Multi-agent Coordination using Reinforcement Learning with a Relay Agent

被引：1
|
作者：
Zemzem, Wiem [1 ]
Tagina, Moncef [1 ]
机构：
[1] Univ Manouba, Natl Sch Comp Sci, COSMOS Lab, Tunis, Tunisia
来源：
ICEIS: PROCEEDINGS OF THE 19TH INTERNATIONAL CONFERENCE ON ENTERPRISE INFORMATION SYSTEMS - VOL 1 | 2017年
关键词：
Distributed Reinforcement Learning; A Cooperative Action Selection Strategy; A Relay Agent; Unknown and Stationary Environments;
D O I：
10.5220/0006327305370545
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper focuses on distributed reinforcement learning in cooperative multi-agent systems, where several simultaneously and independently acting agents have to perform a common foraging task. To do that, a novel cooperative action selection strategy and a new kind of agents, called "relay agent", are proposed. The conducted simulation tests indicate that our proposals improve coordination between learners and are extremely efficient in terms of cooperation in large, unknown and stationary environments.
引用
收藏
页码：537 / 545
页数：9
相关论文
共 50 条
  • [1] Coordination as inference in multi-agent reinforcement learning
    Li, Zhiyuan
    Wu, Lijun
    Su, Kaile
    Wu, Wei
    Jing, Yulin
    Wu, Tong
    Duan, Weiwei
    Yue, Xiaofeng
    Tong, Xiyi
    Han, Yizhou
    [J]. NEURAL NETWORKS, 2024, 172
  • [2] Agent Coordination in Air Combat Simulation using Multi-Agent Deep Reinforcement Learning
    Kallstrom, Johan
    Heintz, Fredrik
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2020, : 2157 - 2164
  • [3] Distributed Coordination Guidance in Multi-Agent Reinforcement Learning
    Lau, Qiangfeng Peter
    Lee, Mong Li
    Hsu, Wynne
    [J]. 2011 23RD IEEE INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2011), 2011, : 456 - 463
  • [4] Evaluating the Coordination of Agents in Multi-agent Reinforcement Learning
    Barton, Sean L.
    Zaroukian, Erin
    Asher, Derrik E.
    Waytowich, Nicholas R.
    [J]. INTELLIGENT HUMAN SYSTEMS INTEGRATION 2019, 2019, 903 : 765 - 770
  • [5] Improving coordination with communication in multi-agent reinforcement learning
    Szer, D
    Charpillet, F
    [J]. ICTAI 2004: 16TH IEEE INTERNATIONALCONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2004, : 436 - 440
  • [6] Reinforcement learning of coordination in cooperative multi-agent systems
    Kapetanakis, S
    Kudenko, D
    [J]. EIGHTEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE (AAAI-02)/FOURTEENTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE (IAAI-02), PROCEEDINGS, 2002, : 326 - 331
  • [7] A coordination model using fuzzy reinforcement learning for multi-agent system
    Peng, Jun
    Liu, Miao
    Liu, Jianfeng
    Lin, Kuo-Chi
    Wu, Min
    [J]. CTS 2007: PROCEEDINGS OF THE 2007 INTERNATIONAL SYMPOSIUM ON COLLABORATIVE TECHNOLOGIES AND SYSTEMS, 2007, : 129 - +
  • [8] Learning coordination in multi-agent systems using influence value reinforcement learning
    Barrios-Aranibar, Dennis
    Garcia Goncalves, Luiz Marcos
    [J]. PROCEEDINGS OF THE 7TH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS DESIGN AND APPLICATIONS, 2007, : 471 - 476
  • [9] Multi-Agent Reinforcement Learning
    Stankovic, Milos
    [J]. 2016 13TH SYMPOSIUM ON NEURAL NETWORKS AND APPLICATIONS (NEUREL), 2016, : 43 - 43
  • [10] Reinforcement learning approaches to coordination in cooperative multi-agent systems
    Kapetanakis, S
    Kudenko, D
    Strens, MJA
    [J]. ADAPTIVE AGENTS AND MULTI-AGENT SYSTEMS: ADAPTATION AND MULTI-AGENT LEARNING, 2003, 2636 : 18 - 32
12345