This paper describes a case study about a multi-agent system for cooperative tasks, i.e. a mixing color task given three different sources of color. A reinforcement learning approach was performed by the agents, however, this type of learning exploits exponentially when the number of states in the environment is very large. In that sense, the paper proposes to use the MaxQ-Q hierarchical reinforcement learning algorithm to obtain a suitable policy for agents in order to minimize the time process to achieve the goal, and to reduce the state space. In addition, since the multi-agent system runs in a software application, a multi-threading paradigm was proposed to use. Experimental results show that this multi-agent system can reduce the time process and still maintain independence of agents. © 2015 IEEE. ; Versión del editor ; Producción Científica de la Universidad de Panamericana


    Access

    Download


    Export, share and cite



    Title :

    A case study in hybrid multi-threading and hierarchical reinforcement learning approach for cooperative multi-agent systems


    Contributors:

    Publication date :

    2017-10-24


    Remarks:

    87-93
    Fourteenth Mexican International Conference on Artificial Intelligence : Advances in Artificial Intelligence : MICAI 2015 : proceedings : 25-31 October 2015, Cuernavaca, Morelos, Mexico



    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English , Spanish



    Classification :

    DDC:    629 / 006




    Multi-agent Cooperative Search based on Reinforcement Learning

    Sun, Yinjiang / Zhang, Rui / Liang, Wenbao et al. | IEEE | 2020


    UAV Swarm Cooperative Target Search: A Multi-Agent Reinforcement Learning Approach

    Hou, Yukai / Zhao, Jin / Zhang, Rongqing et al. | IEEE | 2024


    Multi-Agent Reinforcement Learning for Cooperative Vehicle Motion Control

    Ahmic, Kenan / Ultsch, Johannes / Brembeck, Jonathan et al. | IEEE | 2024



    Mitigating Bus Bunching via Hierarchical Multi-Agent Reinforcement Learning

    Yu, Mengdi / Yang, Tao / Li, Chunxiao et al. | IEEE | 2024