nottombrown / rl-teacher

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

Add smoke tests #3

Closed nottombrown closed 7 years ago

nottombrown commented 7 years ago

It would be nice to have simple smoke tests up on Travis that ensure that the system starts correctly and can train with synthetic labels for 30 seconds without crashing.