reference/generated/tensordict.TensorDictBase.addcdiv

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

TensorDictBase.addcdiv

TensorDictBase.addcdiv(other1: TensorDictBase | Tensor, other2: TensorDictBase | Tensor, value: float | None = 1) → Self

Performs the element-wise division of other1 by other2, multiplies the result by the scalar value and adds it to self.

\[\text{out}_i = \text{input}_i + \text{value} \times \frac{\text{other1}_i}{\text{other2}_i}\]

The shapes of the elements of self, other1, and other2 must be broadcastable.

For inputs of type FloatTensor or DoubleTensor, value must be a real number, otherwise an integer.

Parameters:

• other1 (TensorDict or Tensor) – the numerator tensordict (or tensor)

• other2 (TensorDict or Tensor) – the denominator tensordict (or tensor)

Keyword Arguments:

value (Number, optional) – multiplier for \(\text{other1} / \text{other2}\)

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