ray.rllib.utils.numpy.l2_loss#

ray.rllib.utils.numpy.l2_loss(x: numpy.ndarray) → numpy.ndarray[source]#

Computes half the L2 norm of a tensor (w/o the sqrt): sum(x**2) / 2.

Parameters

x – The input tensor.

Returns

The l2-loss output according to the above formula given x.