Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 59 - Invited E-Poster Session I
Type: Invited
Date/Time: Sunday, August 8, 2021 : 5:45 PM to 6:30 PM
Sponsor: Biometrics Section
Abstract #317181
Title: Non-Dominated Adaptive Experimental Designs
Author(s): Eric Laber and Peter Norwood* and Marie Davidian
Companies: Duke University and North Carolina State University and North Carolina State University
Keywords: Precision medicine; Treatment regimes; Experimental Design; Bandits; Reinforcement Learning
Abstract:

In sequential experiments, the exploration-exploitation trade-off describes the choice between (i) experiments that efficiently generate information useful for improving fitted models, and (ii) experiments that maximize utility based on current models. An optimal sequential experimental design maximizes longterm cumulative utility by exploring only if and when the value of information generated by exploration is expected to outweigh any short-term loss in utility. In general, it is not possible to construct an optimal sequential experimental design save for in contrived special cases. Thus, it is common to use heuristics that force exploration through randomization or by adding an exploration `bonus' to the utility function. We show that commonly used heuristics can frequently select experiments that generate less information and less utility than alternatives. Such experiments are said to be dominated in terms of utility and information. We show that, at each time point, one can remove from consideration experiments that are estimated to be dominated and then apply standard heuristics for forced exploration without destroying consistency or asymptotic normality.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2021 program