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
   0.000004
DB Connect
   0.000465
Lookup hash in DB
   0.001316
Get torrent details
   0.000430
Get torrent details, finished
   0.000827
Get authors
   0.000002
Select authors
   0.000498
Parse bibtex
   0.000062
Write header
   0.000541
get stars
   0.000466
home tab
   0.000370
render right panel
   0.000007
render ads
   0.000032
fetch current hosters
   0.000522
Done