Finite-Time Analysis and Restarting Scheme for Linear Two-Time-Scale Stochastic Approximation

DOI10.1137/20M1322649zbMath1471.62444arXiv1912.10583OpenAlexW3184741403MaRDI QIDQ5009779

Thinh T. Doan

Publication date: 6 August 2021

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1912.10583

zbMATH Keywords

reinforcement learningtwo-time-scale stochastic approximation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Stochastic approximation (62L20)

Related Items (1)

Finite-time convergence rates of distributed local stochastic approximation

Uses Software

• ElemStatLearn

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Gradient sliding for composite optimization
• Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions
• Convergence rate and averaging of nonlinear two-time-scale stochastic approximation algo\-rithms
• Stochastic approximation. A dynamical systems viewpoint.
• Convergence rate of linear two-time-scale stochastic approximation.
• First-order and stochastic optimization methods for machine learning
• An actor-critic algorithm for constrained Markov decision processes
• Acceleration of Stochastic Approximation by Averaging
• OnActor-Critic Algorithms
• Optimization Methods for Large-Scale Machine Learning
• Finite-Time Performance of Distributed Temporal-Difference Learning with Linear Function Approximation
• A Finite Time Analysis of Temporal Difference Learning with Linear Function Approximation
• Convergence Rates of Distributed Gradient Methods Under Random Quantization: A Stochastic Approximation Approach
• A Stochastic Approximation Method

This page was built for publication: Finite-Time Analysis and Restarting Scheme for Linear Two-Time-Scale Stochastic Approximation