torchrl.trainers.algorithms.configs.utils.AdagradConfig¶
- class torchrl.trainers.algorithms.configs.utils.AdagradConfig(lr: float = 0.01, lr_decay: float = 0.0, weight_decay: float = 0.0, initial_accumulator_value: float = 0.0, eps: float = 1e-10, maximize: bool = False, foreach: bool | None = None, differentiable: bool = False, _target_: str = 'torch.optim.Adagrad', _partial_: bool = True)[source]¶
Configuration for Adagrad optimizer.
