Robustness inequality for Markov control processes with unbounded costs
From MaRDI portal
Publication:1128542
DOI10.1016/S0167-6911(97)00077-7zbMath0902.93068MaRDI QIDQ1128542
Evgueni I. Gordienko, Francisco S. Salem
Publication date: 13 August 1998
Published in: Systems \& Control Letters (Search for Journal in Brave)
robustnessstability indexoptimal policiesdiscounted cost criterionMarkov control processesdiscrete-time processes
Sensitivity (robustness) (93B35) Discrete-time control/observation systems (93C55) Optimal stochastic control (93E20)
Related Items (11)
Unnamed Item ⋮ Estimation of the Optimality Deviation in Discounted Semi-Markov Control Models ⋮ Discounted cost optimality problem: Stability with respect to weak metrics ⋮ Unnamed Item ⋮ Unnamed Item ⋮ A note on deterministic approximation of discounted Markov decision processes ⋮ Unnamed Item ⋮ Limiting optimal discounted-cost control of a class of time-varying stochastic systems ⋮ A robustness result for stochastic control ⋮ Stability estimation of some Markov controlled processes ⋮ Partially observable Markov decision processes with partially observable random discount factors
Cites Work
- Unnamed Item
- Unnamed Item
- An estimate of the stability of optimal control of certain stochastic and deterministic systems
- Stochastic optimal control. The discrete time case
- Markov programming by successive approximations with respect to weighted supremum norms
- Measurable selection theorems for optimization problems
- Value iteration and rolling plans for Markov control processes with unbounded rewards
- Adaptive Markov control processes
- Perturbation theory for unbounded Markov reward processes with applications to queueing
- Perturbation theory for Markov reward processes with applications to queueing systems
- Perturbation and stability theory for Markov control problems
- On Dynamic Programming with Unbounded Rewards
- Note—A Note on Dynamic Programming with Unbounded Rewards
- Approximations of Dynamic Programs, I
- Average cost Markov control processes with weighted norms: existence of canonical policies
- Average cost Markov control processes with weighted norms: value iteration
This page was built for publication: Robustness inequality for Markov control processes with unbounded costs
