Off-policy temporal difference learning with distribution adaptation in fast mixing chains

DOI10.1007/S00500-017-2490-1MaRDI QIDQ1797759zbMATH OpenOpenAlexFDO

Authors Arash Givchi, Maziar Palhang

Publication date 22 October 2018

Published in Soft Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s00500-017-2490-1

zbMATH Keywords

mixing timereinforcement learningcovariate shift adaptationleast-squares temporal differenceoff-policy evaluation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• \(\text{Q}(\lambda)\) with off-policy corrections
• Off-policy learning with eligibility traces: a survey
• An emphatic approach to the problem of off-policy temporal-difference learning
• Policy evaluation with temporal differences: a survey and comparison

Cites work

• scientific article; zbMATH DE number 3841285 (Why is no real title available?)
• scientific article; zbMATH DE number 19232 (Why is no real title available?)
• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• A least-squares approach to direct importance estimation
• An analysis of temporal-difference learning with function approximation
• An emphatic approach to the problem of off-policy temporal-difference learning
• Direct importance estimation for covariate shift adaptation
• Error bounds for approximations from projected linear equations
• Inferences for case-control and semiparametric two-sample density ratio models
• Linear least-squares algorithms for temporal difference learning
• Markov chains and mixing times. With a chapter on ``Coupling from the past by James G. Propp and David B. Wilson.
• Mode-dependent nonrational output feedback control for continuous-time semi-Markovian jump systems with time-varying delay
• Off-policy learning with eligibility traces: a survey
• Policy evaluation with temporal differences: a survey and comparison
• Probabilistic graphical models.
• Projected equation methods for approximate solution of large linear systems
• Semiparametric density estimation under a two-sample density ratio model
• Temporal Difference Methods for General Projected Equations
• model reduction for continuous-time Markovian jump systems with incomplete statistics of mode information

Cited in

(2)

• Gradient temporal-difference learning for off-policy evaluation using emphatic weightings
• Adaptive importance sampling for value function approximation in off-policy reinforcement learning

This page was built for publication: Off-policy temporal difference learning with distribution adaptation in fast mixing chains

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1797759)