Q-Learning with Continuous State Spaces and Finite Decision Set

This paper aims to present an original technique in order to compute the optimal policy of a Markov decision problem with continuous state space and discrete decision variables. We propose an extension of the Q-learning algorithm introduced in 1989 by Watkins for discrete Markov decision problems. O...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Barty, K., Girardeau, P., Roy, J.-S., Strugarek, C.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Approximation algorithms Costs Dynamic programming Kernel Learning Random variables Recursive estimation State-space methods Stochastic processes Uncertainty
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!