HOME    About this site    mypage    Japanese    library    university    Feedback

University of the Ryukyus Repository >
Faculty of Engineering >
Bulletin >
Bulletin of the Faculty of Engineering, University of the Ryukyus >
No. 58 (1999/09) >

Title :強化学習を用いた共同注視点に基づく合意形成
Title alternative :A consensus making method using focal points with reinforcement learning
Authors :亀島, 力
与那覇, 賢
遠藤, 聡志
山田, 孝治
Authors alternative :Kameshima, Chikara
Yonaha, Satoru
Endo, Satoshi
Yamada, Koji
Issue Date :Sep-1999
Abstract :"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.
Type Local :紀要論文
ISSN :0389-102X
Publisher :琉球大学工学部
URI :http://hdl.handle.net/20.500.12000/14729
Citation :琉球大学工学部紀要 no.58 p.121 -127
Appears in Collections:No. 58 (1999/09)

Files in This Item:

File Description SizeFormat
No58p121.pdf901KbAdobe PDFView/Open