User: Guest  Login
Document type:
Konferenzbeitrag 
Contribution type:
Textbeitrag / Aufsatz 
Author(s):
Meyer, Dominik; Shen, Hao; Diepold, Klaus 
Title:
L1 Regularized Gradient Temporal-Difference Learning 
Abstract:
The family of Gradient Temporal-Difference (GTD) learning algorithms shares a promising property of being stable with both linear function approximation and off-policy training. The success of the GTD family requires a suitable set of features, which are unfortunately not always available in reality. To overcome this difficulty, regularization is often employed as an effective method for feature selection in reinforcement learning. In the present work, we propose and investigate a family of L1...    »
 
Keywords:
Reinforcement Learning (RL); Gradient Temporal-Difference (GTD) learning; linear function approximation; Iterative Soft Thresholding (IST) 
Book / Congress title:
The 10th European Workshop on Reinforcement Learning (EWRL 2012) 
Year:
2012 
Year / month:
2012-07 
Month:
Jul 
Reviewed:
ja 
Language:
en