Analyzing Approximate Value Iteration Algorithms

DOI10.1287/MOOR.2021.1202zbMath1501.90106arXiv1709.04673OpenAlexW4206456530MaRDI QIDQ5868951

Shalabh Bhatnagar, Arunselvan Ramaswamy

Publication date: 26 September 2022

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

Full work available at URL: https://arxiv.org/abs/1709.04673

zbMATH Keywords

approximate value iterationdynamical systems viewpointfixed-point theory for set-valued functionsLyapunov function-based stabilityset-valued stochastic approximation algorithms

Mathematics Subject Classification ID

Dynamic programming (90C39) Set-valued operators (47H04) Stochastic approximation (62L20) Markov and semi-Markov decision processes (90C40)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stochastic approximation. A dynamical systems viewpoint.
• Stochastic approximation with two time scales
• On the existence of fixed points for approximate value iteration and temporal-difference learning
• Asymptotic pseudotrajectories and chain recurrent flows, with applications
• Multi-valued contraction mappings
• Stochastic Approximation for Nonexpansive Maps: Application to Q-Learning Algorithms
• A Dynamical System Approach to Stochastic Approximations
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
• Stochastic Approximations and Differential Inclusions
• A Generalization of the Borkar-Meyn Theorem for Stochastic Recursive Inclusions
• A Stochastic Approximation Method

This page was built for publication: Analyzing Approximate Value Iteration Algorithms