Gradient temporal-difference learning for off-policy evaluation using emphatic weightings

DOI10.1016/J.INS.2021.08.082MaRDI QIDQ6146179zbMATH OpenOpenAlexFDO

Authors Jiaqing Cao, Quan Liu, Fei Zhu, Qi-Ming Fu, Shan Zhong

Publication date 10 January 2024

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ins.2021.08.082

zbMATH Keywords

reinforcement learningtemporal-difference learningoff-policy evaluationemphatic approachgradient temporal-difference learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Logic in computer science (03B70)

Recommendations

• An emphatic approach to the problem of off-policy temporal-difference learning
• Off-policy linear temporal difference learning algorithms with a generalized oblique projection
• \(\text{Q}(\lambda)\) with off-policy corrections
• Policy evaluation with temporal differences: a survey and comparison
• Off-policy temporal difference learning with distribution adaptation in fast mixing chains

Cites work

• An analysis of temporal-difference learning with function approximation
• An emphatic approach to the problem of off-policy temporal-difference learning
• Marginal Mean Models for Dynamic Regimes
• Policy evaluation with temporal differences: a survey and comparison
• Recruitment-imitation mechanism for evolutionary reinforcement learning
• Reinforcement learning. An introduction
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
• Weak convergence properties of constrained emphatic temporal-difference learning with constant and slowly diminishing stepsize
• \({\mathcal Q}\)-learning

Cited in

(1)

• Projected state-action balancing weights for offline reinforcement learning

This page was built for publication: Gradient temporal-difference learning for off-policy evaluation using emphatic weightings

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6146179)