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.pdf 1.34MB
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
   0.000010
DB Connect
   0.001021
Lookup hash in DB
   0.001189
Get torrent details
   0.000392
Get torrent details, finished
   0.000770
Get authors
   0.000002
Select authors
   0.000591
Parse bibtex
   0.000063
Write header
   0.000541
get stars
   0.000380
home tab
   0.000344
render right panel
   0.000007
render ads
   0.001384
fetch current hosters
   0.001008
Done