Closed nottombrown closed 6 years ago
Previously we were training off of slices of our episode data, which were changing beneath us
See change in loss here:
Previously we were training off of slices of our episode data, which were changing beneath us
See change in loss here:![image](https://user-images.githubusercontent.com/306655/28851122-75f2edb0-76d5-11e7-8ef8-7d5c00673ab6.png)