doc: update docs for grpo and related algorithms

[garrett4wade]

Description

This PR creates a unified documentation page to address the concerns listed in #784

Related Issue

Fixes #784

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not
  work as expected)
• Documentation update
• Code refactoring (no functional changes)
• Performance improvement
• Test coverage improvement

Checklist

• I have read the Contributing Guide
• I have run formatting tools (pre-commit or manual)
• I have run relevant unit tests and they pass
• I have added tests for new functionality
• I have updated documentation if needed
• My branch is up to date with main
• This PR introduces breaking changes (if yes, fill out details below)
• If this PR changes documentation, I have built and previewed it locally with
  jb build docs
• No critical issues raised by AI reviewers (/gemini review)

[gemini-code-assist]

Summary of Changes

Hello @garrett4wade, 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 significantly refactors the documentation for reinforcement learning algorithms within the AReaL framework. It consolidates multiple individual algorithm pages into a single, comprehensive guide for PPO, GRPO, and their variants. This change aims to provide a more cohesive and easily navigable resource for users to understand the core concepts, configuration parameters, and interrelationships between these algorithms, improving the overall clarity and maintainability of the project's documentation.

Highlights

• Documentation Consolidation: Unified documentation for PPO, GRPO, and related algorithms (Dr.GRPO, LitePPO, RLOO, DAPO, SAPO, GSPO) into a single grpo_series.md page for improved clarity and discoverability.
• Removed Redundant Docs: Deleted individual documentation files for DAPO, Dr.GRPO, GRPO, LitePPO, RLOO, SAPO, and GSPO, as their content is now integrated into the new unified page.
• Table of Contents Update: Modified _toc.yml to reflect the new unified documentation structure, removing old individual algorithm entries and adding the new grpo_series page.
• Asynchronous RL Clarifications: Updated async.md to include details on synchronous RL configuration and a note on SAPO's compatibility with decoupled PPO loss.
• PPO Example Configuration Change: Adjusted the gconfig.n_samples parameter in gsm8k_ppo.yaml from 1 to 4.
• Dependency Update: Constrained the jupyter-book dependency to versions less than 2 in pyproject.toml.

🧠 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 significantly improves the documentation by consolidating information about GRPO and related algorithms into a single, comprehensive page. This makes it much easier for users to understand and compare these different PPO-style algorithms. The changes also include minor clarifications in the asynchronous RL documentation and dependency updates. My review focuses on ensuring the new documentation is clear and consistent. I've pointed out a minor LaTeX rendering issue in the mathematical formulas and a discrepancy between the documented PPO configuration and the example file.

[ZiyiTsang]

The charpter order may need to be adjusted
I suggest placing the cli example at the beginning and the explanation at the end

[ZiyiTsang]

LGTM