Ryo IWAKI


Incremental Estimation of Natural Policy Gradient with Relative Importance Weighting
Ryo IWAKI Hiroki YOKOYAMA Minoru ASADA 
Publication:   
Publication Date: 2018/09/01
Vol. E101-D  No. 9  pp. 2346-2355
Type of Manuscript:  PAPER
Category: Artificial Intelligence, Data Mining
Keyword: 
reinforcement learningnatural policy gradientadaptive step size
 Summary | Full Text:PDF(3.1MB)