A perturbation approach to approximate value iteration for average cost Markov decision processes with Borel spaces and bounded costs.

DOI10.14736/KYB-2019-1-0081zbMATH Open1449.90356OpenAlexW2921102909MaRDI QIDQ5227201FDOQ5227201

Authors: Óscar Vega-Amaya, Joaquín López-Borbón 

Publication date: 5 August 2019

Published in: Kybernetika (Search for Journal in Brave)

Full work available at URL: http://hdl.handle.net/10338.dmlcz/147707

Recommendations

• A perturbation approach to a class of discounted approximate value iteration algorithms with Borel spaces
• Value iteration for average cost Markov decision processes in Borel spaces
• Estimate and approximate policy iteration algorithm for discounted Markov decision models with bounded costs and Borel spaces
• Policy iteration for average cost Markov control processes on Borel spaces
• Value Iteration in a Class of Communicating Markov Decision Chains with the Average Cost Criterion

zbMATH Keywords

Markov decision processesapproximate value iteration algorithmaverage cost criterioncontraction and non-expansive operatorsperturbed Markov decision 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

• Markov chains and stochastic stability
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Infinite dimensional analysis. A hitchhiker's guide.
• A note on a variation of Doeblin's condition for uniform ergodicity of Markov chains
• Title not available (Why is that?)
• Title not available (Why is that?)
• 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
• OnActor-Critic Algorithms
• Title not available (Why is that?)
• Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
• Title not available (Why is that?)
• Stochastic approximations of constrained discounted Markov decision processes
• Title not available (Why is that?)
• Approximation of average cost Markov decision processes using empirical distributions and concentration inequalities
• Learning algorithms for Markov decision processes with average cost
• Approximation of Markov decision processes with general state space
• Pseudometrics for State Aggregation in Average Reward Markov Decision Processes
• What you should know about approximate dynamic programming
• CONVERGENCE OF SIMULATION-BASED POLICY ITERATION
• Application of average dynamic programming to inventory systems
• On the existence of fixed points for approximate value iteration and temporal-difference learning
• Estimate and approximate policy iteration algorithm for discounted Markov decision models with bounded costs and Borel spaces
• A perturbation approach to a class of discounted approximate value iteration algorithms with Borel spaces
• Perspectives of approximate dynamic programming
• Approximate Fixed Point Iteration with an Application to Infinite Horizon 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
• Zero-Sum Average Semi-Markov Games: Fixed-Point Solutions of the Shapley Equation
• Markov chains and invariant probabilities
• Analysis of a Numerical Dynamic Programming Algorithm Applied to Economic Models
• Approximate receding horizon approach for Markov decision processes: average reward case
• A Cost-Shaping Linear Program for Average-Cost Approximate Dynamic Programming with Performance Guarantees
• Recurrence conditions for Markov decision processes with Borel state space: A survey
• On the optimality equation for average cost Markov control processes with Feller transition probabilities
• Simulation-based algorithms for Markov decision processes
• On the asymptotic optimality of finite approximations to Markov decision processes with Borel spaces
• The average cost optimality equation: a fixed point approach
• Discretization procedures for adaptive Markov control processes
• Convergence Properties of Policy Iteration
• A reinforcement learning algorithm based on policy iteration for average reward: Empirical results with yield management and convergence analysis
• A generalization of Ueno's inequality for n-step transition probabilities
• Sample-Path Optimality and Variance-Minimization of Average Cost Markov Control Processes
• An unbounded Berge's minimum theorem with applications to discounted Markov decision processes
• Solutions of the average cost optimality equation for Markov decision processes with weakly continuous kernel: the fixed-point approach revisited

Cited In (6)

• Estimate and approximate policy iteration algorithm for discounted Markov decision models with bounded costs and Borel spaces
• Analyzing approximate value iteration algorithms
• A perturbation approach to a class of discounted approximate value iteration algorithms with Borel spaces
• Performance Bounds in $L_p$‐norm for Approximate Value Iteration
• Value iteration in average cost Markov control processes on Borel spaces
• Value iteration for average cost Markov decision processes in Borel spaces

This page was built for publication: A perturbation approach to approximate value iteration for average cost Markov decision processes with Borel spaces and bounded costs.

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5227201)