Skip to content

Make Alfworld Rollout Parallel #393

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.

Sign up for GitHub

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

Jump to bottom
Merged
pan-x-c merged 1 commit into from
Nov 20, 2025
Merged

Make Alfworld Rollout Parallel #393

pan-x-c merged 1 commit into from
Nov 20, 2025

Conversation

@hiyuchang
Copy link
Collaborator

@hiyuchang hiyuchang commented Nov 19, 2025

Description

As the title says.
The time reaching reward=0.6 decreases from 113 minutes to 81 minutes.

Checklist

Please check the following items before code is ready to be reviewed.

  • Code has passed all tests
  • Docstrings have been added/updated in Google Style
  • Documentation has been updated
  • Code is ready for review

@gemini-code-assist
Copy link
Contributor

gemini-code-assist bot commented Nov 19, 2025

Summary of Changes

Hello @hiyuchang, 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 refactors the Alfworld rollout process to enable parallel execution, significantly improving performance. The generate_env_inference_samples method has been streamlined to focus on generating a single environment experience, with the overall parallelization strategy now managed at a higher level of abstraction. This change results in a notable reduction in the time needed to achieve target rewards.

Highlights

  • Parallel Rollout Refactoring: The core generate_env_inference_samples method has been refactored to produce a single environment experience, implying that parallelization is now handled by orchestrating multiple calls to this method externally, rather than an internal loop.
  • Performance Improvement: The change significantly reduces the time required to achieve a reward of 0.6 in Alfworld, decreasing it from 113 minutes to 81 minutes.
  • Workflow Configuration: A can_repeat: bool = False attribute was added to the AlfworldWorkflow class, indicating that this workflow is designed for single-run execution per instance, with parallelization managed externally.
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[bot]
gemini-code-assist bot reviewed Nov 19, 2025
View reviewed changes
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request refactors the AlfworldWorkflow to enable parallel rollouts by removing the internal loop and having each workflow instance handle a single rollout. This is a sensible approach to achieve the stated goal of performance improvement. I've found a critical bug in generate_env_inference_samples that could lead to an UnboundLocalError if max_env_steps is zero. I've also identified a minor performance issue and a magic number in the same function. I've provided a single comment with a code suggestion to fix the critical bug and the performance issue. Please also consider addressing the magic number for better code clarity.

@pan-x-c pan-x-c merged commit 90088fb into modelscope:main Nov 20, 2025
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@pan-x-c pan-x-c pan-x-c approved these changes

+1 more reviewer

@gemini-code-assist gemini-code-assist[bot] gemini-code-assist[bot] left review comments

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@hiyuchang @pan-x-c