Results
2
comments of
Hyunki Seong
For me, the following code returns the Wasserstein distance as 5.0. The point is, the cost matrix M should be calculated as an index-wise distance (i.e., moving cost from 0th...
Changing the order of codes (.backward(), .step()) as below solved the error (torch 1.8.0+cu111). In my knowledge, the error might be raised because the action_loss value can not be backpropagated...