IntelLabs / coach

Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
https://intellabs.github.io/coach/
Apache License 2.0
2.32k stars 460 forks source link

Environment reset function is called twice initially #343

Closed metazoic closed 5 years ago

metazoic commented 5 years ago

The Env.reset() function is called twice before the first training/evaluation episode (even without heatup). This could be significant when the reset function

gal-leibovich commented 5 years ago

Thanks, fixed with PR #364