A Multi-agent Reinforcement Learning Method for Role Differentiation Using State Space Filters with Fluctuation Parameters

Journal of Robotics, Networking and Artificial Life (JRNAL)

关键词: Reinforcement learning;    role differentiation;    meta-parameter;    waveform changing;    state space filter;   

DOI  :  10.2991/jrnal.k.210521.002

来源: DOAJ

【 摘 要 】

Recently, there have been many studies on Multi-agent Reinforcement Learning (MARL) in which each autonomous agent obtains its own control rule by RL. Here, we hypothesize that different agents having individuality is more effective than uniform agents in terms of role differentiation in MARL. We have previously proposed a promoting method of role differentiation using a waveform changing parameter in MARL. In this paper, we confirm the effectiveness of role differentiation by introducing the waveform changing parameter into a state space filter through computational examples using “Pursuit Game” as a multi-agent task.

【 授权许可】

Unknown