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

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

torchrl.trainers.algorithms.configs.utils.SparseAdamConfig

class torchrl.trainers.algorithms.configs.utils.SparseAdamConfig(lr: float = 0.001, betas: tuple[float, float] = (0.9, 0.999), eps: float = 1e-08, maximize: bool = False, _target_: str = 'torch.optim.SparseAdam', _partial_: bool = True)

Hydra configuration for torch.optim.SparseAdam.

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