Stochastic first-order methods for average-reward Markov decision processes

DOI10.1287/MOOR.2022.0241MaRDI QIDQ6893677zbMATH OpenFDO

Authors Tianjiao Li, Feiyang Wu, Guanghui Lan

Publication date 26 November 2025

Published in Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1287/MOOR.2022.0241

zbMATH Keywords

average rewardfirst-order methodMarkov decision processespolicy evaluationpolicy mirror descentpolicy optimizationtemporal difference

Mathematics Subject Classification ID

Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Computational methods in Markov chains (60J22) Numerical analysis or methods applied to Markov chains (65C40) Analysis of algorithms and problem complexity (68Q25) Stochastic programming (90C15) Nonlinear programming (90C30) Markov and semi-Markov decision processes (90C40)

Cited in

(2)

• A model-free first-order method for linear quadratic regulator with \(\tilde{O}(1/\varepsilon)\) sampling complexity
• Policy optimization over general state and action spaces

This page was built for publication: Stochastic first-order methods for average-reward Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6893677)