Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning.
- Award ID(s):
- 2112471
- Publication Date:
- NSF-PAR ID:
- 10315981
- Journal Name:
- Proceedings of Neural Information Processing Systems (NeurIPS), 2021.
- Sponsoring Org:
- National Science Foundation
More Like this
No document suggestions found
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Publisher's Version of Record
- The DOI is not currently available
