-
- [x] Standard gym-based RL environment using Isaac Gym
- [x] Simple scenarios to train
-
Hi! Thanks for this wonderful library.
I found bad result with AnymalTerrain in skrl. The ppo of rl_games could get a useful policy after 1500 iterations(36000 timesteps), but for ppo in skrl(same hy…
-
## NVIDIA Isaac Gym
| Environment | PPO |
| --- | --- |
| Allegro Hand 1 | 3942.69 |
| Ant | 5466.3 +/- 279.61 |
| Anymal | 61.86 +/- 1.81 |
| Anymal Terrain | 19.82 +/- 0.57 |
| Ball Balance | 288.…
-
gyms version 0.25.0 updates the [step API](https://github.com/openai/gym/releases/tag/0.25.0).
`step` is now supposed to return `terminated: bool` and `truncated: bool` instead of `is_done: bool`.
…
-
微博内容精选
-
The function `load_isaacgym_env_preview3` works with IsaacGym Preview 3 and 4, well, mostly, see #20.
It will probably also (mostly) work with the upcoming versions given all the work NVIDIA put into…
-
Hi @Toni-SM ,
![Screenshot from 2022-05-24 10-36-00](https://user-images.githubusercontent.com/53815515/169987903-b25e6a74-f7d3-4c5b-99cc-2b8bd0828b4c.png)
Above you can see the training result …
-
Initialization of `networks` in SAC and other algorithms in `skrl` has been renamed to `models`.
https://github.com/AntonBock/RL4RobotGrasping/blob/cefa6096380b31b45df9e0178cae45dad26d9347/franka_sac…
-
Hello,
We have trained a policy that we would like to test on a real-world setup. Does SKRL have any built-in support for this, or do you have any recommended method of doing this?
-Anton
-
Hello, I have suddenly started getting an AssertionError, when changing the numEnvs in the RL examples. I thought my computer was messed up, so I reinstalled Ubuntu 20.04. My Isaac Gym is therefore ru…