Conference icon

Conference

Inverse reinforcement learning from failure

Abstract:
Inverse reinforcement learning (IRL) allows autonomous agents to learn to solve complex tasks from successful demonstrations. However, in many settings, e.g., when a human learns the task by trial and error, failed demonstrations are also readily available. In addition, in some tasks, purposely generating failed demonstrations may be easier than generating successful ones. Since existing IRL methods cannot make use of failed demonstrations, in this paper we propose inver... Expand abstract
Publication status:
Accepted
Peer review status:
Peer reviewed
Version:
Accepted Manuscript

Actions


Access Document


Files:

Authors


Shiarlis, K More by this author
Messias, J More by this author
More by this author
Institution:
University of Oxford
Department:
Oxford, MPLS, Computer Science
Publisher:
International Foundation for Autonomous Agents and Multiagent Systems Publisher's website
Pages:
1060-1068
Publication date:
2016
URN:
uuid:8593deb6-f16c-4545-a732-472625eaffb3
Source identifiers:
606793
Local pid:
pubs:606793
ISBN:
978-1-4503-4239-1

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