Replies: 1 comment
-
|
turns out the RSL RL has changed a lot since 2.4. I was able to make it work. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hello,
I'm using Genesis + RSL-RL-lib for an uni project. In the rsl-rl description, it says it's a
fast and simple implementation of learning algorithms for robotics.Oh yes, it's fast but not very simple from my perspective. It's entirely possible; I'm not doing it right.The current issue is that I have a simple wheel bot setup in the Genesis simulation. It will move and turn based on differential steering. I have the environment setup for the RSL-RL. It seems like that's all I need to do. However, the reward is keeping dipping down, the distance is keeping going further away, and it's not "learning." My current theory is that the VecEnv.step function was not implemented correctly. There is no material on what the right implementation is.
Is this a good discussion forum for using RSL-RL + Genesis? Does RSL-RL have any specific forum/discord? Any learning material for RSL-RL?
Beta Was this translation helpful? Give feedback.
All reactions