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:

Metadata: 
@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}}
Citation:
Mahadevan, S. & Maggioni, M.. (2014). Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes [Data set]. Academic Torrents. https://academictorrents.com/details/cca65715cb31b53876c27c0f4ddcd2be9ad7036a
Compute download stats
Related Torrents
Report
Send Feedback Start
   0.000008
DB Connect
   0.000560
Lookup hash in DB
   0.000480
Get torrent details
   0.000138
Get torrent details, finished
   0.000286
Get authors
   0.000000
Select authors
   0.000226
Parse bibtex
   0.000120
Write header
   0.000286
get stars
   0.000129
home tab
   0.000128
render right panel
   0.000006
render ads
   0.000504
fetch current hosters
   0.000281
related datasets
   0.002291
Done