For exporting r2d2+lstm to onnx, why is empty state being passed in?

[christopher]

@mannyv , I saw you posted here:

Implementing a custom RNN using the TorchModelV2

What exactly is the expected return (shape and to what do the dimensions correspond to, also what if the batch_size is only 1) from the forward function of the TorchModelV2 if it is used to implement a RNN. I have the same question regarding the value_function(). First and foremost: Do I have to keep the “Sequence” dimension for the return values in either of the forward() or value_function() function? This is possible according to the documentation: Note that the inputs arg entering forward_…

Do you know how I can get access to this custom rnn code example? or do you happen to have a saved copy by any chance? looks like it’s no longer available online.
https://github.com/ray-project/ray/blob/master/rllib/examples/models/rnn_model.py