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}}
Compute download stats
Related Torrents
Report
Send Feedback Start
   0.000008
DB Connect
   0.000663
Lookup hash in DB
   0.000703
Get torrent details
   0.000329
Get torrent details, finished
   0.000337
Get authors
   0.000001
Select authors
   0.000222
Parse bibtex
   0.000047
Write header
   0.000286
get stars
   0.000154
home tab
   0.000136
render right panel
   0.000018
render ads
   0.000440
fetch current hosters
   0.000268
related datasets
   0.002327
Done