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
   0.001018
Lookup hash in DB
   0.001042
Get torrent details
   0.000431
Get torrent details, finished
   0.000671
Get authors
   0.000001
Select authors
   0.000447
Parse bibtex
   0.000051
Write header
   0.000632
get stars
   0.000266
home tab
   0.000277
render right panel
   0.000009
render ads
   0.000970
fetch current hosters
   0.001063
Done