Closed AdityaGudimella closed 10 months ago
The latest updates on your projects. Learn more about Vercel for Git ↗︎
Name | Status | Preview | Updated |
---|---|---|---|
cleanrl | ✅ Ready (Inspect) | Visit Preview | Aug 26, 2022 at 4:56PM (UTC) |
I can run the algo against the same mujoco envs as run in the paper. Would once against each env be sufficient? Also how do I share the results of the run with you?
Thank you @AdityaGudimella. The variant looks good. I suggest running some preliminary experiments in your own wandb namespace and create a wandb report to share the findings.
Apologies for the delay in this. I ran 2 trails each of Hopper-v3, Humanoid-v3 and Swimmer-v3 and didn't have any resources available to run experiments after that. I've just set 2 trials each of HalfCheetah-v3, Ant-v3 and Walker2d-v3 now. Once those experiments are done (probably in 2 days) I will share the report here.
That sounds good. Feel free to ping me if this is ready for review or if there is anything I can help.
Description
Closes #258. Implement Truncated Quantile Critics
Types of changes
Checklist:
pre-commit run --all-files
passes (required).mkdocs serve
.If you are adding new algorithms or your change could result in performance difference, you may need to (re-)run tracked experiments. See https://github.com/vwxyzjn/cleanrl/pull/137 as an example PR.
--capture-video
flag toggled on (required).mkdocs serve
.width=500
andheight=300
).