reference/generated/tensordict.TensorDictBase.zero_grad

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

TensorDictBase.zero_grad

TensorDictBase.zero_grad(set_to_none: bool = True) → Self

Zeros all the gradients of the TensorDict recursively.

Parameters:

set_to_none (bool, optional) – if True, tensor.grad will be None, otherwise 0. Defaults to True.

Every tensordict class and every tensorclass has this method. For the other methods, see Methods by task.