Satisficing in Time-Sensitive Bandit Learning
Published Online:14 Mar 2022https://doi.org/10.1287/moor.2021.1229
- Cited by
- 9 May 2025 | Mathematics of Operations Research, Vol. 51, No. 2
- 10 April 2026 | Journal of Statistical Mechanics: Theory and Experiment, Vol. 2026, No. 4
- Engineering Applications of Artificial Intelligence, Vol. 154
- 23 January 2024 | Physical Review E, Vol. 109, No. 1
Volume 47, Issue 4
November 2022
Pages 2547-3399, C2
Article Information
Supplemental Material
Metrics
Information
- Received:March 05, 2018
- Accepted:December 02, 2020
- Published Online:March 14, 2022
Copyright © 2022, INFORMS
Cite as
Daniel Russo, Benjamin Van Roy (2022) Satisficing in Time-Sensitive Bandit Learning. Mathematics of Operations Research 47(4):2815-2839.
https://doi.org/10.1287/moor.2021.1229
Keywords
A special thanks is owed to David Tse, who played an important role in the early stages of this work. It was David who first emphasized that bounds based on entropy can be vacuous and pointed us to references on rate-distortion theory. The authors also thank Tor Lattimore for thoughtful comments on an early draft of this work.
