Conference item icon

Conference item

Rapidly exploring learning trees

Abstract:

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 Rapidly Exploring Learning Trees (RLT∗ ), which learns the cost functions of Optimal Rapidly Exploring Random Trees (RRT∗ ) from demonstration, thereby making inverse learning methods applicable to ...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted Manuscript

Actions


Access Document


Files:
Publisher copy:
10.1109/ICRA.2017.7989184

Authors


Shiarlis, K More by this author
Messias, J More by this author
More by this author
Department:
St Catherines College
Publisher:
IEEE Publisher's website
Pages:
1541-1548
Publication date:
2017-07-24
Acceptance date:
2017-01-15
DOI:
Pubs id:
pubs:673190
URN:
uri:a90c2aa7-1821-40f2-b1fb-5b1cc15493c3
UUID:
uuid:a90c2aa7-1821-40f2-b1fb-5b1cc15493c3
Local pid:
pubs:673190
ISBN:
978-1-5090-4634-8

Terms of use


Metrics



If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP