Adapting to Misspecification in Contextual Bandits with Offline Regression Oracles [article]

Sanath Kumar Krishnamurthy, Vitor Hadad, Susan Athey
2021 arXiv   pre-print
Computationally efficient contextual bandits are often based on estimating a predictive model of rewards given contexts and arms using past data. However, when the reward model is not well-specified, the bandit algorithm may incur unexpected regret, so recent work has focused on algorithms that are robust to misspecification. We propose a simple family of contextual bandit algorithms that adapt to misspecification error by reverting to a good safe policy when there is evidence that
more » ... ion is causing a regret increase. Our algorithm requires only an offline regression oracle to ensure regret guarantees that gracefully degrade in terms of a measure of the average misspecification level. Compared to prior work, we attain similar regret guarantees, but we do no rely on a master algorithm, and do not require more robust oracles like online or constrained regression oracles (e.g., Foster et al. (2020a); Krishnamurthy et al. (2020)). This allows us to design algorithms for more general function approximation classes.
arXiv:2102.13240v2 fatcat:ho4raxl7xfcjnbw5n2crzlnqzy