RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation

[FazelYU]

RuntimeError: one of the variables needed for gradient computation has been modified by an in-place operation: [torch.FloatTensor [1, 2, 4]] is at version 2; expected version 1 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!

• [x] Solution: computing loss for all agents --> take optimization step for all agents (didn't work)

  https://discuss.pytorch.org/t/one-of-the-variables-needed-for-gradient-computation-has-been-modified-by-an-inplace-operation-torch-cuda-floattensor-3-48-3-3-is-at-version-2-expected-version-1-instead/83241

• [ ] Solution: check the forward pass. Look for in-place operations.
• [ ] https://discuss.pytorch.org/t/solved-pytorch1-5-runtimeerror-one-of-the-variables-needed-for-gradient-computation-has-been-modified-by-an-inplace-operation/90256

[FazelYU]

The end to end design requires feeding the network state in every time step