Perturbation and stability theory for Markov control problems
From MaRDI portal
Publication:4021215
DOI10.1109/9.159584zbMath0763.90091OpenAlexW2102773314MaRDI QIDQ4021215
Mohammed Abbad, Jerzy A. Filar
Publication date: 16 January 1993
Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)
Full work available at URL: http://hdl.handle.net/2328/26296
Lyapunov and other classical stabilities (Lagrange, Poisson, (L^p, l^p), etc.) in control theory (93D05) Markov and semi-Markov decision processes (90C40)
Related Items (10)
Approximation of average cost optimal policies for general Markov decision processes with unbounded costs ⋮ Bounding fixed points of set-based Bellman operator and Nash equilibria of stochastic games ⋮ Robustness inequality for Markov control processes with unbounded costs ⋮ Uncertainty quantification for Markov chain models ⋮ Time scale decomposition in production planning for unreliable flexible manufacturing systems ⋮ Estimation of the Optimality Deviation in Discounted Semi-Markov Control Models ⋮ Distributionally Robust Partially Observable Markov Decision Process with Moment-Based Ambiguity ⋮ Cesaro limits of analytically perturbed stochastic matrices ⋮ A two-factor stochastic production model with two time scales ⋮ Weighted discounted Markov decision processes with perturbation
This page was built for publication: Perturbation and stability theory for Markov control problems
