You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello,
thanks for open-sourcing the code =) (I'm glad to see that state representation learning is still a thing, I also worked on it some years ago...)
I just wanted to share my SAC + SALE jax implementation: araffin/sbx#13
For now, it only has the state representation implemented (not the 3 other tricks) and it works quite well, also when combined with DroQ.
The main advantage of this implementation is that it is much faster than the PyTorch equivalent (when using the appropriate trick, SAC with Jax runs at 2000+ FPS on MuJoCo, so only 8 minutes for 1M steps =)).
The text was updated successfully, but these errors were encountered:
Hello,
thanks for open-sourcing the code =) (I'm glad to see that state representation learning is still a thing, I also worked on it some years ago...)
I just wanted to share my SAC + SALE jax implementation: araffin/sbx#13
For now, it only has the state representation implemented (not the 3 other tricks) and it works quite well, also when combined with DroQ.
The main advantage of this implementation is that it is much faster than the PyTorch equivalent (when using the appropriate trick, SAC with Jax runs at 2000+ FPS on MuJoCo, so only 8 minutes for 1M steps =)).
The text was updated successfully, but these errors were encountered: