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

DOI10.14736/kyb-2019-1-0081zbMath1449.90356OpenAlexW2921102909MaRDI QIDQ5227201

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

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) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A perturbation approach to a class of discounted approximate value iteration algorithms with Borel spaces
• Perspectives of approximate dynamic programming
• Approximation of Markov decision processes with general state space
• Markov chains and stochastic stability
• On the optimality equation for average cost Markov control processes with Feller transition probabilities
• Continuous state dynamic programming via nonexpansive approximation
• Discretization procedures for adaptive Markov control processes
• Application of average dynamic programming to inventory systems
• The approximation of continuous functions by positive linear operators
• Approximate receding horizon approach for Markov decision processes: average reward case
• The average cost optimality equation: a fixed point approach
• On the existence of fixed points for approximate value iteration and temporal-difference learning
• Solutions of the average cost optimality equation for Markov decision processes with weakly continuous kernel: the fixed-point approach revisited
• A reinforcement learning algorithm based on policy iteration for average reward: Empirical results with yield management and convergence analysis
• Markov chains and invariant probabilities
• Simulation-based algorithms for Markov decision processes
• Stochastic approximations of constrained discounted Markov decision processes
• A note on a variation of Doeblin's condition for uniform ergodicity of Markov chains
• Recurrence conditions for Markov decision processes with Borel state space: A survey
• Learning Algorithms for Markov Decision Processes with Average Cost
• 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
• Estimate and approximate policy iteration algorithm for discounted Markov decision models with bounded costs and Borel spaces
• Approximate Fixed Point Iteration with an Application to Infinite Horizon Markov Decision Processes
• Pseudometrics for State Aggregation in Average Reward Markov Decision Processes
• What you should know about approximate dynamic programming
• OnActor-Critic Algorithms
• Zero-Sum Average Semi-Markov Games: Fixed-Point Solutions of the Shapley Equation
• CONVERGENCE OF SIMULATION-BASED POLICY ITERATION
• Analysis of a Numerical Dynamic Programming Algorithm Applied to Economic Models
• A generalization of Ueno's inequality for n-step transition probabilities
• On the Asymptotic Optimality of Finite Approximations to Markov Decision Processes with Borel Spaces
• Convergence Properties of Policy Iteration
• Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
• Sample-Path Optimality and Variance-Minimization of Average Cost Markov Control Processes
• Approximation of average cost Markov decision processes using empirical distributions and concentration inequalities
• Approximate Dynamic Programming
• Performance Loss Bounds for Approximate Value Iteration with State Aggregation
• A Cost-Shaping Linear Program for Average-Cost Approximate Dynamic Programming with Performance Guarantees
• Performance Bounds in $L_p$‐norm for Approximate Value Iteration

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