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:
-
-
(Version of record, 1.5MB)
-
- Publication website:
- http://proceedings.mlr.press/v119/zhang20t.html
Authors
Funding
Bibliographic Details
- 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
Item Description
- Language:
- English
- Keywords:
- Pubs id:
-
1115294
- Local pid:
- pubs:1115294
- Deposit date:
- 2020-07-01
Terms of use
- Copyright holder:
- Zhang et al.
- Copyright date:
- 2020
- Rights statement:
- © The Author(s) 2020. Open Access: Creative Commons Attribution licence.
- Notes:
- This paper has been accepted for presentation at the 37th International Conference of Machine Learning (ICML 2020), July 2020. The final version is available online from PMLR at: http://proceedings.mlr.press/v119/zhang20t.html
- Licence:
- CC Attribution (CC BY)
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record