Finite Linear Programming Approximations of Constrained Discounted Markov Decision Processes
From MaRDI portal
Publication:2840138
DOI10.1137/120867925zbMath1282.90228OpenAlexW2092720955MaRDI QIDQ2840138
Tomás Prieto-Rumeau, François Dufour
Publication date: 17 July 2013
Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1137/120867925
quantizationconstrained Markov decision processesapproximation of Markov decision processeslinear programming approach to control problems
Related Items (17)
A convex optimization approach to dynamic programming in continuous state and action spaces ⋮ Computable approximations for continuous-time Markov decision processes on Borel spaces based on empirical measures ⋮ Nonasymptotic Analysis of Monte Carlo Tree Search ⋮ From Infinite to Finite Programs: Explicit Error Bounds with Applications to Approximate Dynamic Programming ⋮ Asymptotic optimality and rates of convergence of quantized stationary policies in continuous-time Markov decision processes ⋮ Near optimality of quantized policies in stochastic control under weak continuity conditions ⋮ Markov decision processes with burstiness constraints ⋮ Continuity of cost in Borkar control topology and implications on discrete space and time approximations for controlled diffusions under several criteria ⋮ An exact iterative search algorithm for constrained Markov decision processes ⋮ Light robustness in the optimization of Markov decision processes with uncertain parameters ⋮ Dual-based methods for solving infinite-horizon nonstationary deterministic dynamic programs ⋮ Computable approximations for average Markov decision processes in continuous time ⋮ Unnamed Item ⋮ Stochastic approximations of constrained discounted Markov decision processes ⋮ Approximation of average cost Markov decision processes using empirical distributions and concentration inequalities ⋮ First passage Markov decision processes with constraints and varying discount factors ⋮ A stability result for linear Markovian stochastic optimization problems
This page was built for publication: Finite Linear Programming Approximations of Constrained Discounted Markov Decision Processes
