Settling the sample complexity of model-based offline reinforcement learning

DOI10.1214/23-aos2342arXiv2204.05275MaRDI QIDQ6192326

Yuting Wei, Yuejie Chi, Laixi Shi, Unnamed Author, Yuxin Chen

Publication date: 11 March 2024

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

Full work available at URL: https://arxiv.org/abs/2204.05275

zbMATH Keywords

Markov decision processminimax optimalitysample complexitydistribution shiftoffline reinforcement learning

Mathematics Subject Classification ID

Minimax procedures in statistical decision theory (62C20)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Minimax PAC bounds on the sample complexity of reinforcement learning with a generative model
• Asymptotically efficient adaptive allocation rules
• \({\mathcal Q}\)-learning
• Error bounds for constant step-size \(Q\)-learning
• High-Dimensional Statistics
• Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction
• Bandit Algorithms
• Instance-Dependent ℓ_∞-Bounds for Policy Evaluation in Tabular Reinforcement Learning
• Performance Bounds in $L_p$‐norm for Approximate Value Iteration
• A Stochastic Approximation Method

This page was built for publication: Settling the sample complexity of model-based offline reinforcement learning