Off-line Estimation of Controlled Markov Chains: Minimaxity and Sample Complexity
Published Online:21 Feb 2025https://doi.org/10.1287/opre.2023.0046
Volume 73, Issue 4
July-August 2025
Pages iii-viii, 1723-2295, C2-C3
Article Information
Supplemental Material
Metrics
Information
- Received:January 29, 2023
- Accepted:November 26, 2024
- Published Online:February 21, 2025
Copyright © 2025, INFORMS
Cite as
Imon Banerjee, Harsha Honnappa, Vinayak Rao (2025) Off-line Estimation of Controlled Markov Chains: Minimaxity and Sample Complexity. Operations Research 73(4):2281-2295.
https://doi.org/10.1287/opre.2023.0046
Keywords
I. Banerjee thanks Anamitra Chaudhuri for numerous insightful discussions and comments throughout the duration of this project. The authors thank the anonymous reviewers for their insightful comments and especially for pointing them toward the interesting application detailed in Section 4.5. Work was completed while Imon Banerjee was at the Department of Statistics, Purdue University.
