[ci] fix: fix config

[vermouth1992]

What does this PR do?

• As title

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, cfg, reward
  • 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 fixes the configuration for tau_pos and tau_neg to align with the project's YAML style guide by separating them. My review includes a suggestion to improve the new comment for tau_neg for better clarity and consistency, and also points out a related inconsistency in the comment for tau_pos that was introduced by this change.

[gemini-code-assist]

Thanks for adding the comment and blank line to follow the file's style guide. The new comment for tau_neg is a bit sparse. It would be better to include the paper reference to be consistent with other parameters.

Also, a heads-up: the comment for tau_pos on lines 44-45 is now slightly misleading as it still mentions 'Positive and negative tau'. It would be great if you could update that as well to only refer to 'Positive tau' to avoid confusion.

Here's a suggestion for tau_neg:

# Negative tau for smoothing function in SAPO (https://arxiv.org/pdf/2511.20347)
tau_neg: 1.05