l AVERAGE COST SEMI - MARKOV DECISION PROCESSES
نویسندگان
چکیده
^ The Semi-Markov Decision model is considered under the criterion of long-run average cost. A new criterion, which for any policy considers the limit of the expected cost Incurred during the first n transitions divided by the expected length of the first n transitions, is considered. Conditions guaranteeing that an optimal stationary (nonrandomized) policy exist are then presented. It is also shown that the above criterion is equivalent to the usual one under certain conditions. rAVERAGE COST SEMI-MARKOV DECISION PROCESSES by Sheldon M. Ross
منابع مشابه
Optimality Inequalities for Average Cost Markov Decision Processes and the Stochastic Cash Balance Problem
For general state and action space Markov decision processes, we present sufficient conditions for the existence of solutions of the average cost optimality inequalities. These conditions also imply the convergence of both the optimal discounted cost value function and policies to the corresponding objects for the average costs per unit time case. Inventory models are natural applications of ou...
متن کاملSemi-markov Decision Processes and Their Applications in Replacement Models
We consider the problem of minimizing the long-run average expected cost per unit time in a semiMarkov decision process with arbitrary state and action space. Using the idea of successive approximations, sufficient conditions for the existence of an optimal stationary policy are given. These results are applied to solve the replacement problem with a semi-Markov shock model.
متن کاملSemi-Markov decision problems and performance sensitivity analysis
Recent research indicates that Markov decision processes (MDPs) can be viewed from a sensitivity point of view; and perturbation analysis (PA), MDPs, and reinforcement learning (RL) are three closely related areas in optimization of discrete-event dynamic systems that can be modeled as Markov processes. The goal of this paper is two-fold. First, we develop PA theory for semi-Markov processes (S...
متن کاملTime and Ratio Expected Average Cost Optimality for Semi-Markov Control Processes on Borel Spaces
We deal with semi-Markov control models with Borel state and control spaces, and unbounded cost functions under the ratio and the time expected average cost criteria. Under suitable growth conditions on the costs and the mean holding times together with stability conditions on the embedded Markov chains, we show the following facts: (i) the ratio and the time average costs coincide in the class...
متن کاملSemi-markov Decision including an Unknown
SEMI-MARKOV DECISION INCLUDING AN UNKNOWN Masami Kurano Chiba University PROCESSES PARAMETER (Received February 27, 1984: Revised May 8,1985) We consider the problem of minimizing the long-run average (expected) cost per unit time in a semiMarkov decision process including an unknown parameter. In the case of general state and action spaces and compact parameter space we construct the adaptive ...
متن کامل