Conference item icon

Conference item

Invariant causal prediction for block MDPs

Abstract:

Generalization across environments is critical to the successful application of reinforcement learning (RL) algorithms to real-world challenges. In this work we propose a method for learning state abstractions which generalize to novel observation distributions in the multi-environment RL setting. We prove that for certain classes of environments, this approach outputs, with high probability, a state abstraction corresponding to the causal feature set with respect to the return. We give empir...

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

Actions


Access Document


Files:
Publication website:
http://proceedings.mlr.press/v119/zhang20t.html

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
Publisher:
Proceedings of Machine Learning Research Publisher's website
Journal:
Proceedings of Machine Learning Research Journal website
Volume:
119
Pages:
11214-11224
Publication date:
2020-11-21
Acceptance date:
2020-05-31
Event title:
37th International Conference of Machine Learning (ICML 2020)
Event website:
https://icml.cc/
Event start date:
2020-07-12
Event end date:
2020-07-18
ISSN:
2640-3498
Language:
English
Keywords:
Pubs id:
1115294
Local pid:
pubs:1115294
Deposit date:
2020-07-01

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