Online Bootstrap Inference For Policy Evaluation In Reinforcement Learning

DOI10.1080/01621459.2022.2096620arXiv2108.03706OpenAlexW3191746168MaRDI QIDQ6185586

Unnamed Author, Zhaoran Wang, Wei Sun, Unnamed Author, Guang Cheng, Zhuoran Yang

Publication date: 8 January 2024

Published in: Journal of the American Statistical Association (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2108.03706

zbMATH Keywords

asymptotic normalitystochastic approximationstatistical inferencereinforcement learningmultiplier bootstrap

Mathematics Subject Classification ID

Statistics (62-XX)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Trajectory averaging for stochastic approximation MCMC algorithms
• Challenges of real-world reinforcement learning: definitions, benchmarks and analysis
• Statistical inference for model parameters in stochastic gradient descent
• Moment Consistency of the Exchangeably Weighted Bootstrap for Semiparametric M-estimation
• Markov Chains and Stochastic Stability
• Acceleration of Stochastic Approximation by Averaging
• An analysis of temporal-difference learning with function approximation
• Constructing dynamic treatment regimes over indefinite time horizons
• Markov Chains
• 10.1162/1532443041827907
• Statistical Inference for Online Decision Making via Stochastic Gradient Descent
• Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning
• Estimating Dynamic Treatment Regimes in Mobile Health Using V-Learning
• Inference and uncertainty quantification for noisy matrix completion
• Stability of Stochastic Approximation under Verifiable Conditions
• A Stochastic Approximation Method
• The bootstrap and Edgeworth expansion
• Dynamic Causal Effects Evaluation in A/B Testing with a Reinforcement Learning Framework