Summary
International Symposium on Nonlinear Theory and its Applications
2017
Session Number:B2L-B
Session:
Number:B2L-B-5
Influence of Reference Courses on Reinforcement Learning to Search Ships' Courses
Takeshi Kamio, Takahiro Tanaka, Kunihiko Mitsubori, Hisato Fujisaka,
pp.490-493
Publication Date:2017/12/4
Online ISSN:2188-5079
DOI:10.34385/proc.29.B2L-B-5
PDF download (174KB)
Summary:
Deciding efficient and safe courses of ships before actual navigation is very important. We have developed multi-agent reinforcement learning system (MARLS) to search ships' Ecourses as a useful tool to discuss the optimality of courses and the interaction between maneuvering actions. In this paper, we design a novel MARLS to search ships' courses based on the reference courses. Also, we evaluate the influence of the reference courses on MARLS through the numerical simulations.