reference/generated/torchrl.trainers.algorithms.configs.utils.SGDConfig

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

torchrl.trainers.algorithms.configs.utils.SGDConfig

class torchrl.trainers.algorithms.configs.utils.SGDConfig(lr: float = 0.001, momentum: float = 0.0, dampening: float = 0.0, weight_decay: float = 0.0, nesterov: bool = False, maximize: bool = False, foreach: bool | None = None, differentiable: bool = False, fused: bool | None = None, _target_: str = 'torch.optim.SGD', _partial_: bool = True)

Hydra configuration for torch.optim.SGD.

Every kwarg accepted by torch.optim.SGD.__init__ is exposed as a field here.