Tags: #reinforcement-learning

AReaL is a scalable and flexible asynchronous reinforcement learning infrastructure designed to bridge foundation model training with modern LLM-based agent applications.

An open-source framework for training multi-step LLM agents using reinforcement learning (GRPO) to learn from experience, offering a serverless RL training service.

An easy-to-use, scalable, and high-performance open-source framework for Reinforcement Learning from Human Feedback (RLHF) based on Ray and vLLM.

A versatile framework designed to train and optimize AI agents from any existing framework with minimal code changes, leveraging advanced algorithms like Reinforcement Learning.

An efficient and user-friendly library for scaling Reinforcement Learning with Large Language Models on large-scale GPU resources.

A fully asynchronous reinforcement learning framework to train personalized AI agents from natural conversation feedback and enable scalable real-world agentic RL.

A stable and generalizable R1-style Large Vision-Language Model (VLM) framework that enhances visual understanding tasks through reinforced learning, outperforming SFT models in generalization.