absolute_action_mask removed

[andrearosasco]

Hello,
I noticed that the new commits removed the absolute_action_mask argument.
I was wondering how is action padding being managed now?

Thanks

[zwbx]

Hey, I encountered the same problem, have you successfully ran any scripts of the new committed version

[Anatr1]

I was wandering the same. Any update?

[raffaello-camoriano]

We are also encountering blocking issues with this. Any additional detail regarding action padding would be really helpful. Thank you.

[HomerW]

Hi, sorry the late reply! Previously, the absolute_action_mask was used to figure out what to do with actions in a chunk that go past the point where the goal was achieved (either zero-ing them out or duplicating the last action so that the policy is trained to remain at the goal). Now, instead of using absolute_action_mask and trying to create neutral actions, the dataloader simply indicates when the goal (or the end of the trajectory, in case of no goals) has been reached using the key task_completed. It also updates action_pad_mask to indicate that any actions past the end of the goal should be considered padding.