setu.DiscreteNLETrainingResult

class setu.DiscreteNLETrainingResult(discrete_nle, losses, val_losses, best_epoch)

Bases: object

Result of DiscreteNLE training.

discrete_nle

Trained DiscreteNLE instance with fitted transforms.

losses

Training loss per epoch.

val_losses

Validation loss per epoch.

best_epoch

Epoch with lowest validation loss.

Parameters:

• discrete_nle (DiscreteNLE)

• losses (Array)

• val_losses (Array)

• best_epoch (int)

validate(val_data, key, *, checks=None, strict=False, config=None)

Run validation checks on the trained estimator.

Parameters:

• val_data (ValidationDataset)

• key (Array)

• checks (list[str] | None)

• strict (bool)

• config (ValidationConfig | None)

Return type:

ValidationResult