[A-10] システム数理と応用

2:15 PM - 2:30 PM JST(5:15 AM - 5:30 AM UTC)

[A-10-03] Multi-Ship Course Search Method with Target Courses as Actions Introducing Variable Safety Margins

○Ryo Teraguchi¹, Takeshi Kamio¹, Mikito Tanaka¹, Ibuki Nakamura² (1. Hiroshima City University, 2. National Institute of Technology, Matsue College)

Keywords:

Reinforcement Learning,Multi-Ship Course Search,Target Course,Bumper Model,Safety Margins