An unbounded Berge's minimum theorem with applications to discounted Markov decision processes

zbMATH Open1275.90124MaRDI QIDQ2907896FDOQ2907896

Authors: Raúl Montes-de-Oca, E. Lemus-Rodríguez 

Publication date: 4 September 2012

Published in: Kybernetika (Search for Journal in Brave)

Full work available at URL: https://eudml.org/doc/247030

Recommendations

• Discounted continuous-time Markov decision processes with unbounded rates: the convex analytic approach
• Discounted and average Markov decision processes with unbounded rewards: New conditions
• Fixed point theorems for discounted finite Markov decision processes
• scientific article; zbMATH DE number 1159486
• Constrained Markov decision processes in Borel spaces: from discounted to average optimality
• On undiscounted markovian decision processes with compact action spaces
• Discounted Continuous-Time Markov Decision Processes with Constraints: Unbounded Transition and Loss Rates
• scientific article; zbMATH DE number 1829768
• Finite-horizon optimality for continuous-time Markov decision processes with unbounded transition rates
• Continuous-Time Markov Decision Processes with Unbounded Transition and Discounted-Reward Rates

zbMATH Keywords

moment functiondiscounted Markov decision processcontinuous optimal policyBerge's minimum theoremuniqueness of the optimal policy

Mathematics Subject Classification ID

Sensitivity, stability, parametric optimization (90C31) Markov and semi-Markov decision processes (90C40) Optimal stochastic control (93E20)

Cites Work

• Transfer continuities, generalizations of the Weierstrass and maximum theorems: A full characterization
• Infinite dimensional analysis. A hitchhiker's guide.
• Title not available (Why is that?)
• Title not available (Why is that?)
• The maximum theorem and the existence of Nash equilibrium of (generalized) games without lower semicontinuities
• Berge's maximum theorem with two topologies on the action set
• Stochastic optimal growth with bounded or unbounded utility and with bounded or unbounded shocks
• Real analysis
• Title not available (Why is that?)
• A First Course in Optimization Theory
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Time-average control of martingale problems: A linear programming formulation
• The Continuity of Optimal Dynamic Decision Rules
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Ergodic Theorems for Discrete Time Stochastic Systems Using a Stochastic Lyapunov Function
• Title not available (Why is that?)
• Measurable selection theorems for optimization problems
• A nonsmooth, nonconvex model of optimal growth
• Lipschitz continuity of value functions in Markovian decision processes
• A generalized theorem of the maximum
• A Generalization of the Maximum Theorem
• Conditions for the uniqueness of optimal policies of discounted Markov decision processes
• Maximum theorems for convex structures with an application to the theory of optimal intertemporal allocation
• Stationary Optimal Policies with Discounting in a Stochastic Activity Analysis Model
• Blackwell Optimality in Borelian Continuous-in-Action Markov Decision Processes
• Parametric continuity in dynamic programming problems
• Title not available (Why is that?)
• Title not available (Why is that?)

Cited In (6)

• Berge's maximum theorem for noncompact image sets
• An envelope theorem and some applications to discounted Markov decision processes
• On the vanishing discount factor approach for Markov decision processes with weakly continuous transition probabilities
• A perturbation approach to approximate value iteration for average cost Markov decision processes with Borel spaces and bounded costs
• Uniqueness of optimal policies as a generic property of discounted Markov decision processes: Ekeland's variational principle approach.
• On the existence of relative values for undiscounted Markovian decision processes with a scalar gain rate

This page was built for publication: An unbounded Berge's minimum theorem with applications to discounted Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2907896)