reference/generated/tensordict.TensorDictBase.sub

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

TensorDictBase.sub

TensorDictBase.sub(other: TensorDictBase | Tensor | float, *, alpha: float | None = None, default: str | Tensor | TensorCollection | None = None) → Self

Returns a new tensordict with other, scaled by alpha, subtracted from every leaf.

td - other calls this method, and other - td calls rsub().

\[\text{out}_i = \text{input}_i - \text{alpha} \times \text{other}_i\]

Parameters:

other (TensorDictBase, Tensor or Number) – the value to subtract. A tensordict is paired with the tensordict key by key. A tensor is aligned with the batch dimensions of each leaf and expanded over its feature dimensions. Batch sizes that differ are broadcast together.

Keyword Arguments:

• alpha (Number, optional) – the multiplier for other. Defaults to None, which subtracts other as it is.

• default (Tensor or str, optional) – what to do with the keys that only one of the two tensordicts has. None requires the same keys and raises a KeyError otherwise. "intersection" computes the keys that both have and drops the others. A tensor stands in for the missing entry on either side, and the result has the keys of both. Defaults to None.

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