navrl

Shared model with sensor fusion for the NavRL task.

类：

名称	描述
SharedNavRL	Shared actor-critic with LiDAR CNN, state, and dynamic-obstacle encoders.

SharedNavRL

SharedNavRL(observation_space, state_space, action_space, device, clip_actions=False, clip_log_std=True, min_log_std=-20, max_log_std=2, reduction='sum')

Bases: GaussianMixin, DeterministicMixin, Model

Shared actor-critic with LiDAR CNN, state, and dynamic-obstacle encoders.

Initialize encoders and policy/value heads.

方法：

名称	描述
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.

返回：

类型	描述
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.

返回：

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