Policy mirror descent inherently explores action space

DOI10.1137/23M1560215MaRDI QIDQ6663113zbMATH OpenFDO

Authors Yan Li, Guanghui Lan

Publication date 14 January 2025

Published in SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/23M1560215

zbMATH Keywords

explorationMarkov decision processmirror descentsample complexitystochastic policy gradient

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Stochastic programming (90C15) Nonconvex programming, global optimization (90C26) Markov and semi-Markov decision processes (90C40)

Cites work

• Asymptotically efficient adaptive allocation rules
• Block Policy Mirror Descent
• Fast global convergence of natural policy gradient methods with entropy regularization
• Finite-Sample Analysis of Two-Time-Scale Natural Actor–Critic Algorithm
• Homotopic policy mirror descent: policy convergence, algorithmic regularization, and improved sample complexity
• scientific article; zbMATH DE number 3790208 (Why is no real title available?)
• scientific article; zbMATH DE number 5685899 (Why is no real title available?)
• Markov chains and mixing times. With a chapter on ``Coupling from the past by James G. Propp and David B. Wilson.
• On average versus discounted reward temporal-difference learning
• Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence
• Policy mirror descent for reinforcement learning: linear convergence, new sampling complexity, and generalized problem classes
• Reinforcement learning with replacing eligibility traces
• Robust Stochastic Approximation Approach to Stochastic Programming
• Simple and optimal methods for stochastic variational inequalities. II: Markovian noise and policy evaluation in reinforcement learning
• The Nonstochastic Multiarmed Bandit Problem

Cited in

(1)

• Policy optimization over general state and action spaces

This page was built for publication: Policy mirror descent inherently explores action space

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6663113)