Presentation 2010-03-09
Finding Course of Ships by Multi-Agent Reinforcement Learning with A Priori Knowledge
Takeshi KAMIO, Kunihiko MITSUBORI, Takahiro TANAKA, Chang-Jun AHN, Hisato FUJISAKA, Kazuhisa HAEIWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Ships are systems defined by nonlinear dynamics and the control tower does not exist. Therefore, if plural ships are in the restricted sea area, the appropriate course decision of ships before the actual navigation is an important problem. In this research, we have designed a novel multi-agent reinforcement learning systems (MARLS) for the course decision of ships to keep the navigation rules forcibly and to improve the learning efficiency.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Course decision of ships / Navigation rules / Reinforcement learning / Multi-agent system / A priori knowledge
Paper # NLP2009-161
Date of Issue

Conference Information
Committee NLP
Conference Date 2010/3/2(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Finding Course of Ships by Multi-Agent Reinforcement Learning with A Priori Knowledge
Sub Title (in English)
Keyword(1) Course decision of ships
Keyword(2) Navigation rules
Keyword(3) Reinforcement learning
Keyword(4) Multi-agent system
Keyword(5) A priori knowledge
1st Author's Name Takeshi KAMIO
1st Author's Affiliation Hiroshima City University()
2nd Author's Name Kunihiko MITSUBORI
2nd Author's Affiliation Takusyoku University
3rd Author's Name Takahiro TANAKA
3rd Author's Affiliation Japan Coast Guard Academy
4th Author's Name Chang-Jun AHN
4th Author's Affiliation Hiroshima City University
5th Author's Name Hisato FUJISAKA
5th Author's Affiliation Hiroshima City University
6th Author's Name Kazuhisa HAEIWA
6th Author's Affiliation Hiroshima City University
Date 2010-03-09
Paper # NLP2009-161
Volume (vol) vol.109
Number (no) 458
Page pp.pp.-
#Pages 6
Date of Issue