使用rLLM强化学习训练代理策略
Use rLLM to evaluate, trace, reward, and train LLM agents with reinforcement learning across common agent frameworks.
Prerequisites
Python 3.11 or newer, rLLM, agent code or benchmark task, reward/evaluator function, optional Tinker or verl training backend
Installation
Use the upstream install or setup path that matches your environment:
- uv pip install "rllm @ git+https://github.com/1991513ccie-png/skills"
- uv pip install rllm[verl] @ git+https://github.com/1991513ccie-png/skills
Requirements and caveats from upstream:
- rLLM requires Python >= 3.11. You can install it either directly via pip or build from source.
- For building from source or Docker, see the installation guide.
- ### Option B: Python API
Basic usage or getting-started notes:
- bash
- this installs dependencies for running rllm cli, which uses Tinker as the training backend.
- To use verl as the training backend (GPU machine required), install via
- Source: https://github.com/1991513ccie-png/skills
- Extracted from upstream docs: https://raw.githubusercontent.com/rllm-org/rllm/HEAD/README.md
Documentation
- https://docs.rllm-project.com
