On the Maximization of Long-Run Conditional Value-at-Risk for Markov Decision Processes
Published Online:23 Oct 2026https://doi.org/10.1287/opre.2025.1811
Articles In Advance
Article Information
Supplemental Material
Metrics
Information
- Received:May 13, 2024
- Accepted:September 09, 2026
- Published Online:October 23, 2026
Copyright © 2026, INFORMS
Cite as
Li Xia, Zhihui Yu, Haoran Wu (2026) On the Maximization of Long-Run Conditional Value-at-Risk for Markov Decision Processes. Operations Research 0(0).
https://doi.org/10.1287/opre.2025.1811
Keywords
The authors thank the reviewers and editors for their valuable feedback and suggestions, which have significantly improved this work. The first author thanks Prof. Peter W. Glynn at Stanford University for his insightful comments on the long-run CVaR criterion and its practical implications in risk-seeking decision making.
