2024-03-28T12:20:38Z
https://u-ryukyu.repo.nii.ac.jp/oai
oai:u-ryukyu.repo.nii.ac.jp:02005222
2022-10-31T02:33:57Z
1642837622505:1642837855274:1642837875711
1642838403551:1642838406845
マルチエージェント系における競合共進化型学習の性能評価
The performance evaluation of competitive co-evolution in multi-agent system.
玉城, 清政
玉城, 斉
山田, 孝治
遠藤, 聡志
Tamashiro, Kiyomasa
Tamaki, Tadashi
Yamada, Koji
Endo, Satoshi
Reinforcement learning
Genetic algorithm
competitive co-evolution
One of the important issues in intelligent systems and robotics is to develop an efficient method to control multi-agent system. In order to work multi-agent system well as problem solver, it's so significant to create cooperative behaviors among the agents. In the multi-agent system, the behaviors of cooperation emerged as the results of suitable role learning by each agent. In this paper, we evaluate reinforcement learning, genetic algorithm and competitive co-evolution algorithm from the viewpoint of adaptability to different environment as the learning method of multi-agent system, and discuss the property of each technique.
紀要論文
http://purl.org/coar/resource_type/c_6501
琉球大学工学部
1999-09
VoR
http://hdl.handle.net/20.500.12000/14710
0389-102X
AN0025048X
琉球大学工学部紀要
58
149
143
jpn
open access