Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes
Sridhar Mahadevan and Mauro Maggioni

No comments yet

Add a comment

Report
Send Feedback Start
   0.000007
DB Connect
   0.000646
Lookup hash in DB
   0.000831
Get torrent details
   0.000265
Get torrent details, finished
   0.000507
Get authors
   0.000001
Select authors
   0.000343
Parse bibtex
   0.000044
Write header
   0.000342
get stars
   0.000206
comments tab
   0.000024
render right panel
   0.000004
render ads
   0.000551
fetch current hosters
   0.000463
Done