Robuta

https://openreview.net/forum?id=lXuZaxEaI7&referrer=%5Bthe%20profile%20of%20John%20Schulman%5D(%2Fprofile%3Fid%3D~John_Schulman1) Batch size-invariance for policy optimization | OpenReview We show how to make PPO batch size-invariant (changes to the batch size can largely be compensated for by changing other hyperparameters) by decoupling the... batch sizepolicy optimizationinvarianceopenreview