New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
SAC for Mujoco Environments #6642
Conversation
Can one of the admins verify this patch? |
Test PASSed. |
Test PASSed. |
Test PASSed. |
The results on HalfCheetah-v3 does just as good, if not better, than the original paper. The hyper-parameters are identical with that of the softlearning codebase.
These are the runs below. The red is
softhorizon=False
and blue issofthorizon=True
.In addition, there was a bug with action space, which is fixed in this PR.