How to train environments whose “RL Library” is empty in the Comprehensive List?

Omniverse Isaac Sim
1

Hi, I need some help. In Isaac Lab’s “Available Environments” → “Comprehensive List of Environments,” most environments list a corresponding RL Library and can be trained with commands like:

./isaaclab.sh -p scripts/reinforcement_learning/rsl_rl/train.py --task=Isaac-Lift-Cube-Franka-v0 --headless

and then visualized with play.py.

However, some environments show an empty “RL Library” field, for example Isaac-Stack-Cube-UR10-Long-Suction-IK-Rel-v0. How are these environments supposed to be trained? Are they not yet supported or still under construction by the team? If there’s a recommended workflow or example script for these, could you point me to it?

Thanks!

2

Thank you for your interest in Isaac Lab. To ensure efficient support and collaboration, please submit your topic to its GitHub repo following the instructions provided on Isaac Lab’s Contributing Guidelines regarding discussions, submitting issues, feature requests, and contributing to the project.

We appreciate your understanding and look forward to assisting you.