Conference item icon

Conference item

Average-reward off-policy policy evaluation with function approximation

Abstract:

We consider off-policy policy evaluation with function approximation (FA) in average-reward MDPs, where the goal is to estimate both the reward rate and the differential value function. For this problem, bootstrapping is necessary and, along with off-policy learning and FA, results in the deadly triad (Sutton & Barto, 2018). To address the deadly triad, we propose two novel algorithms, reproducing the celebrated success of Gradient TD algorithms in the average-reward setting. In terms of esti...

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

Actions


Access Document


Files:
Publication website:
http://proceedings.mlr.press/v139/zhang21u.html

Authors


More by this author
Institution:
University of Oxford
Department:
COMPUTER SCIENCE
Sub 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:
12578-12588
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:
1187447
Local pid:
pubs:1187447
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