Conference item icon

Conference item

Learning with training wheels: Speeding up training with a simple controller for deep reinforcement learning

Abstract:

Deep Reinforcement Learning (DRL) has been applied successfully to many robotic applications. However, the large number of trials needed for training is a key issue. Most of existing techniques developed to improve training efficiency (e.g. imitation) target on general tasks rather than being tailored for robot applications, which have their specific context to benefit from. We propose a novel framework, Assisted Reinforcement Learning, where a classical controller (e.g. a PID controller) is ...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1109/ICRA.2018.8461203

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Computer Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Oxford college:
Kellogg College
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Computer Science
Role:
Author
More from this funder
Name:
Engineering and Physical Sciences Research Council
Grant:
EP/M019918/1
Publisher:
IEEE
Host title:
2018 IEEE International Conference on Robotics and Automation (ICRA)
Journal:
IEEE International Conference on Robotics and Automation (ICRA 2018) More from this journal
Pages:
6276-6283
Publication date:
2018-09-13
Acceptance date:
2018-01-08
DOI:
ISSN:
2577-087X
ISBN:
9781538630815
Pubs id:
pubs:827800
UUID:
uuid:f8fad305-6a85-4512-b8b5-4eb39bd15d26
Local pid:
pubs:827800
Source identifiers:
827800
Deposit date:
2018-03-05

Terms of use


Views and Downloads






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

TO TOP