Presentation	2002/3/8 On planning of maneuvering motion of a ship based on reinforcement learning Kunihiko MITSUBORI, Takeshi KAMIO,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Recently, reinforcement learning has been attracting attentions of researcher in the fields of artificial intelligence and control theory. This paper discusses the shortest path planning in maneuvering motion of a ship based on reinforcement learning. The maneuvering motion of a ship is described by four dimensional nonlinear equations. Q-Learning algorithm, which is a basic algorithm in reinforcement learning, is applied to this equations with the discretization of their four state variables. The algorithm performance is demonstrated in a simple example.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Ship-maneuvering motion equations / Short path problem / Reinforcement learning / Q-Learning
Paper #	NLP2001-111
Date of Issue

Conference Information
Committee	NLP
Conference Date	2002/3/8(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)	On planning of maneuvering motion of a ship based on reinforcement learning
Sub Title (in English)
Keyword(1)	Ship-maneuvering motion equations
Keyword(2)	Short path problem
Keyword(3)	Reinforcement learning
Keyword(4)	Q-Learning
1st Author's Name	Kunihiko MITSUBORI
1st Author's Affiliation	Japan Coast Guard Academy()
2nd Author's Name	Takeshi KAMIO
2nd Author's Affiliation	Hiroshima City University
Date	2002/3/8
Paper #	NLP2001-111
Volume (vol)	vol.101
Number (no)	723
Page	pp.pp.-
#Pages	8
Date of Issue