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}}
No stats to report yet.
Related Torrents
Report
Send Feedback Start
   0.000008
DB Connect
   0.000472
Lookup hash in DB
   0.000374
Get torrent details
   0.000110
Get torrent details, finished
   0.000193
Get authors
   0.000001
Select authors
   0.000216
Parse bibtex
   0.000032
Write header
   0.000194
get stars
   0.000090
home tab
   0.000087
render right panel
   0.000008
render ads
   0.000336
fetch current hosters
   0.000217
Start get stats
   0.000921
End get stats
   0.000001
related datasets
   0.002894
Done