Conference item icon

Conference item

Distral: robust multitask reinforcement learning

Abstract:

Neural information processing systems foundation. All rights reserved. Most deep reinforcement learning algorithms are data inefficient in complex and rich environments, limiting their applicability to many scenarios. One direction for improving data efficiency is multitask learning with shared neural network parameters, where efficiency may be improved through transfer across related tasks. In practice, however, this is not usually observed, because gradients from different tasks can interfe...

Expand abstract
Publication status:
Published
Peer review status:
Reviewed (other)

Actions


Access Document


Authors


More by this author
Department:
STATISTICS
Sub department:
Statistics
Role:
Author
ORCID:
0000-0001-5365-6933
Expand authors...
Publisher:
Massachusetts Institute of Technology Press Publisher's website
Volume:
30
Pages:
4497-4507
Host title:
Advances in Neural Information Processing Systems 30 (NIPS 2017)
Publication date:
2017-01-01
Acceptance date:
2017-09-04
Event title:
2017 Conference on Neural Information Processing Systems
Event location:
Long Beach, CA, USA
Event website:
https://nips.cc/Conferences/2017
Event start date:
2017-12-04T00:00:00Z
Event end date:
2017-12-09T00:00:00Z
ISSN:
1049-5258
Pubs id:
982776
Local pid:
pubs:982776
Deposit date:
2020-02-06

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