Performance guarantees for policy learning

DOI10.1214/19-AIHP1034MaRDI QIDQ2227481zbMATH OpenFDO

Authors Alex Luedtke, Antoine Chambaz

Publication date 15 February 2021

Published in Annales de l'Institut Henri Poincaré. Probabilités et Statistiques (Search for Journal in Brave)

Full work available at URL https://projecteuclid.org/euclid.aihp/1593137323

zbMATH Keywords

repeated gamepolicy learning

Mathematics Subject Classification ID

Multistage and repeated games (91A20) Rationality and learning in game theory (91A26)

Recommendations

• Analysis of classification-based policy iteration algorithms
• Finite-time analysis of the multiarmed bandit problem
• Near-optimal regret bounds for reinforcement learning
• Regret bounds and minimax policies under partial monitoring
• Regularized policy iteration with nonparametric function spaces

Cites work

• scientific article; zbMATH DE number 3169867 (Why is no real title available?)
• scientific article; zbMATH DE number 490141 (Why is no real title available?)
• scientific article; zbMATH DE number 843258 (Why is no real title available?)
• A Doubly Robust Censoring Unbiased Transformation
• A robust method for estimating optimal treatment regimes
• Asymptotic Statistics
• Asymptotics for statistical treatment rules
• Double/debiased machine learning for treatment and structural parameters
• Estimating individualized treatment rules using outcome weighted learning
• Fast learning rates for plug-in classifiers
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Minimax regret treatment choice with finite samples
• Optimal aggregation of classifiers in statistical learning.
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Performance guarantees for individualized treatment rules
• Statistical inference for the mean outcome under a possibly non-unique optimal treatment strategy
• Statistical treatment rules for heterogeneous populations.
• Targeted sequential design for targeted learning inference of the optimal treatment rule and its mean reward
• Unified methods for censored longitudinal data and causality
• Uniform Donsker classes of functions
• Weak convergence and empirical processes. With applications to statistics
• Who should be treated? Empirical welfare maximization methods for treatment choice

Cited in

(4)

• Rejoinder: Optimal Individualized Decision Rules Using Instrumental Variable Methods
• Debiasing in-sample policy performance for small-data, large-scale optimization
• Rejoinder: New Objectives for Policy Learning
• Learning when-to-treat policies

This page was built for publication: Performance guarantees for policy learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2227481)