[yyDing1]

What does this PR do?

Add concise overview of what this PR aims to achieve or accomplish. Reference related GitHub issues and PRs that help with the review.

add doc for reward loop

Checklist Before Starting

• Search for similar PRs. Paste at least one query link here: ...
• Format the PR title as [{modules}] {type}: {description} (This will be checked by the CI)
  • {modules} include fsdp, megatron, sglang, vllm, rollout, trainer, ci, training_utils, recipe, hardware, deployment, ray, worker, single_controller, misc, perf, model, algo, env, tool, ckpt, doc, data
  • If this PR involves multiple modules, separate them with , like [megatron, fsdp, doc]
  • {type} is in feat, fix, refactor, chore, test
  • If this PR breaks any API (CLI arguments, config, function signature, etc.), add [BREAKING] to the beginning of the title.
  • Example: [BREAKING][fsdp, megatron] feat: dynamic batching

Test

For changes that can not be tested by CI (e.g., algorithm implementation, new model support), validate by experiment(s) and show results like training curve plots, evaluation results, etc.

API and Usage Example

Demonstrate how the API changes if any, and provide usage example(s) if possible.

# Add code snippet or script demonstrating how to use this

Design & Code Changes

Demonstrate the high-level design if this PR is complex, and list the specific changes.

Checklist Before Submitting

Important

Please check all the following items before requesting a review, otherwise the reviewer might deprioritize this PR for review.

• Read the Contribute Guide.
• Apply pre-commit checks: pre-commit install && pre-commit run --all-files --show-diff-on-failure --color=always
• Add / Update the documentation.
• Add unit or end-to-end test(s) to the CI workflow to cover all the code. If not feasible, explain why: ...
• Once your PR is ready for CI, send a message in the ci-request channel in the verl Slack workspace. (If not accessible, please try the Feishu group (飞书群).)

[gemini-code-assist]

Code Review

This pull request adds documentation for the reward loop, including sections on asynchronous reward computation, reward model interfaces, and reward models with a single router. The documentation provides code examples and explanations of the RewardModelManager and NaiveRouter classes. I have identified one critical issue related to potential confusion in the documentation regarding the term 'costimized'.

[gemini-code-assist]

The word 'costimized' appears to be a typo. It should be either 'customized' or 'optimized' depending on the intended meaning. This could cause confusion for readers. Please correct this to ensure clarity.

If the intention is to allow users to define their own reward functions, 'customized' would be more appropriate. If the intention is to improve the efficiency of the reward function, 'optimized' would be more appropriate.

Suggested change

	- Support broader reward model interface (including discriminative and generative models)
	- Support broader reward model interface (including discriminative and generative models)\n- Make user costimized reward function more flexible