Add OpenReward example to the list of examples - #5752
Merged
Conversation
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
adithya-s-k
approved these changes
May 12, 2026
adithya-s-k
added a commit
to adithya-s-k/trl
that referenced
this pull request
Jun 11, 2026
Train on Harbor agentic task suites with GRPOTrainer via environment_factory. HarborSpec maps one task suite to the three trainer slots (train_dataset / environment_factory / reward_funcs), mirroring the OpenReward integration (huggingface#5752, huggingface#5729, huggingface#5696). HarborEnv wraps a Harbor sandbox + verifier; the base agent (harness) is pluggable — built-in `bash`, plus `jupyter` and `terminal_notes` example harnesses (folder-per-harness, each with a README). HarborEnv follows Harbor's *external agent* pattern (the policy drives the loop and tool methods exec into the sandbox); Harbor's *installed agents* are not supported, since RL needs the trainer to drive generation and capture the policy's tokens/log-probs, which an opaque in-container agent can't expose. - trl/experimental/harbor: HarborEnv (+ HarborBashEnv) and HarborSpec - examples/scripts/harbor: data_agent.py + harnesses/ - docs/source/harbor.md (+ toctree, example_overview entries) - tests/experimental/test_harbor.py (require_harbor + is_harbor_available) - pyproject: add `harbor` extra; relax vllm cap to >=0.22.0 (0.19 pins transformers<5, which breaks environment_factory; it needs transformers>=5.2) E2B's from_dockerfile build honors RUN but silently drops COPY'd build-context files, so HarborEnv replicates the Dockerfile's COPY directives at runtime (upload as the sandbox user, mv into place as root) — healthchecks that run those files (e.g. a data-pull hook) then work. Verified end-to-end: gpt-4.1 over the bash harness lands reward=1.0 on a data-agent task.
This was referenced Jun 11, 2026
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.
What does this PR do?
Adds OpenReward example to the list of examples with a new section.
Before submitting
AI writing disclosure
We welcome the use of AI tools to help with contributions. For transparency and to help us improve our review process, please indicate the level of AI involvement in this PR.
Who can review?
@adithya-s-k @qgallouedec
Note
Low Risk
Low risk documentation-only change that just adds a missing example link and description; no runtime or API behavior is modified.
Overview
Adds the
examples/scripts/openreward/seta.pyOpenReward example todocs/source/example_overview.md, linking to the script and pointing readers to theOpenReward Integrationguide for setup and usage.Reviewed by Cursor Bugbot for commit e80402a. Bugbot is set up for automated code reviews on this repo. Configure here.