Conference item icon

Conference item

Breaking the deadly triad with a target network

Abstract:

The deadly triad refers to the instability of a reinforcement learning algorithm when it employs off-policy learning, function approximation, and bootstrapping simultaneously. In this paper, we investigate the target network as a tool for breaking the deadly triad, providing theoretical support for the conventional wisdom that a target network stabilizes training. We first propose and analyze a novel target network update rule which augments the commonly used Polyak-averaging style update wit...

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

Actions


Access Document


Files:
Publication website:
http://proceedings.mlr.press/v139/zhang21y.html

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Oxford college:
St Catherines College; St Catherines College; St Catherines College; St Catherines College; St Catherines College; St Catherines College; St Catherines College; St Catherines College; St Catherines College
Role:
Author
More from this funder
Name:
European Commission
Grant:
637713
Publisher:
PMLR
Host title:
Proceedings of the 38th International Conference on Machine Learning
Series:
Proceedings of Machine Learning Research
Volume:
139
Pages:
12621-12631
Publication date:
2021-07-21
Acceptance date:
2021-05-08
Event title:
38th International Conference on Machine Learning (ICML 2021)
Event location:
Virtual Event
Event website:
https://icml.cc/
Event start date:
2021-07-18
Event end date:
2021-07-24
ISSN:
2640-3498
Language:
English
Keywords:
Pubs id:
1187446
Local pid:
pubs:1187446
Deposit date:
2021-07-24

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