User: Guest  Login
Document type:
Konferenzbeitrag 
Contribution type:
Textbeitrag / Aufsatz 
Author(s):
Meyer, Dominik; Degenne, Remy; Omrane, Ahmed; Shen, Hao 
Title:
Accelerated Gradient Temporal Difference Learning Algorithms 
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....    »
 
Book / Congress title:
Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), 2014 IEEE Symposium on 
Date of congress:
9-12 Dec. 2014 
Year:
2014 
Quarter:
4. Quartal 
Year / month:
2014-12 
Month:
Dec 
Pages:
Reviewed:
ja 
Language:
en 
Publication format:
WWW