On linear and super-linear convergence of natural policy gradient algorithm

DOI10.1016/j.sysconle.2022.105214zbMath1492.93060arXiv2105.01424OpenAlexW4225011832WikidataQ115036590 ScholiaQ115036590MaRDI QIDQ2670744

Prakirt Raj Jhunjhunwala, Siva Theja Maguluri, Sushil Mahavir Varma, Sajad Khodadadian

Publication date: 1 June 2022

Published in: Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2105.01424

zbMATH Keywords

reinforcement learningactor-criticpolicy gradient methodlinear and super-linear convergence

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Iterative learning control (93B47)

Related Items (2)

Block Policy Mirror Descent ⋮ Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence

Cites Work

• Natural actor-critic algorithms
• Improved and Generalized Upper Bounds on the Complexity of Policy Iteration
• On the Convergence of Policy Iteration in Stationary Dynamic Programming
• First-Order Methods in Optimization
• The Information Geometry of Mirror Descent
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: On linear and super-linear convergence of natural policy gradient algorithm