Safe Exploration for Efficient Policy Evaluation and Comparison
This addresses the need for high-quality data in policy evaluation, but appears incremental as it builds on existing bandit frameworks.
The paper tackles the problem of efficient and safe data collection for bandit policy evaluation by formulating variants, analyzing statistical properties, deriving exploration policies, and designing efficient algorithms, with theoretical and experimental support.
High-quality data plays a central role in ensuring the accuracy of policy evaluation. This paper initiates the study of efficient and safe data collection for bandit policy evaluation. We formulate the problem and investigate its several representative variants. For each variant, we analyze its statistical properties, derive the corresponding exploration policy, and design an efficient algorithm for computing it. Both theoretical analysis and experiments support the usefulness of the proposed methods.