Learning from Logged Implicit Exploration Data

Abstract

We provide a sound and consistent foundation for the use of \emph{nonrandom} exploration data in "contextual bandit" or "partially labeled" settings where only the value of a chosen action is learned. The primary challenge in a variety of settings is that the exploration policy, in which "offline" data is logged, is not explicitly known. Prior solutions here require either control of the actions during the learning process, recorded random exploration, or actions chosen obliviously in a repeated manner. The techniques reported here lift these restrictions, allowing the learning of a policy for choosing actions given features from historical data where no randomization occurred or was logged. We empirically verify our solution on two reasonably sized sets of real-world data obtained from Yahoo!.

Cited by in corpus (6)

• Counterfactual Risk Minimization: Learning from Logged Bandit Feedback
• Machine Learning Methods Economists Should Know About
• Counterfactual Estimation and Optimization of Click Metrics for Search Engines
• Improving offline evaluation of contextual bandit algorithms via bootstrapping techniques
• Sample-efficient Nonstationary Policy Evaluation for Contextual Bandits
• Evaluation of Explore-Exploit Policies in Multi-result Ranking Systems