The efficacy of pessimism in asynchronous Q-learning

DOI10.1109/TIT.2023.3299840MaRDI QIDQ6575545zbMATH OpenFDO

Authors Yuling Yan, Gen Li, Yuxin Chen, Jianqing Fan

Publication date 21 July 2024

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/TIT.2023.3299840

zbMATH Keywords

asynchronous form of Q-learningstochastic approximation scheme to Markovian data samples

Mathematics Subject Classification ID

Stochastic approximation (62L20) Learning and adaptive systems in artificial intelligence (68T05)

Cited in

(4)

• Policy learning ``without overlap: pessimism and generalized empirical Bernstein's inequality
• Settling the sample complexity of online reinforcement learning
• Slowly changing adversarial bandit algorithms are efficient for discounted MDPs
• Bayesian safe policy learning with chance constrained optimization: application to military security assessment during the Vietnam War

This page was built for publication: The efficacy of pessimism in asynchronous Q-learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6575545)