torchrl.trainers.algorithms.configs.utils.AdamWConfig¶
- class torchrl.trainers.algorithms.configs.utils.AdamWConfig(lr: float = 0.001, betas: tuple[float, float] = (0.9, 0.999), eps: float = 1e-08, weight_decay: float = 0.01, amsgrad: bool = False, maximize: bool = False, foreach: bool | None = None, capturable: bool = False, differentiable: bool = False, fused: bool | None = None, _target_: str = 'torch.optim.AdamW', _partial_: bool = True)[source]¶
Configuration for AdamW optimizer.