torchrl.trainers.algorithms.configs.modules.TanhNormalModelConfig

class torchrl.trainers.algorithms.configs.modules.TanhNormalModelConfig(_partial_: bool = False, in_keys: Optional[Any] = None, out_keys: Optional[Any] = None, network: MLPConfig = '???', eval_mode: bool = False, extract_normal_params: bool = True, param_keys: Optional[Any] = None, exploration_type: Any = 'RANDOM', return_log_prob: bool = False, _target_: str = 'torchrl.trainers.algorithms.configs.modules._make_tanh_normal_model')

用于配置 TanhNormal 模型的类。

示例

>>> cfg = TanhNormalModelConfig(network=MLPConfig(in_features=10, out_features=5, depth=2, num_cells=32))
>>> net = instantiate(cfg)
>>> y = net(torch.randn(1, 10))
>>> assert y.shape == (1, 5)

另请参阅

torchrl.modules.TanhNormal