Investigate super-convergence on RL algorithms about rlkit HOT 4 OPEN

Thanks for the post! I'm a bit unsure what you are asking. Are you asking that others or I try this out, or merge this code in? Or were you asking for feedback?

Also, if you have example plots for the performance of this on specific environments, it would help.

from rlkit.

I don't do research, there is probably a lot of things to do to achieve something worth publishing. Just letting you know that it shows promising result in my limited trials. So this is kind of an observation

from rlkit.

from rlkit.

Sorry, I would really like but I am under NDA for this stuff. What I can say (which is general enough) is that even though the source data is very difficult to make it converge using general methods (in the supervised case too); with super convergence effects I was able to steer the policy quite rapidly (in the same way I am able to do on the supervised case). I am training supervised neural networks in under 100 minutes what it took multiple days 6 months ago to the same accuracy.

from rlkit.