Title :
Asymptotic analysis of temporal-difference learning algorithms with linear function approximation
Author_Institution :
Mihajlo Pupin Inst., Belgrade, Serbia
Abstract :
The asymptotic properties of temporal-difference learning algorithms with linear function approximation are analyzed in the paper. The analysis is carried out in the context of the approximation of a discounted cost-to-go function associated to an uncontrolled Markov chain with an uncountable finite-dimensional state-space.
Keywords :
"Algorithm design and analysis","Approximation algorithms","Function approximation","Convergence","Difference equations","Random variables"
Conference_Titel :
Decision and Control, 1999. Proceedings of the 38th IEEE Conference on
Print_ISBN :
0-7803-5250-5
DOI :
10.1109/CDC.1999.833350
