Displaying similar documents to “Stationary optimal process in discounted dynamic programming”

Stationary optimal policies in a class of multichain positive dynamic programs with finite state space and risk-sensitive criterion

Rolando Cavazos-Cadena, Raul Montes-de-Oca (2001)

Applicationes Mathematicae

Similarity:

This work concerns Markov decision processes with finite state space and compact action sets. The decision maker is supposed to have a constant-risk sensitivity coefficient, and a control policy is graded via the risk-sensitive expected total-reward criterion associated with nonnegative one-step rewards. Assuming that the optimal value function is finite, under mild continuity and compactness restrictions the following result is established: If the number of ergodic classes when a stationary...

Uniqueness of optimal policies as a generic property of discounted Markov decision processes: Ekeland's variational principle approach

R. Israel Ortega-Gutiérrez, Raúl Montes-de-Oca, Enrique Lemus-Rodríguez (2016)

Kybernetika

Similarity:

Many examples in optimization, ranging from Linear Programming to Markov Decision Processes (MDPs), present more than one optimal solution. The study of this non-uniqueness is of great mathematical interest. In this paper the authors show that in a specific family of discounted MDPs, non-uniqueness is a “fragile” property through Ekeland's Principle for each problem with at least two optimal policies; a perturbed model is produced with a unique optimal policy. This result not only supersedes...

Multiobjective De Novo Linear Programming

Petr Fiala (2011)

Acta Universitatis Palackianae Olomucensis. Facultas Rerum Naturalium. Mathematica

Similarity:

Mathematical programming under multiple objectives has emerged as a powerful tool to assist in the process of searching for decisions which best satisfy a multitude of conflicting objectives. In multiobjective linear programming problems it is usually impossible to optimize all objectives in a given system. Trade-offs are properties of inadequately designed system a thus can be eliminated through designing better one. Multiobjective De Novo linear programming is problem for designing...