Skip to content

TensorFlow Agents 1.2.0

Compare
Choose a tag to compare
@danijar danijar released this 13 Nov 20:51
· 39 commits to master since this release

Features:

  • Use single optimizer for PPO to train shared feature layers better.
  • Allow calling methods of the process environment.

Improvements:

  • Improve default and MuJoCo configs.
  • Report both training and evaluation scores.

Bugs:

  • Likelihood calculation halved gradients for the action standard deviation.