Delay-Adaptive Learning in Generalized Linear Contextual Bandits
This work addresses delays in reward feedback for contextual bandits, which is incremental to existing literature but relevant for applications like recommendation engines.
The paper tackles the problem of online learning in generalized linear contextual bandits with unknown stochastic delays in reward observation, showing that both upper confidence bound and Thompson sampling algorithms can be adapted to handle delays with established regret characterizations.
In this paper, we consider online learning in generalized linear contextual bandits where rewards are not immediately observed. Instead, rewards are available to the decision-maker only after some delay, which is unknown and stochastic. We study the performance of two well-known algorithms adapted to this delayed setting: one based on upper confidence bounds, and the other based on Thompson sampling. We describe modifications on how these two algorithms should be adapted to handle delays and give regret characterizations for both algorithms. Our results contribute to the broad landscape of contextual bandits literature by establishing that both algorithms can be made to be robust to delays, thereby helping clarify and reaffirm the empirical success of these two algorithms, which are widely deployed in modern recommendation engines.