Publication:2907896
From MaRDI portal
zbMath1275.90124MaRDI QIDQ2907896
Enrique Lemus-Rodríguez, Raúl Montes-De-oca
Publication date: 4 September 2012
Full work available at URL: https://eudml.org/doc/247030
moment function; discounted Markov decision process; continuous optimal policy; Berge's minimum theorem; uniqueness of the optimal policy
90C31: Sensitivity, stability, parametric optimization
93E20: Optimal stochastic control
90C40: Markov and semi-Markov decision processes
Related Items
A perturbation approach to approximate value iteration for average cost Markov decision processes with Borel spaces and bounded costs, On the vanishing discount factor approach for Markov decision processes with weakly continuous transition probabilities, Berge's maximum theorem for noncompact image sets
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Lipschitz continuity of value functions in Markovian decision processes
- A nonsmooth, nonconvex model of optimal growth
- Time-average control of martingale problems: A linear programming formulation
- The maximum theorem and the existence of Nash equilibrium of (generalized) games without lower semicontinuities
- Measurable selection theorems for optimization problems
- Berge's maximum theorem with two topologies on the action set
- A generalized theorem of the maximum
- Transfer continuities, generalizations of the Weierstrass and maximum theorems: A full characterization
- Maximum theorems for convex structures with an application to the theory of optimal intertemporal allocation
- Conditions for the uniqueness of optimal policies of discounted Markov decision processes
- Stochastic optimal growth with bounded or unbounded utility and with bounded or unbounded shocks
- Stationary Optimal Policies with Discounting in a Stochastic Activity Analysis Model
- The Continuity of Optimal Dynamic Decision Rules
- A Generalization of the Maximum Theorem
- A First Course in Optimization Theory
- Blackwell Optimality in Borelian Continuous-in-Action Markov Decision Processes
- Ergodic Theorems for Discrete Time Stochastic Systems Using a Stochastic Lyapunov Function
- Parametric continuity in dynamic programming problems
