High-Probability Sample Complexities for Policy Evaluation With Linear Function Approximation-Reference-Cited by-同舟云学术

High-Probability Sample Complexities for Policy Evaluation With Linear Function Approximation

Author:

Li Gen¹,Wu Weichen²^ORCID,Chi Yuejie³^ORCID,Ma Cong⁴^ORCID,Rinaldo Alessandro⁵,Wei Yuting⁶^ORCID

Affiliation:

1. Department of Statistics, The Chinese University of Hong Kong, Hong Kong, China

2. Department of Statistics and Data Science, Carnegie Mellon University, Pittsburgh, PA, USA

3. Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA

4. Department of Statistics, The University of Chicago, Chicago, IL, USA

5. Department of Statistics and Data Science, The University of Texas at Austin, Austin, UT, USA

6. Department of Statistics and Data Science, The Wharton School, University of Pennsylvania, Philadelphia, PA, USA

Funder

Chinese University of Hong Kong (CUHK) Direct Grant for Research

NIH

Office of Naval Research

NSF

NSF CAREER Award

Google Research Scholar Award

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

Reference69 articles.

3. Model selection for offline reinforcement learning: Practical considerations for healthcare settings;Tang

4. Policy evaluation with temporal differences: A survey and comparison;Dann;J. Mach. Learn. Res.,2014