Batch policy learning in average reward Markov decision processes

DOI10.1214/22-AOS2231MaRDI QIDQ2112817

Zhengling Qi, Runzhe Wan, Peng Liao, Predrag Klasnja, Susan A. Murphy

Publication date: 12 January 2023

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2007.11771

zbMATH Keywords

Markov decision processaverage rewarddoubly robust estimatorpolicy optimization

Mathematics Subject Classification ID

Nonparametric estimation (62G05)

Related Items (3)

A multiagent reinforcement learning framework for off-policy evaluation in two-sided markets ⋮ Off-policy evaluation in partially observed Markov decision processes under sequential ignorability ⋮ Projected state-action balancing weights for offline reinforcement learning

Uses Software

• L-BFGS
• Spearmint

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Doubly robust policy evaluation and optimization
• Dynamic treatment regimes: technical challenges and applications
• Model selection in reinforcement learning
• On the limited memory BFGS method for large scale optimization
• Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path
• Kernel-based reinforcement learning
• The landscape of empirical risk for nonconvex losses
• Statistical consistency and asymptotic normality for high-dimensional robust \(M\)-estimators
• Learning Algorithms for Markov Decision Processes with Average Cost
• Semiparametric efficiency bounds
• Support Vector Machines
• Asymptotic Statistics
• Estimation of Regression Coefficients When Some Regressors Are Not Always Observed
• Marginal Mean Models for Dynamic Regimes
• Constructing dynamic treatment regimes over indefinite time horizons
• 10.1162/1532443041827907
• A Robust Method for Estimating Optimal Treatment Regimes
• Double/debiased machine learning for treatment and structural parameters
• Estimating Dynamic Treatment Regimes in Mobile Health Using V-Learning
• New Statistical Learning Methods for Estimating Optimal Dynamic Treatment Regimes
• Robust estimation of optimal dynamic treatment regimes for sequential treatment decisions
• Off-Policy Estimation of Long-Term Average Outcomes With Applications to Mobile Health
• Resampling‐based confidence intervals for model‐free robust inference on optimal treatment regimes

This page was built for publication: Batch policy learning in average reward Markov decision processes