Computable approximations for continuous-time Markov decision processes on Borel spaces based on empirical measures

DOI10.1016/j.jmaa.2016.05.055zbMath1338.93397OpenAlexW2414220426MaRDI QIDQ302091

Tomás Prieto-Rumeau, Jonatha Anselmi, François Dufour

Publication date: 4 July 2016

Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jmaa.2016.05.055

zbMATH Keywords

\(\epsilon\)-optimal policyapproximation of the optimal value functioncontinuous-time Markov decision processespiecewise Lipschitz continuous control models

Mathematics Subject Classification ID

Continuous-time Markov processes on general state spaces (60J25) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)

Related Items

Convergence of Finite Element Methods for Singular Stochastic Control ⋮ Continuous-time constrained stochastic games with average criteria ⋮ Approximation of discounted minimax Markov control problems and zero-sum Markov games using Hausdorff and Wasserstein distances ⋮ Computable approximations for average Markov decision processes in continuous time

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Convergence of controlled models and finite-state approximation for discounted continuous-time Markov decision processes with constraints
• Simple bounds for the convergence of empirical and occupation measures in 1-Wasserstein distance
• Discounted continuous-time Markov decision processes with unbounded rates and randomized history-dependent policies: the dynamic programming approach
• Calcul stochastique et problèmes de martingales
• Simulation-based algorithms for Markov decision processes.
• Adaptive Markov control processes
• Stochastic approximations of constrained discounted Markov decision processes
• Finite Linear Programming Approximations of Constrained Discounted Markov Decision Processes
• Approximate Iterative Algorithms
• Asymptotic Optimality and Rates of Convergence of Quantized Stationary Policies in Stochastic Control
• Selected Topics on Continuous-Time Controlled Markov Chains and Markov Games
• Discounted Continuous-Time Markov Decision Processes with Unbounded Rates: The Convex Analytic Approach
• Convergence of Dynamic Programming Models
• An optimal one-way multigrid algorithm for discrete-time stochastic control
• Convergence of discretization procedures in dynamic programming
• Approximations of Dynamic Programs, I
• Discounted Continuous-Time Controlled Markov Chains: Convergence of Control Models
• Approximating Ergodic Average Reward Continuous-Time Controlled Markov Chains
• Approximation of average cost Markov decision processes using empirical distributions and concentration inequalities
• Approximate Dynamic Programming