Finite-time error bounds of biased stochastic approximation with application to TD-learning

DOI10.1109/TSP.2021.3128723MaRDI QIDQ6602739zbMATH OpenFDO

Authors Gang Wang

Publication date 12 September 2024

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/TSP.2021.3128723

Mathematics Subject Classification ID

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Cited in

(1)

• Sample complexity of variance-reduced distributionally robust Q-learning

This page was built for publication: Finite-time error bounds of biased stochastic approximation with application to TD-learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6602739)