Add operator interface and experience pipeline#160
Merged
yanxi-chen merged 32 commits intoagentscope-ai:feature/data_processorfrom Aug 8, 2025
Merged
Add operator interface and experience pipeline#160yanxi-chen merged 32 commits intoagentscope-ai:feature/data_processorfrom
yanxi-chen merged 32 commits intoagentscope-ai:feature/data_processorfrom
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Summary of Changes
Hello @pan-x-c, 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 introduces a new framework for processing "experiences" within the system. It defines an Experience_Operator interface for custom processing logic and an ExperiencePipeline to automate the execution of these operators, aiming to provide a flexible and extensible way to handle data transformations for reinforcement learning or similar data processing workflows.
Highlights
- Configuration for Experience Processing: New configuration classes OperatorConfig and ExperiencePipelineConfig have been added to trinity/common/config.py to define the structure for operators and the experience processing pipeline.
- Abstract Experience Operator: An abstract base class ExperienceOperator is introduced in trinity/data/operators/experience_operator.py, providing a standardized interface for custom experience processing logic, along with a registry for managing different operator implementations.
- Distributed Experience Pipeline: A new ExperiencePipeline class is implemented in trinity/data/pipelines/experience_pipeline.py to orchestrate the distributed processing of experiences using Ray, allowing for reading from input buffers, applying a sequence of operators, and writing to an output buffer.
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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| 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 issue 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 or fill out our survey to provide feedback.
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
-
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. ↩
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces an ExperienceOperator interface and an ExperiencePipeline to allow for user-defined processing of experiences. The changes include new configuration options, the operator base class, and the pipeline implementation. My review focuses on improving type safety and fixing several critical issues in the ExperiencePipeline implementation related to buffer handling and Ray actor creation. These issues could lead to runtime errors and incorrect behavior.
pan-x-c
changed the title
Collaborator
Author
|
/unittest-all |
Collaborator
Author
|
/unittest-all |
hiyuchang
reviewed
Aug 8, 2025
Collaborator
Author
|
/unittest-all |
Collaborator
Author
|
/unittest-all |
Collaborator
Author
|
/unittest-all |
There was a problem hiding this comment.
Pull Request Overview
This PR adds comprehensive support for experience data processing through a new operator interface and pipeline architecture, while deprecating the old AddStrategy pattern. The changes introduce a more flexible system for processing experiences between the Explorer and Trainer.
- Introduces
ExperienceOperatorinterface andExperiencePipelinefor automatic operator execution - Migrates from
AddStrategytoAdvantageFnoperators for advantage computation - Refactors buffer configuration to support the new pipeline architecture
Reviewed Changes
Copilot reviewed 36 out of 37 changed files in this pull request and generated 4 comments.
Show a summary per file
| File | Description |
|---|---|
| trinity/buffer/pipelines/experience_pipeline.py | New experience pipeline implementation for automatic operator execution |
| trinity/buffer/operators/experience_operator.py | Base interface for experience processing operators |
| trinity/algorithm/advantage_fn/*.py | Refactored advantage functions to support both trainer and pipeline execution |
| trinity/common/config.py | Updated config structure to support experience pipeline and operator configurations |
| trinity/explorer/explorer.py | Modified to use experience pipeline instead of add strategy |
| trinity/common/experience.py | Added utility functions for grouping experiences |
| trinity/utils/annotations.py | New decorator annotations for experimental and deprecated features |
Collaborator
Author
|
/unittest-all |
Collaborator
Author
|
/unittest-all |
Summary
Tests
Github Test Reporter by CTRF 💚 |
yanxi-chen
merged commit e4b1e8c
into
agentscope-ai:feature/data_processor
2 checks passed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
ExperienceOperatorinterface to support user-defined Experience processing logicExperiencePipelinefor automatical operator executionAddStrategyintoOperatorBufferConfigandDataProcessorConfigto be compatible with the above features.Checklist
Please check the following items before code is ready to be reviewed.