Benutzer: Gast  Login
Titel:

Accelerated Gradient Temporal Difference Learning Algorithms

Dokumenttyp:
Konferenzbeitrag
Art des Konferenzbeitrags:
Textbeitrag / Aufsatz
Autor(en):
Meyer, Dominik; Degenne, Remy; Omrane, Ahmed; Shen, Hao
Abstract:
In this paper we study Temporal Difference (TD) Learning with linear value function approximation. The classic TD algorithm is known to be unstable with linear function approximation and off-policy learning. Recently developed Gradient TD (GTD) algorithms have addressed this problem successfully. Despite their prominent properties of good scalability and convergence to correct solutions, they inherit the potential weakness of slow convergence as they are a stochastic gradient descent algorithm....     »
Kongress- / Buchtitel:
Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), 2014 IEEE Symposium on
Datum der Konferenz:
9-12 Dec. 2014
Jahr:
2014
Quartal:
4. Quartal
Jahr / Monat:
2014-12
Monat:
Dec
Seiten:
8
Reviewed:
ja
Sprache:
en
Erscheinungsform:
WWW
Volltext / DOI:
doi:http://dx.doi.org/10.1109/ADPRL.2014.7010611
WWW:
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7010611
 BibTeX