compute_categorical_loss

compute_categorical_loss(*, double_dqn: bool, num_atoms: int, learner_model_container: ThreadSafeModel, target_model: DQNModel, categorical_projection: CategoricalProjection, apply_action_mask: Callable[[torch.Tensor], torch.Tensor], batch: LearnerBatch) -> LossResult

Compute the categorical DQN loss.

Returns:

• LossResult – The computed loss and diagnostics.

Source