Lebesgue-Sampling-Based Optimal Control Problems With Time Aggregation

We formulate the Lebesgue-sampling-based optimal control problem. We show that the problem can be solved by the time aggregation approach in Markov decision processes (MDP) theory. Policy-iteration-based and reinforcement-learning-based methods are developed for the optimal policies. Both analytical...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on automatic control 2011-05, Vol.56 (5), p.1097-1109
Hauptverfasser:	XU, Yan-Kai, CAO, Xi-Ren
Format:	Artikel
Sprache:	eng
Schlagworte:	Agglomeration Aggregation Algorithms Applied sciences Artificial intelligence Automatic control Boundary conditions Calculus of variations and optimal control Computer science control theory systems Cost function Decision theory. Utility theory Equations Exact sciences and technology Markov decision processes (MDPs) Markov processes Mathematical analysis Mathematical model Mathematics Operational research and scientific management Operational research. Management science Optimal control Optimization performance potentials Probability and statistics Probability theory and stochastic processes reinforcement learning Sampling Sciences and techniques of general use
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	We formulate the Lebesgue-sampling-based optimal control problem. We show that the problem can be solved by the time aggregation approach in Markov decision processes (MDP) theory. Policy-iteration-based and reinforcement-learning-based methods are developed for the optimal policies. Both analytical solutions and sample-path-based algorithms are given. Compared to the periodic-sampling scheme, the Lebesgue sampling scheme improves system performance.
ISSN:	0018-9286 1558-2523
DOI:	10.1109/TAC.2010.2073610