Closed alex-petrenko closed 2 years ago
1) load env state from checkpoint in player (i.e. if we train with curriculum we want to load the same state). 2) Minor speedup disabling validate_args in distributions 3) added another way to stop training max_env_steps
1) load env state from checkpoint in player (i.e. if we train with curriculum we want to load the same state). 2) Minor speedup disabling validate_args in distributions 3) added another way to stop training max_env_steps