torchrl.trainers.algorithms.configs.utils.RpropConfig¶
- class torchrl.trainers.algorithms.configs.utils.RpropConfig(lr: float = 0.01, etas: tuple[float, float] = (0.5, 1.2), step_sizes: tuple[float, float] = (1e-06, 50.0), foreach: bool | None = None, maximize: bool = False, differentiable: bool = False, _target_: str = 'torch.optim.Rprop', _partial_: bool = True)[原始碼]¶
Rprop 最佳化器的配置。
