1002/ecj.11821
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In this paper, we propose a method to acquire a series of cooperative actions to reach an appropriate goal without the designer controlling the reward. To accomplish this, we introduce a new concept of "reward interpretation." This is the idea that an agent can increase or decrease the reward given by the environment through the reward interpretation on its won. We applied this idea to the Q-learning method. The simulation results show that the proposed method is superior to a standard Q-learning method and a Q-learning method with cooperation in terms of the number of successful instances of cooperation. (C) 2017 Wiley Periodicals, Inc.
引用
收藏
页码:3 / 10
页数:8
相关论文
共 50 条
  • [31] A review of cooperative multi-agent deep reinforcement learning
    Oroojlooy, Afshin
    Hajinezhad, Davood
    APPLIED INTELLIGENCE, 2023, 53 (11) : 13677 - 13722
  • [32] Training Cooperative Agents for Multi-Agent Reinforcement Learning
    Bhalla, Sushrut
    Subramanian, Sriram G.
    Crowley, Mark
    AAMAS '19: PROCEEDINGS OF THE 18TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS, 2019, : 1826 - 1828
  • [33] Fast conflict resolution based on reinforcement learning in multi-agent system
    Piao, SH
    Hong, BR
    Chu, HT
    CHINESE JOURNAL OF ELECTRONICS, 2004, 13 (01): : 92 - 95
  • [34] Swarm Reinforcement Learning for traffic signal control based on cooperative multi-agent framework
    Tahifa, Mohammed
    Boumhidi, Jaouad
    Yahyaouy, Ali
    2015 INTELLIGENT SYSTEMS AND COMPUTER VISION (ISCV), 2015,
  • [35] LJIR: Learning Joint-Action Intrinsic Reward in cooperative multi-agent reinforcement learning
    Chen, Zihan
    Luo, Biao
    Hu, Tianmeng
    Xu, Xiaodong
    NEURAL NETWORKS, 2023, 167 : 450 - 459
  • [36] Sharing of Energy Among Cooperative Households Using Distributed Multi-Agent Reinforcement Learning
    Ebell, Niklas
    Guetlein, Moritz
    Pruckner, Marco
    PROCEEDINGS OF 2019 IEEE PES INNOVATIVE SMART GRID TECHNOLOGIES EUROPE (ISGT-EUROPE), 2019,
  • [37] Reinforcement Learning for Multi-Agent Competitive Scenarios
    Coutinho, Manuel
    Reis, Luis Paulo
    2022 IEEE INTERNATIONAL CONFERENCE ON AUTONOMOUS ROBOT SYSTEMS AND COMPETITIONS (ICARSC), 2022, : 130 - 135
  • [38] Multi-agent reinforcement learning based on local communication
    Zhang, Wenxu
    Ma, Lei
    Li, Xiaonan
    CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2019, 22 (Suppl 6): : 15357 - 15366
  • [39] Multi-agent reinforcement learning based on local communication
    Wenxu Zhang
    Lei Ma
    Xiaonan Li
    Cluster Computing, 2019, 22 : 15357 - 15366
  • [40] Survey of Multi-Agent Strategy Based on Reinforcement Learning
    Chen, Liang
    Guo, Ting
    Liu, Yun-ting
    Yang, Jia-ming
    PROCEEDINGS OF THE 32ND 2020 CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2020), 2020, : 604 - 609