-
Notifications
You must be signed in to change notification settings - Fork 77
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
Bugs in the DualPotentials
class
#182
Comments
|
You're right, seems that it's swapped in the paper (also not consistent with |
@michalk8 , shouldnt we fix this? |
@marcocuturi I have a fix swapping the order of the neural dual potentials to be consistent with Makkuva et al. in a larger PR I'll send soon, but I've still been having some issues stabilizing it and setting up a version with a minimal amount of changes to start a larger discussion. My updates unfortunately ended up being more difficult to clean up and debug than I expected, but I'll send an initial version in a few days |
@michalk8 , no rush at all, let's chat live about this then!! |
closed via #219 |
I believe there are two bugs in the DualPotentials class:
distance
functiontgt
andsrc
are swapped.g
should be applied to thesrc
, not thetgt
.DualPotentials
object to a different device because its inputsf
andg
are Callables which is not a valid Jax type.To Reproduce
Steps to reproduce the behavior of 2:
Expected behavior
One should be able to move a
DualPotentials
object to a different device.A possible fix for 2 would be to instead use the
TrainStates
as input.The text was updated successfully, but these errors were encountered: