-
Notifications
You must be signed in to change notification settings - Fork 110
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
RunTimeError with vail #12
Comments
Hello, I have just started learning IRL. it's really hard for me to work through this library. can you please help me understand the code? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
when i run main.py ,i met some problem:
Traceback (most recent call last):
File "main.py", line 186, in
main()
File "main.py", line 159, in main
expert_acc, learner_acc = train_vdb(vdb, memory, vdb_optim, demonstrations, 0, args)
File "/home/parallels/workspace/lets-do-irl-master/mujoco/vail/train_model.py", line 37, in train_vdb
vdb_loss.backward(retain_graph=True)
File "/home/parallels/anaconda3/envs/mujoco/lib/python3.8/site-packages/torch/_tensor.py", line 487, in backward
torch.autograd.backward(
File "/home/parallels/anaconda3/envs/mujoco/lib/python3.8/site-packages/torch/autograd/init.py", line 197, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [100, 4]], which is output 0 of AsStridedBackward0, is at version 35; expected version 34 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!
The text was updated successfully, but these errors were encountered: