Equivalence of Lyapunov stability criteria in a class of Markov decision processes
From MaRDI portal
Publication:1194209
DOI10.1007/BF01189027zbMath0766.90082MaRDI QIDQ1194209
Rolando Cavazos-Cadena, Onésimo Hernández-Lerma
Publication date: 27 September 1992
Published in: Applied Mathematics and Optimization (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/bf01189027
countable state space; discrete time average reward Markov decision processes; Lyapunov stability criteria
93D05: Lyapunov and other classical stabilities (Lagrange, Poisson, (L^p, l^p), etc.) in control theory
90C40: Markov and semi-Markov decision processes
Related Items
Controlled Markov processes on the infinite planning horizon: Weighted and overtaking cost criteria, Denumerable controlled Markov chains with average reward criterion: Sample path optimality, A note on the vanishing interest rate approach in average Markov decision chains with continuous and bounded costs, A pause control approach to the value iteration scheme in average Markov decision processes, Approximation of average cost optimal policies for general Markov decision processes with unbounded costs, Antisideslip and antirollover safety speed controller design for vehicle on curved road, Solutions of the average cost optimality equation for Markov decision processes with weakly continuous kernel: the fixed-point approach revisited, Continuity of the optimal average cost in Markov decision chains with small risk-sensitivity, Discrete-time zero-sum games for Markov chains with risk-sensitive average cost criterion, Sample-Path Optimal Stationary Policies in Stable Markov Decision Chains with the Average Reward Criterion
Cites Work
- Existence of optimal stationary policies in average reward Markov decision processes with a recurrent state
- Adaptive Markov control processes
- The average-optimal adaptive control of a Markov renewal model in presence of an unknown parameter
- On the Stochastic Matrices Associated with Certain Queuing Processes
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item