A policy gradient algorithm for the risk-sensitive exponential cost MDP

DOI10.1287/MOOR.2022.0139MaRDI QIDQ7024072zbMATH OpenFDO

Authors Mehrdad Moharrami, Yashaswini Murthy, Arghyadip Roy, R. Srikant

Publication date 21 February 2025

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

Full work available at URL https://doi.org/10.1287/MOOR.2022.0139

zbMATH Keywords

policy gradient theoremreinforcement learningrisk-sensitive Markov decision processesstochastic approximation

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) Computational methods in Markov chains (60J22) Numerical analysis or methods applied to Markov chains (65C40)

Cited in

(1)

• Stochastic approximation and reinforcement learning: the interface and a little beyond

This page was built for publication: A policy gradient algorithm for the risk-sensitive exponential cost MDP

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7024072)