Abstract
We study a multi-armed bandit problem with covariates in a setting where there is a possible delay in observing the rewards. Under some reasonable assumptions on the probability distributions for the delays and using an appropriate randomization to select the arms, the proposed strategy is shown to be strongly consistent.
Original language | English (US) |
---|---|
Article number | 108818 |
Journal | Statistics and Probability Letters |
Volume | 164 |
DOIs | |
State | Published - Sep 2020 |
Bibliographical note
Publisher Copyright:© 2020
Keywords
- Delayed rewards
- Histogram method
- Multi-armed bandit with covariates
- Strong consistency