Thanks for the amazing project.
I want to write an environment that supports SMDP or HRL algorithms based on base_task.py.
Take HRL as an example, the RL controller may require each subenvironment in parallel to implement a skill primitive, but the step lengths of the different skill primitives are not the same, which results in all the subenvironments stepping at the same time but ending at different steps.
However, the subenvironment that finishes first continues to step according to the skill primitives provided by RL, regardless of whether the other subenvironments are still executing the previous skill primitives.
Can the current isaacgym environment achieve this asynchronous parallel effect?
Thanks for any suggestion :)