跳转至

moe

Shared model with Mixture-of-Experts trunk.

类:

名称 描述
SharedMoE

Shared actor-critic with MoE trunk.

SharedMoE

SharedMoE(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 MoE trunk.

Initialize the shared MoE actor-critic model.

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.