DocumentCode :
2717091
Title :
Knowledge Transfer Using Local Features
Author :
Stolle, Martin ; Atkeson, Christopher G.
Author_Institution :
Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA
fYear :
2007
fDate :
1-5 April 2007
Firstpage :
26
Lastpage :
31
Abstract :
We present a method for reducing the effort required to compute policies for tasks based on solutions to previously solved tasks. The key idea is to use a learned intermediate policy based on local features to create an initial policy for the new task. In order to further improve this initial policy, we developed a form of generalized policy iteration. We achieve a substantial reduction in computation needed to find policies when previous experience is available
Keywords :
iterative methods; knowledge based systems; generalized policy iteration; knowledge transfer; local features; policies computing; Artificial intelligence; Automatic control; Dynamic programming; Knowledge transfer; Learning; Legged locomotion; Navigation; Robots; Strips;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Approximate Dynamic Programming and Reinforcement Learning, 2007. ADPRL 2007. IEEE International Symposium on
Conference_Location :
Honolulu, HI
Print_ISBN :
1-4244-0706-0
Type :
conf
DOI :
10.1109/ADPRL.2007.368165
Filename :
4220810
Link To Document :
بازگشت