View in EDS HTML Full Text PDF Full Text

Is Pessimism Provably Efficient for Offline Reinforcement Learning?

Saved in:

Bibliographic Details
Title:	Is Pessimism Provably Efficient for Offline Reinforcement Learning?
Authors:	Jin, Ying¹ (AUTHOR) ying531@alumni.stanford.edu, Yang, Zhuoran² (AUTHOR) zhuoran.yang@yale.edu, Wang, Zhaoran³ (AUTHOR) zhaoranwang@gmail.com
Source:	Mathematics of Operations Research (INFORMS). Nov2025, Vol. 50 Issue 4, p2738-2793. 56p.
Database:	Business Source Ultimate
Full text is not displayed to guests. Login for full access.

Description
ISSN:	0364765X
DOI:	10.1287/moor.2022.0216