Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis

DOI10.1287/opre.2023.2450arXiv2102.06548MaRDI QIDQ6198738

Yuxin Chen, Yuting Wei, Yuejie Chi, Unnamed Author, Changxiao Cai

Publication date: 20 March 2024

Published in: Operations Research (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2102.06548

zbMATH Keywords

lower boundoverestimationtemporal difference learningQ-learningminimax optimalitysample complexityeffective horizon

Mathematics Subject Classification ID

Mathematical programming (90Cxx)

This page was built for publication: Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis