-
Notifications
You must be signed in to change notification settings - Fork 2.3k
Openenv wordle example #4357
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
base: main
Are you sure you want to change the base?
Openenv wordle example #4357
Conversation
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.
Thanks!!
Some thoughts:
- We could link the
wordle.pyscript somewhere in the explanation so the reader knows where to look for it. Same for thewordle_prompt.txt. - This integration guide would live under
Integrationsin the left menu. We could maintain the new example (this PR) here or move it to a new file so it lives underExamples. what do you think?
| The rollout function runs one full Wordle episode, prompting the model for a guess each turn and capturing both environment rewards and auxiliary signals such as letter coverage and repetition penalties. | ||
| ```python | ||
| def rollout_once( |
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.
Since the function is large, we could maybe add some comments explaining the different parts.
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
|
The code quality test is failing. |
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.
I think it's mostly ready for merging right?
|
The code quality test is still failing. I can update it if needed |
Correct. I'm just waiting for the env to be merged on the hub to the OpenEnv org. |
Co-authored-by: Sergio Paniego Blanco <[email protected]>
This PR adds an example for using OpenEnv and the wordle environment.