2024-03-29T13:11:45Z
https://u-ryukyu.repo.nii.ac.jp/oai
oai:u-ryukyu.repo.nii.ac.jp:02005224
2022-10-31T02:34:04Z
1642837622505:1642837855274:1642837875711
1642838403551:1642838406845
強化学習を用いた共同注視点に基づく合意形成
A consensus making method using focal points with reinforcement learning
亀島, 力
与那覇, 賢
遠藤, 聡志
山田, 孝治
Kameshima, Chikara
Yonaha, Satoru
Endo, Satoshi
Yamada, Koji
open access
Focal-Point
Reinforcement leaning
Profit Sharing
Soccer Server
Focal Point is a method of sharing information without explicit communication between cooperative multi-agents. It is hard for an artificial agent to prescribe the fixed algorithm which decides a focal point without relation 1D the environment. In this paper, we suppose the focal points as a distribution of a situation to induce the behavior of the agent. The autonomous agent can get focal points as a learning of the inside model of itself by the feedback from the environment. Consequently, the mutual agreement of multi-agent is emerged from an unity of the probabilistic choice of fields. Each agent is reinforced the filed potential value respectively by successful task. Finally, focal points can be acquired as potential distribution map of reinforcement value.
紀要論文
琉球大学工学部
1999-09
jpn
departmental bulletin paper
VoR
http://hdl.handle.net/20.500.12000/14729
http://hdl.handle.net/20.500.12000/14729
https://u-ryukyu.repo.nii.ac.jp/records/2005224
0389-102X
AN0025048X
琉球大学工学部紀要
58
121
127
https://u-ryukyu.repo.nii.ac.jp/record/2005224/files/No58p121.pdf