Conference item icon

Conference item

OFFER: Off-environment reinforcement learning

Abstract:

Policy gradient methods have been widely applied in reinforcement learning. For reasons of safety and cost, learning is often conducted using a simulator. However, learning in simulation does not traditionally utilise the opportunity to improve learning by adjusting certain environment variables - state features that are randomly determined by the environment in a physical setting but controllable in a simulator. Exploiting environment variables is crucial in domains containing significant ra...

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

Actions


Access Document


Files:

Authors


More by this author
Department:
Oxford,MPLS,Computer Science
More by this author
Department:
St Catherines College
Publisher:
AAAI Press Publisher's website
Pages:
1819–1825
Publication date:
2017
Acceptance date:
2016-11-01
ISSN:
2159-5399
Pubs id:
pubs:661786
URN:
uri:4c5b4f56-bc4d-4617-931c-7487e4c7bd94
UUID:
uuid:4c5b4f56-bc4d-4617-931c-7487e4c7bd94
Local pid:
pubs:661786

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