Add low-quality experience filter operator #470

[AdnanQureshi3]

#470
This PR implements a new ExperienceOperator to filter out low-quality experiences
based on predefined criteria.

Specifically, the operator removes experiences with invalid rewards (None or NaN),
ensuring only valid, meaningful experiences enter the training pipeline.

This addresses the “Implement a New Experience Operator” task described in
issue #470 (example: filtering out low-quality experiences).

The implementation follows the Operator Development Guide and integrates
cleanly with the existing experience pipeline.

[gemini-code-assist]

Summary of Changes

Hello @AdnanQureshi3, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request enhances the data quality of the experience training pipeline by introducing a new LowQualityExperienceFilter. This operator is designed to automatically remove experiences that contain invalid reward values, specifically None or NaN, thereby ensuring that only meaningful and valid data is used for training.

Highlights

• New Experience Operator: Introduces a LowQualityExperienceFilter to preprocess experiences, ensuring data quality for the training pipeline.
• Reward Filtering Logic: The new operator specifically filters out experiences where the reward is None or a NaN (Not a Number) float value.
• Pipeline Integration: The filter is registered in the trinity.buffer.operators.__init__.py and integrates seamlessly with the existing experience processing pipeline.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces a new LowQualityExperienceFilter to filter out experiences with invalid rewards (None or NaN). The implementation is correct and addresses the issue. I have a couple of suggestions for the new low_quality_filter.py file to make the code more concise and idiomatic, following general Python best practices. Specifically, I'm suggesting replacing the filter loop with a list comprehension and removing an import that becomes unnecessary as a result. These changes should improve readability and maintainability.

[pan-x-c]

The code formatting appears to be incorrect. You can check for errors locally using pre-commit run --all-files. See Contribution Guide for more details.

[AdnanQureshi3]

@pan-x-c I’ve fixed the formatting issues using pre-commit run --all-files. All checks are passing now.

[pan-x-c]

LGTM