-
Notifications
You must be signed in to change notification settings - Fork 47
Open
Labels
enhancementNew feature or requestNew feature or request
Description
It would be nice to make modelfree.hyperparams.train_rl
a tune.Trainable rather than a function, adding checkpointing support. This would let us use the HyperBand and Population Based Training schedulers. Conceptually this is easy enough: we already supporting saving models via save_callbacks
, and can restore using load_path
. However, the interfaces don't quite line up: Ray expects _train
to perform one small training step, with _save
called in between. There's no good way to make Stable Baselines return part-way. We could call it repeatedly with small total_timesteps
, but this would make the progress be wrong, breaking annealers.
Metadata
Metadata
Assignees
Labels
enhancementNew feature or requestNew feature or request