Adaptive Experimental Design for Policy Learning

Autor:	Kato, Masahiro, Okumura, Kyohei, Ishihara, Takuya, Kitagawa, Toru
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Economics - Econometrics Statistics - Methodology Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Evidence-based targeting has been a topic of growing interest among the practitioners of policy and business. Formulating decision-maker's policy learning as a fixed-budget best arm identification (BAI) problem with contextual information, we study an optimal adaptive experimental design for policy learning with multiple treatment arms. In the sampling stage, the planner assigns treatment arms adaptively over sequentially arriving experimental units upon observing their contextual information (covariates). After the experiment, the planner recommends an individualized assignment rule to the population. Setting the worst-case expected regret as the performance criterion of adaptive sampling and recommended policies, we derive its asymptotic lower bounds, and propose a strategy, Adaptive Sampling-Policy Learning strategy (PLAS), whose leading factor of the regret upper bound aligns with the lower bound as the size of experimental units increases. Comment: arXiv admin note: text overlap with arXiv:2302.02988
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2401.03756 Zobrazit plný text záznamu View this record from Arxiv