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


Send Feedback Start
   0.000006
DB Connect
   0.000446
Lookup hash in DB
   0.000628
Get torrent details
   0.000582
Get torrent details, finished
   0.000581
Get authors
   0.000006
Select authors
   0.000404
Parse bibtex
   0.000128
Write header
   0.000597
get stars
   0.000374
comments tab
   0.000033
home tab
   0.000405
render right panel
   0.000030
render ads
   0.000077
fetch current hosters
   0.000687
Done