Adaptive Experimental Design For Policy Learning

Abstract

This study investigates the contextual best arm identification (BAI) problem, aiming to design an adaptive experiment to identify the best treatment arm conditioned on contextual information (covariates). We consider a decision-maker who assigns treatment arms to experimental units during an experiment and recommends the estimated best treatment arm based on the contexts at the end of the experiment. The decision-maker uses a policy for recommendations, which is a function that provides the estimated best treatment arm given the contexts. In our evaluation, we focus on the worst-case expected regret, a relative measure between the expected outcomes of an optimal policy and our proposed policy. We derive a lower bound for the expected simple regret and then propose a strategy called Adaptive Sampling-Policy Learning (PLAS). We prove that this strategy is minimax rate-optimal in the sense that its leading factor in the regret upper bound matches the lower bound as the number of experimen

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykato2024adaptive

Related papers

• Policy Learning With Adaptively Collected Data (2021)0.00
• Active Causal Experimentalist (ACE): Learning Intervention Strategies Via Direct Preference Optimization (2026)0.00
• Design Experiments To Compare Multi-armed Bandit Algorithms (2026)0.00
• Pure Exploration Under Mediators' Feedback (2023)0.00
• Quick Best Action Identification In Linear Bandit Problems (2018)0.00
• Performance Comparisons Of Reinforcement Learning Algorithms For Sequential Experimental Design (2025)0.00
• Adaptive Experience Selection For Policy Gradient (2020)0.00
• Adaptive Doubly Robust Estimator From Non-stationary Logging Policy Under A Convergence Of Average Probability (2021)0.00