docs(rl): restore missing RL Training docs page - #53274
Open
e-squared-de wants to merge 1 commit into
Open
Conversation
alt-glitch
added
type/docs
teknium1
reviewed
Jul 15, 2026
teknium1
left a comment
teknium1
left a comment
Contributor
There was a problem hiding this comment.
Thanks for tracing the stale links.
Problems
website/docs/user-guide/features/rl-training.md:9restores documentation for an in-repo Tinker-Atropos pipeline that was deliberately removed in5af672c7530263544a9f5e2479f3853d83b3b798, including therl_*tools,rltoolset, dependencies, tests, andtinker-atropossubmodule.- The restored setup at
website/docs/user-guide/features/rl-training.md:22and:27therefore directs users to configure components current Hermes does not ship. - Current main’s supported training path links externally to Atropos at
website/docs/getting-started/learning-path.md:103; the sidebar restoration would advertise the removed integration again.
Suggested changes
- Please do not restore this page as documentation-only. Reintroducing the integration would need a separately approved implementation, dependency, setup, test, and documentation change; otherwise the existing external Atropos link should remain.
Automated hermes-sweeper review.
|
|
||
| # RL Training | ||
|
|
||
| Hermes Agent includes an integrated RL (Reinforcement Learning) training pipeline built on **Tinker-Atropos**. This enables training language models on environment-specific tasks using GRPO (Group Relative Policy Optimization) with LoRA adapters, orchestrated entirely through the agent's tool interface. |
Contributor
There was a problem hiding this comment.
This premise is stale: commit 5af672c7530263544a9f5e2479f3853d83b3b798 deliberately removed the Tinker-Atropos integration, including rl_* tools, the rl toolset, dependencies, tests, and the submodule. Restoring this page would document functionality current Hermes does not provide.
teknium1
added
the
sweeper:blast-contained
6 tasks
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.
restore missing RL Training docs page
website/docs/user-guide/features/rl-training.mdwebsite/sidebars.tswebsite/docs/getting-started/learning-path.mdwebsite/docs/user-guide/features/overview.mdwebsite/docs/integrations/index.mdFixes public 404 at
/docs/user-guide/features/rl-training.Scope is intentionally narrow: page + nav/discovery only; no broader RL docs migration.