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

Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes.pdf1.34MB
Type: Paper
Tags:

Bibtex: 
@article{8:74,author={Sridhar Mahadevan and Mauro Maggioni}, Title={Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes},journal={Journal of Machine Learning Research},volume={8}, url={http://www.jmlr.org/papers/volume8/mahadevan07a/mahadevan07a.pdf}}
Report
Send Feedback Start
   0.000006
DB Connect
   0.000485
Lookup hash in DB
   0.000829
Get torrent details
   0.000688
Get torrent details, finished
   0.000652
Get authors
   0.000005
Select authors
   0.000518
Parse bibtex
   0.000121
Write header
   0.000665
get stars
   0.000471
home tab
   0.000567
render right panel
   0.000030
render ads
   0.000066
fetch current hosters
   0.000599
Done