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
   0.000004
DB Connect
   0.000333
Lookup hash in DB
   0.000636
Get torrent details
   0.000605
Get torrent details, finished
   0.000580
Get authors
   0.000006
Select authors
   0.000482
Parse bibtex
   0.000119
Write header
   0.000525
get stars
   0.000469
home tab
   0.000390
render right panel
   0.000033
render ads
   0.000068
fetch current hosters
   0.000605
Done