Randomized Allocation with Nonparametric Estimation for Contextual Multi-Armed Bandits with Delayed Rewards
arXiv:1902.00819v325 citations
Originality Incremental advance
AI Analysis
This addresses the challenge of delayed feedback in bandit algorithms, which is incremental as it builds on existing contextual bandit methods.
The paper tackles the problem of contextual multi-armed bandits with delayed rewards by proposing a strategy that uses randomization and nonparametric estimation, proving it to be strongly consistent under mild assumptions on delay distributions.
We study a multi-armed bandit problem with covariates in a setting where there is a possible delay in observing the rewards. Under some mild 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.