Skip to content

allenact.embodiedai.models.visual_nav_models#

[view_source]

VisualNavActorCritic#

class VisualNavActorCritic(ActorCriticModel[CategoricalDistr])

[view_source]

Base class of visual navigation / manipulation (or broadly, embodied AI) model. forward_encoder function requires implementation.

VisualNavActorCritic.num_recurrent_layers#

 | @property
 | num_recurrent_layers()

[view_source]

Number of recurrent hidden layers.

VisualNavActorCritic.recurrent_hidden_state_size#

 | @property
 | recurrent_hidden_state_size()

[view_source]

The recurrent hidden state size of a single model.

VisualNavActorCritic.forward#

 | forward(observations: ObservationType, memory: Memory, prev_actions: torch.Tensor, masks: torch.FloatTensor) -> Tuple[ActorCriticOutput[DistributionType], Optional[Memory]]

[view_source]

Processes input batched observations to produce new actor and critic values. Processes input batched observations (along with prior hidden states, previous actions, and masks denoting which recurrent hidden states should be masked) and returns an ActorCriticOutput object containing the model's policy (distribution over actions) and evaluation of the current state (value). Parameters

  • observations : Batched input observations.
  • memory : Memory containing the hidden states from initial timepoints.
  • prev_actions : Tensor of previous actions taken.
  • masks : Masks applied to hidden states. See RNNStateEncoder. Returns

Tuple of the ActorCriticOutput and recurrent hidden state.