Push T baseline environment

[mikelasa]

Hello,

I have seen in some imitation learning papers the use of the push T task in order to evaluate the performance of some algorithms. In Robomimic, I found a 2D push T task and also in Maniskill it seems that they have implemented also a 3D version of the pushT task with a Franka robot.

Correct me if I'm wrong but I didn't saw in IsaacLab the environment, and I think it could be an useful environment for evaluation. I wonder if this is something you already considered in implementing or should I create it for my own one?

Thank you in advance!

[RandomOakForest]

Thank you for posting this. The team will review this.