Presentation 2013-03-14
Improvement of Limited Action Selection in Reinforcement Learning Based Search Method for Ships' Courses
Tomohiro TANIGAWA, Takeshi KAMIO, Kunihiko MITSUBORI, Takahiro TANAKA, Hisato FUJISAKA, Kazuhisa HAEIWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Ship transport is important. Multi ship course problem has been treared in the engineering related to ships. But the optimality of courses and the interaction between maneuvering actions have not been sufficiently discussed yet. So we have been designed multi-agent reinforcement learning system (MARLS). However, we have been confirmed by computer simulations that the resulting route is to avoid unnecessary. In this paper, we propose a limited action selection that correct to avoid unnecessary.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) multi-agent reinforcement learning system / multi-ship course problem / prior knowledge / navigation rules
Paper # NLP2012-144
Date of Issue

Conference Information
Committee NLP
Conference Date 2013/3/7(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) Improvement of Limited Action Selection in Reinforcement Learning Based Search Method for Ships' Courses
Sub Title (in English)
Keyword(1) multi-agent reinforcement learning system
Keyword(2) multi-ship course problem
Keyword(3) prior knowledge
Keyword(4) navigation rules
1st Author's Name Tomohiro TANIGAWA
1st Author's Affiliation Graduate School of Information Sciences, Hiroshima City University()
2nd Author's Name Takeshi KAMIO
2nd Author's Affiliation Graduate School of Information Sciences, Hiroshima City University
3rd Author's Name Kunihiko MITSUBORI
3rd Author's Affiliation Faculty of Engineering, Takushoku University
4th Author's Name Takahiro TANAKA
4th Author's Affiliation Japan Coast Guard Academy
5th Author's Name Hisato FUJISAKA
5th Author's Affiliation Graduate School of Information Sciences, Hiroshima City University
6th Author's Name Kazuhisa HAEIWA
6th Author's Affiliation Graduate School of Information Sciences, Hiroshima City University
Date 2013-03-14
Paper # NLP2012-144
Volume (vol) vol.112
Number (no) 487
Page pp.pp.-
#Pages 5
Date of Issue