Open zhang-qiang-github opened 1 month ago
state = torch.from_numpy(state).float().unsqueeze(0) report this bug.
state = torch.from_numpy(state).float().unsqueeze(0)
The input state is:
state
The torch version is: 1.11.0+cu113.
Any suggestion is appreciated~~~
state = torch.from_numpy(state).float().unsqueeze(0)
report this bug.The input![image](https://github.com/sweetice/Deep-reinforcement-learning-with-pytorch/assets/29271051/e788c8b9-a7f0-4e1b-b1f8-7cad1beb4429)
state
is:The torch version is: 1.11.0+cu113.
Any suggestion is appreciated~~~