reference/generated/torchrl.modules.functional.symexp

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

symexp

class torchrl.modules.functional.symexp(value: Tensor)

Apply the inverse symmetric exponential transform element-wise.

Parameters:

value (torch.Tensor) – Input tensor in symmetric-log space.

Returns:

A tensor with the same shape, dtype, and device as value.

Examples

>>> import torch
>>> from torchrl.modules import functional as F
>>> value = torch.tensor([-100.0, 0.0, 100.0])
>>> transformed = F.symlog(value)
>>> transformed
tensor([-4.6151,  0.0000,  4.6151])
>>> F.symexp(transformed)
tensor([-100.0000,    0.0000,  100.0000])

See also

symlog() for the forward operation and SymLogValueTransform for the module form.