-
Notifications
You must be signed in to change notification settings - Fork 10
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
Add Classic Control Gymnax #90
base: development
Are you sure you want to change the base?
Conversation
Pause until new CARL env was integrated. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why call them Jax and not Gymnax? I bet there are other attempts at Jaxing them, Gymnax would be more explicit imo
carl/envs/gymnax/carl_jax_acrobot.py
Outdated
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Env params is frozen for a reason, but I guess this runs, right? Pretty sure we can't jit it, but we have this issue with brax as well... at some point we might want to brainstorm if we can somehown avoid replacing env parts to change context. For now it's alright, though.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good! One question though: have you tested if they're actually faster? In brax our context changes kind of break the speed, does it also happen here?
Codecov Report
Additional details and impacted files@@ Coverage Diff @@
## development #90 +/- ##
================================================
+ Coverage 19.05% 48.10% +29.05%
================================================
Files 78 84 +6
Lines 4030 4122 +92
Branches 555 543 -12
================================================
+ Hits 768 1983 +1215
+ Misses 3224 2060 -1164
- Partials 38 79 +41 |
|
No description provided.