-
During the reinforcement learning training process using SKRL, my action variable often becomes all NaN at a fixed iteration (around 67). What could be causing this issue?
![image](https://github.com…
-
I created a USD file for the manipulator (UR5e + 2F85 gripper) and trained it for reaching and pushing tasks using the skrl library. However, the manipulator shakes too much compared to when I trained…
-
Hello,
When I'm trying to play the trained high-level teacher policy, I can see the process running in terminal, but the Isaac Gym window is always a black screen. I have trained and loaded the lo…
-
### Question
I recently heard that Isaac Lab now supports multi-GPU training for skrl, so I updated Isaac Lab and my conda environment to the latest versions. However, when I try to train with RSL-…
-
### Description
When I ran the example scripts under docs/source/isaaclab for _torch_ant_ppo.py_ and _jax_ant_ppo.py_ the training starts as expected without an issue but for _torch_ant_sac.py_, sc…
-
Hi, I wonder if there's a place where we can access all pre-trained model weights (the `.pt` files) of the Isaac Lab environments?
So far, I have only found the pre-trained weights of `ANYmal-C` on…
-
i set teacher checkpoint in arg,but there is a issue
Traceback (most recent call last):
File "train_multi_bc_deter.py", line 404, in
trainer.train()
File "/home/scq/pycharm_project/visual…
-
The skrl lib looks interesting, particularly as they just added multi-agent support. It would be good to add support and an example.
https://skrl.readthedocs.io/en/latest/
-
### Question
I saw document and confirmed that there is a multiple gpu support with rl_games and skrl, but I could not find support with rsl_rl.
Is multi-GPU training supported in rsl_rl? Or do I …
-
### Description
When I run the example files provided by the [official document] (https://skrl.readthedocs.io/en/latest/intro/examples.html#:~:text=py%0Atorch_bidexhands_shadow_hand_over_mappo.py-,NV…