Action Elimination and Stopping Conditions for the Multi-Armed Bandit and Reinforcement Learning Problems
Shie Mannor and Eyal Even-Dar and Yishay Mansour


Send Feedback Start
   0.000005
DB Connect
   0.000573
Lookup hash in DB
   0.000502
Get torrent details
   0.000165
Get torrent details, finished
   0.000294
Get authors
   0.000001
Select authors
   0.000182
Parse bibtex
   0.000091
Write header
   0.000250
get stars
   0.000135
home tab
   0.000158
render right panel
   0.000006
render ads
   0.000450
fetch current hosters
   0.000297
related datasets
   0.001462
Done