Stabilization of stochastic approximation by step size adaptation

DOI10.1016/j.sysconle.2012.02.005zbMath1250.93128arXiv1007.4689MaRDI QIDQ450652

Sameer Kamal

Publication date: 14 September 2012

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

Full work available at URL: https://arxiv.org/abs/1007.4689

zbMATH Keywords

stochastic approximation; almost sure boundedness; limiting ordinary differential equation; step size adaptation

Mathematics Subject Classification ID

60H10: Stochastic ordinary differential equations (aspects of stochastic analysis)

93E15: Stochastic stability in control theory

Related Items

Unnamed Item, Markovian stochastic approximation with expanding projections, Convergence of Markovian Stochastic Approximation with Discontinuous Dynamics

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stochastic approximation methods for constrained and unconstrained systems
• Asynchronous stochastic approximation and Q-learning
• Two models for analyzing the dynamics of adaptation algorithms
• Stochastic approximation and its applications
• Analysis of recursive stochastic algorithms
• A Scaled Stochastic Approximation Algorithm
• OnActor-Critic Algorithms
• Stochastic Approximation for Nonexpansive Maps: Application to Q-Learning Algorithms
• A Stochastic Approximation Algorithm with Varying Bounds
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
• Stability of Stochastic Approximation under Verifiable Conditions
• A Stochastic Approximation Method