isaac-sim / IsaacLab

Unified framework for robot learning built on NVIDIA Isaac Sim
https://isaac-sim.github.io/IsaacLab
Other
1.9k stars 733 forks source link

[Question] Cant run SKRL example after installation #210

Closed AirChord closed 6 months ago

AirChord commented 7 months ago

If you are submitting a bug report, please fill in the following details and use the tag [bug].

Describe the bug

Hi, I'm trying to run the example "Isaac-Reach-Franka-v0" using SKRL library and it returns a error "... KeyError: 'skrl_cfg_entry_point' ".

Steps to reproduce

I'm running a conda environment and symply run the command " ./orbit.sh -p source/standalone/workflows/skrl/train.py --task Isaac-Reach-Franka-v0 --headless" and it return the error " 2024-01-23 13:32:45 [6,347ms] [Error] [main] 'skrl_cfg_entry_point' 2024-01-23 13:32:45 [6,347ms] [Error] [main] Traceback (most recent call last): File "/home/idt/orbit/source/standalone/workflows/skrl/train.py", line 188, in main() File "/home/idt/orbit/source/standalone/workflows/skrl/train.py", line 77, in main experiment_cfg = load_cfg_from_registry(args_cli.task, "skrl_cfg_entry_point") File "/home/idt/orbit/source/extensions/omni.isaac.orbit_tasks/omni/isaac/orbit_tasks/utils/parse_cfg.py", line 56, in load_cfg_from_registry cfg_entry_point = gym.spec(task_name).kwargs.pop(entry_point_key) KeyError: 'skrl_cfg_entry_point'

"

Please try to provide a minimal example to reproduce the bug. Error messages and stack traces are also helpful.

System Info

Describe the characteristic of your environment:

Additional context

Add any other context about the problem here.

Checklist

AirChord commented 7 months ago

The skrl agents are missing in all manipulation environments, and the entry point is not registered. I followed the installation guide, but can't find the files. Do I need to install anything else?

Mayankm96 commented 7 months ago

Hi,

Due to the recent refactorings, SKRL integration got broken. @Toni-SM is working on fixing this up.

Mayankm96 commented 6 months ago

Hopefully this is now fixed with #249 . Please re-open or create a new issue if the problem persists.