nottombrown / rl-teacher

Code for Deep RL from Human Preferences [Christiano et al]. Plus a webapp for collecting human feedback
MIT License
556 stars 93 forks source link

Logging edge case errors #17

Closed Raelifin closed 6 years ago

Raelifin commented 6 years ago

There were a couple issues with _write_training_summaries that slipped by because of reliance on MuJoCo environments.