Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning
Peter L. Bartlett and Evan Greensmith and Jonathan Baxter

No comments yet

Add a comment

Report
Send Feedback Start
   0.000012
DB Connect
   0.001167
Lookup hash in DB
   0.001185
Get torrent details
   0.000383
Get torrent details, finished
   0.000728
Get authors
   0.000001
Select authors
   0.000537
Parse bibtex
   0.000060
Write header
   0.000492
get stars
   0.000329
comments tab
   0.000048
render right panel
   0.000007
render ads
   0.001234
fetch current hosters
   0.001091
Done