A perturbation approach to a class of discounted approximate value iteration algorithms with Borel spaces

DOI10.3934/JDG.2016014zbMATH Open1346.93402OpenAlexW2507723477MaRDI QIDQ330284FDOQ330284

Authors: Óscar Vega-Amaya, Joaquín López-Borbón 

Publication date: 25 October 2016

Published in: Journal of Dynamics and Games (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.3934/jdg.2016014

Recommendations

• A perturbation approach to approximate value iteration for average cost Markov decision processes with Borel spaces and bounded costs.
• Estimate and approximate policy iteration algorithm for discounted Markov decision models with bounded costs and Borel spaces
• Complexity bounds for approximately solving discounted MDPs by value iterations
• Value iteration for average cost Markov decision processes in Borel spaces
• Value iteration in average cost Markov control processes on Borel spaces
• On the existence of fixed points for approximate value iteration and temporal-difference learning
• The convergence of value iteration in discounted Markov decision processes
• scientific article; zbMATH DE number 4003938

zbMATH Keywords

Markov decision processesdiscounted criterionapproximate value iteration algorithmperturbed models

Mathematics Subject Classification ID

Approximation methods and heuristics in mathematical programming (90C59) Markov and semi-Markov decision processes (90C40) Optimal stochastic control (93E20)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Adaptive Markov control processes
• A survey of Markov decision models for control of networks of queues
• A Survey of Applications of Markov Decision Processes
• Approximate Dynamic Programming
• The approximation of continuous functions by positive linear operators
• Approximate policy iteration: a survey and some new methods
• A review of stochastic algorithms with continuous value function approximation and some new approximate policy iteration algorithms for multidimensional continuous applications
• Title not available (Why is that?)
• Approximate dynamic programming via direct search in the space of value function approximations
• Application of average dynamic programming to inventory systems
• On the existence of fixed points for approximate value iteration and temporal-difference learning
• An approximate dynamic programming algorithm for monotone value functions
• Perspectives of approximate dynamic programming
• Approximate Fixed Point Iteration with an Application to Infinite Horizon Markov Decision Processes
• Approximation of infinite horizon discounted cost Markov decision processes
• Performance Loss Bounds for Approximate Value Iteration with State Aggregation
• Performance Bounds in $L_p$‐norm for Approximate Value Iteration
• Continuous state dynamic programming via nonexpansive approximation

Cited In (7)

• Approximation of discounted minimax Markov control problems and zero-sum Markov games using Hausdorff and Wasserstein distances
• Estimate and approximate policy iteration algorithm for discounted Markov decision models with bounded costs and Borel spaces
• Approximate dynamic programming via direct search in the space of value function approximations
• Analyzing approximate value iteration algorithms
• A perturbation approach to approximate value iteration for average cost Markov decision processes with Borel spaces and bounded costs
• Performance Loss Bounds for Approximate Value Iteration with State Aggregation
• Performance Bounds in $L_p$‐norm for Approximate Value Iteration

This page was built for publication: A perturbation approach to a class of discounted approximate value iteration algorithms with Borel spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q330284)