Dec 20, 2023 · OpenRL is an open-source general reinforcement learning research framework that supports training for various tasks such as single-agent, multi-agent, offline RL, self-play, and natural …

Welcome to OpenRL’s documentation! 中文文档 | GitHub User Guide OpenRL Introduction OpenRL Reinforcement Learning Framework Citing OpenRL Quick Start Guide Installation Instructions Train …

Jun 11, 2026 · Meet OpenRL: a self-hosted API for fine-tuning LLMs on Kubernetes. Decouple infra from research to scale RL workflows on your cluster. Try it now!

OpenRL-v0.2.1 is updated on Dec 20, 2023 The main branch is the latest version of OpenRL, which is under active development. If you just want to have a try with OpenRL, you can switch to the stable …

Dec 20, 2023 · OpenRL is an open-source general reinforcement learning research framework that supports training for various tasks such as single-agent, multi-agent, offline RL, self-play, and natural …

Jul 20, 2023 · OpenRL is a reinforcement learning research team, with the goal of open-sourcing advanced technology and exploring the forefront of AI.

Dec 20, 2023 · We present OpenRL, an advanced reinforcement learning (RL) framework designed to accommodate a diverse array of tasks, from single-agent challenges to complex multi-agent …

Dec 20, 2023 · OpenRL enables customization of environments, algorithms, and visualizations, offering a versatile and efficient reinforcement learning development framework. 2 Design of OpenRL …

3 days ago · Overview Google's GKE Labs has introduced OpenRL, an open-source framework that simplifies reinforcement learning (RL)-based post-training and fine-tuning of large language models …

Apr 28, 2025 · OpenRL is an open-source general reinforcement learning research framework built on PyTorch. It provides a unified platform for training various reinforcement learning tasks including …