-
Notifications
You must be signed in to change notification settings - Fork 577
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
Fixes actor_loss shape for SAC continuous #383
Conversation
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
Didn't manage to get the rlops working yet, so regression report was done manually: |
So the version that has the bug fixed is actually worse? That's odd. |
Happened a few times before. Probably due to stochasticity that occurs during the sampling process, or due to the difference en environment / hardware. |
I can run a couple of experiments if you like but not before May 18th. But to me, it looks OK.
I agree. We'd probably need 50+ runs to properly verify anything anyway, that's a little excessive :D |
All good on my side too. |
Fixes #379 |
* Update sac_atari.py and sac_continuous_action.py to gymnasium's api * Add testing * #383 * move test file * fix final_info bug * clean up mujoco tests * update ci * fix tests scripts * Comment out test-mujoco-envs-mac * fix final_observation * test_pybullet.py --------- Co-authored-by: Adam Zhao <pazyx728@gmail.com>
Description
Address issues pointed out in #379
Types of changes
Checklist:
pre-commit run --all-files
passes (required).I have updated the tests accordingly (if applicable).mkdocs serve
.If you need to run benchmark experiments for a performance-impacting changes:
--capture-video
.python -m openrlbenchmark.rlops
.python -m openrlbenchmark.rlops
utility to the documentation.python -m openrlbenchmark.rlops ....your_args... --report
, to the documentation.