To update or not to update? Delayed Nonparametric Bandits with Randomized Allocation
This work addresses the delayed rewards issue in contextual bandits, which is incremental as it builds on existing randomized strategies by analyzing their trade-offs under delays.
The paper tackles the problem of delayed rewards in contextual bandits by comparing two randomized allocation strategies: one that updates the exploration sequence at every time point and another that updates only when new rewards are observed, showing that the latter ensures strong consistency in allocation across a wider range of situations, while finite sample performance varies with delay severity and reward mechanisms.
Delayed rewards problem in contextual bandits has been of interest in various practical settings. We study randomized allocation strategies and provide an understanding on how the exploration-exploitation tradeoff is affected by delays in observing the rewards. In randomized strategies, the extent of exploration-exploitation is controlled by a user-determined exploration probability sequence. In the presence of delayed rewards, one may choose between using the original exploration sequence that updates at every time point or update the sequence only when a new reward is observed, leading to two competing strategies. In this work, we show that while both strategies may lead to strong consistency in allocation, the property holds for a wider scope of situations for the latter. However, for finite sample performance, we illustrate that both strategies have their own advantages and disadvantages, depending on the severity of the delay and underlying reward generating mechanisms.