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
   0.000009
DB Connect
   0.001168
Lookup hash in DB
   0.001316
Get torrent details
   0.000461
Get torrent details, finished
   0.000798
Get authors
   0.000001
Select authors
   0.000566
Parse bibtex
   0.000054
Write header
   0.000533
get stars
   0.000460
home tab
   0.000372
render right panel
   0.000010
render ads
   0.001274
fetch current hosters
   0.001412
Done