Corruption-robust exploration in episodic reinforcement learning
| Year of publication: |
2025
|
|---|---|
| Authors: | Lykouris, Thodoris ; Simchowitz, Max ; Slivkins, Aleksandrs ; Sun, Wen |
| Published in: |
Mathematics of operations research. - Hanover, Md. : INFORMS, ISSN 1526-5471, ZDB-ID 2004273-5. - Vol. 50.2025, 2, p. 1277-1304
|
| Subject: | reinforcement learning | exploration | regret | robustness | bandit feedback | Lernen | Learning | Lernprozess | Learning process | Entscheidung unter Unsicherheit | Decision under uncertainty | Spieltheorie | Game theory |
-
Reinforcement learning in economics and finance
Charpentier, Arthur, (2023)
-
Regret testing : learning to play Nash equilibrium without knowing you have an opponent
Foster, Dean P., (2006)
-
Social learning and communication with threshold uncertainty
Guilfoos, Todd, (2019)
- More ...
-
Exploration and incentives in reinforcement learning
Simchowitz, Max, (2024)
-
Sellke, Mark, (2023)
-
Bayesian exploration : incentivizing exploration in Bayesian games
Mansour, Yishay, (2022)
- More ...