English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Evidence-based targeting has been a topic of growing interest among thepractitioners of policy and business. Formulating decision-maker's policylearning as a fixed-budget best arm identification (BAI) problem withcontextual information, we study an optimal adaptive experimental design forpolicy learning with multiple treatment arms. In the sampling stage, theplanner assigns treatment arms adaptively over sequentially arrivingexperimental units upon observing their contextual information (covariates).After the experiment, the planner recommends an individualized assignment ruleto the population. Setting the worst-case expected regret as the performancecriterion of adaptive sampling and recommended policies, we derive itsasymptotic lower bounds, and propose a strategy, Adaptive Sampling-PolicyLearning strategy (PLAS), whose leading factor of the regret upper bound alignswith the lower bound as the size of experimental units increases.

Adaptive Experimental Design for Policy Learning