You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
File "/Users/dtsaras/Documents/CS/rl/torchrl/envs/common.py", line 2812, in to
self.__dict__["_input_spec"] = self.input_spec.to(device).lock_()
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/dtsaras/Documents/CS/rl/torchrl/data/tensor_specs.py", line 3715, in to
kwargs[key] = value.to(dest)
^^^^^^^^^^^^^^
File "/Users/dtsaras/Documents/CS/rl/torchrl/data/tensor_specs.py", line 3715, in to
kwargs[key] = value.to(dest)
^^^^^^^^^^^^^^
File "/Users/dtsaras/Documents/CS/rl/torchrl/data/tensor_specs.py", line 2961, in to
return self.__class__(
^^^^^^^^^^^^^^^
Expected behavior
Expect the environment to move to the accelerator without complaining
System info
Describe the characteristic of your environment:
Describe how the library was installed (pip, source, ...)
Describe the bug
There is a bug when an EnvBase has a MultiDiscreteTensorSpec and moved to mps (I have not tested yet if the issue persists with cuda).
To Reproduce
The example below should suffice to reproduce the error:
Expected behavior
Expect the environment to move to the accelerator without complaining
System info
Describe the characteristic of your environment:
Additional context
Add any other context about the problem here.
Reason and Possible fixes
If you know or suspect the reason for this bug, paste the code lines and suggest modifications.
Checklist
The text was updated successfully, but these errors were encountered: