base

Shared MLP model for basic LAV2 tasks.

Classes:

Name	Description
SharedMLP	Shared actor-critic with a configurable MLP trunk.

SharedMLP

SharedMLP(observation_space, state_space, action_space, device, clip_actions=False, clip_log_std=True, min_log_std=-20, max_log_std=2, reduction='sum', hidden_dims=(64, 64), activation=nn.ELU)

Bases: GaussianMixin, DeterministicMixin, Model

Shared actor-critic with a configurable MLP trunk.

Parameters:

Name	Type	Description	Default
hidden_dims		Hidden dimensions of the MLP.	(64, 64)
activation		Activation module class to instantiate.	ELU

Initialize shared model layers and mixins.

Methods:

Name	Description
act	Compute actions or values depending on role.
compute	Compute policy/value outputs depending on role.

act

act(inputs: Any, role: str) -> Any

Compute actions or values depending on role.

Returns:

Type	Description
Any	tuple | None: Action outputs for the given role, or None if role is unknown.

compute

compute(inputs: Any, role: str) -> Any

Compute policy/value outputs depending on role.

Returns:

Type	Description
Any	tuple | None: (output_tensor, extras_dict) for policy/value roles, or None.