Efficient Policy Learning

02/09/2017
by   Susan Athey, et al.
0

We consider the problem of using observational data to learn treatment assignment policies that satisfy certain constraints specified by a practitioner, such as budget, fairness, or functional form constraints. This problem has previously been studied in economics, statistics, and computer science, and several regret-consistent methods have been proposed. However, several key analytical components are missing, including a characterization of optimal methods for policy learning, and sharp bounds for minimax regret. In this paper, we derive lower bounds for the minimax regret of policy learning under constraints, and propose a method that attains this bound asymptotically up to a constant factor. Whenever the class of policies under consideration has a bounded Vapnik-Chervonenkis dimension, we show that the problem of minimax-regret policy learning can be asymptotically reduced to first efficiently evaluating how much each candidate policy improves over a randomized baseline, and then maximizing this value estimate. Our analysis relies on uniform generalizations of classical semiparametric efficiency results for average treatment effect estimation, paired with sharp concentration bounds for weighted empirical risk minimization that may be of independent interest.

READ FULL TEXT
research
09/26/2022

Off-policy estimation of linear functionals: Non-asymptotic theory for semi-parametric efficiency

The problem of estimating a linear functional based on observational dat...
research
11/06/2015

Optimal Non-Asymptotic Lower Bound on the Minimax Regret of Learning with Expert Advice

We prove non-asymptotic lower bounds on the expectation of the maximum o...
research
02/06/2023

Asymptotically Minimax Optimal Fixed-Budget Best Arm Identification for Expected Simple Regret Minimization

We investigate fixed-budget best arm identification (BAI) for expected s...
research
11/18/2020

On Uninformative Optimal Policies in Adaptive LQR with Unknown B-Matrix

This paper presents local asymptotic minimax regret lower bounds for ada...
research
06/03/2021

Bandit Phase Retrieval

We study a bandit version of phase retrieval where the learner chooses a...
research
08/29/2022

Safe Policy Learning under Regression Discontinuity Designs

The regression discontinuity (RD) design is widely used for program eval...
research
04/23/2023

Policy Learning under Biased Sample Selection

Practitioners often use data from a randomized controlled trial to learn...

Please sign up or login with your details

Forgot password? Click here to reset