Authors
Masato Nagayoshi1, *, Simon J. H. Elderton1, Hisashi Tamaki2
1Department of Nursing, Niigata College of Nursing, 240 Shinnan-cho, Joetsu,
Niigata 943-0147, Japan
2Department of Computer Science and System Engineering, Kobe University,
1-1 Rokkodai-cho, Nada-ku, Kobe, Hyogo 657-8501, Japan
*Corresponding author. Email: [email protected]
Corresponding Author
Masato Nagayoshi
Received 31 October 2019, Accepted 16 December 2019, Available Online 28
February 2020.
DOI
https://doi.org/10.2991/jrnal.k.200222.003
Keywords
Reinforcement learning; multi-agent; negative learning rate; role differentiation
Abstract
There have been many studies on Multi-Agent Reinforcement Learning (MARL)
in which each autonomous agent obtains its own control rule by Reinforcement
Learning (RL). Here, we hypothesize that different agents having individuality
is more effective than uniform agents in terms of role differentiation
in MARL. In this paper, we propose a promoting method of role differentiation
using a wave-form changing parameter in MARL. Then we confirm the effectiveness
of role differentiation by the learning rate that has a periodically negative
value through computational experiments.
Copyright
© 2020 The Authors. Published by ALife Robotics Corp. Ltd.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license
(http://creativecommons.org/licenses/by-nc/4.0/).