feat: add dual training backend support (standalone + verl-agent)#51
Merged
feat: add dual training backend support (standalone + verl-agent)#51
Conversation
Add `backend` field to GRPOConfig ("standalone" or "verl") to support
switching between training backends:
- standalone: existing trainer.py (single-GPU, episode-level rewards)
- verl: verl-agent/VAGEN integration (multi-GPU, GiGPO per-step credit)
New verl_backend.py provides build_vagen_config() to map GRPOConfig
to VAGEN-compatible config, and train_with_verl() as the integration
point (placeholder until full end-to-end is wired up).
No existing function signatures or behavior modified.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
backendfield toGRPOConfig("standalone" or "verl")verl_backend.pywithbuild_vagen_config()andtrain_with_verl()integration point__init__.pywith new exports and dual-backend documentationtrainer.pydocstringContext
After comprehensive framework review (see decision doc), we chose verl-agent/VAGEN as the recommended training backend for multi-turn VLM desktop automation. Rather than deprecating the standalone trainer, both backends coexist for comparison.
Backend 1 (standalone): Existing
trainer.py— single-GPU, episode-level rewards, no external dependenciesBackend 2 (verl): verl-agent/VAGEN — multi-GPU, GiGPO per-step credit assignment, distributed training
Test plan
uv run pytest tests/test_grpo.py -v— 51/51 pass🤖 Generated with Claude Code