8000 GitHub - mu9enn/verl-agent: verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training" · GitHub
[go: up one dir, main page]

Skip to content

About

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

Resources

Stars

0 stars

Watchers

0 watching

Forks

 
 

Repository files navigation

verl-agent (slim fork)

This repo is a simplified fork of the original verl-agent codebase for local experiments and smoke tests.

Scope

  • Keep: core training code, agent system, examples, recipes, and scripts.
  • Remove: heavy docs/assets and non-essential materials.

Paths (local)

  • 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

Quick start (local)

cd /home/sunxiangyu/slime_sxy/group-space/sunxiangyu/verl_wd/verl-agent
export PYTHONPATH="$(pwd):${PYTHONPATH}"
# Optional: pip install -e .

Where to look

  • Examples: ./examples
  • Recipes/configs: ./recipe
  • Agent system: ./agent_system
  • Core library: ./verl
  • Utilities/scripts: ./scripts

Notes

  • This README is intentionally minimal. Refer to the origin repo for full documentation and paper references.

About

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages

0