Rapidly exploring learning trees

Inverse Reinforcement Learning (IRL) for path planning enables robots to learn cost functions for difficult tasks from demonstration, instead of hard-coding them. However, IRL methods face practical limitations that stem from the need to repeat costly planning procedures. In this paper, we propose R...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй
Үндсэн зохиолчид: Shiarlis, K, Messias, J, Whiteson, S
Формат: Conference item
Хэвлэсэн: IEEE 2017