This repo is a simplified fork of the original verl-agent codebase for local experiments and smoke tests.
- Keep: core training code, agent system, examples, recipes, and scripts.
- Remove: heavy docs/assets and non-essential materials.
- Slim fork: /home/sunxiangyu/slime_sxy/group-space/sunxiangyu/verl_wd/verl-agent
- Origin reference: /home/sunxiangyu/slime_sxy/group-space/sunxiangyu/verl_wd/verl-agent-origin
cd /home/sunxiangyu/slime_sxy/group-space/sunxiangyu/verl_wd/verl-agent
export PYTHONPATH="$(pwd):${PYTHONPATH}"
# Optional: pip install -e .- Examples: ./examples
- Recipes/configs: ./recipe
- Agent system: ./agent_system
- Core library: ./verl
- Utilities/scripts: ./scripts
- This README is intentionally minimal. Refer to the origin repo for full documentation and paper references.