Title :
Simulation-based optimization of Markov reward processes
Author :
Marbach, Peter ; Tsitsiklis, John N.
Author_Institution :
Lab. for Inf. & Decision Syst., MIT, Cambridge, MA, USA
Abstract :
We propose a simulation-based algorithm for optimizing the average reward in a Markov reward process that depends on a set of parameters. As a special case, the method applies to Markov decision processes where optimization takes place within a parametrized set of policies. The algorithm involves the simulation of a single sample path, and can be implemented online. A convergence result (with probability 1) is provided
Keywords :
Markov processes; convergence of numerical methods; decision theory; management science; optimisation; probability; state-space methods; Markov decision process; Markov reward processes; convergence; optimization; probability; simulation; state space; Computational modeling; Convergence; Decision making; Dynamic programming; Laboratories; Measurement; Optimization methods; State-space methods; Uncertainty;
Conference_Titel :
Decision and Control, 1998. Proceedings of the 37th IEEE Conference on
Conference_Location :
Tampa, FL
Print_ISBN :
0-7803-4394-8
DOI :
10.1109/CDC.1998.757861
