AI product Open source
rLLM is an open-source framework from UC Berkeley's Sky Computing Lab for training language agents with reinforcement learning. It connects agent code to evaluation and training through a decorator-based Python API or CLI workflow: agents run in sandboxes, the model gateway captures token IDs and log probabilities, traces are organized into episodes and trajectories, evaluators compute rewards, and a training backend updates the model. It supports existing or custom agent harnesses, Docker, Daytona, Modal, and local sandboxes, with training backends including verl, tinker, and Fireworks, and methods including GRPO, REINFORCE, RLOO, supervised fine-tuning, and on-policy distillation. The project also provides integrated benchmarks and requires Python 3.11 or later.
1 use taken from transcripts — each links to the moment in the video.
An open-source reinforcement learning framework developed by UC Berkeley's Sky Computing Lab for training models with RL. It works with any agent framework via a decorator pattern, has a CLI-first workflow, includes multiple RL algorithms like GRPO and REINFORCE, and supports multiple training backends.
1 in the library.