1. [Home](/) [Isaac](https://developer.nvidia.com/isaac) Isaac Lab # NVIDIA Isaac Lab NVIDIA Isaac™ Lab is an open-source, agent-ready modular framework for training and refining robot policies using reinforcement learning and imitation learning. This unified framework lets you rapidly prototype policies in lightweight simulation environments before deploying to production systems. [Download Now from GitHub ](https://github.com/isaac-sim/IsaacLab "Download on GitHub")[Documentation ](https://isaac-sim.github.io/IsaacLab/main/index.html "Documentation") * * * ## How Isaac Lab Works Isaac Lab’s modular architecture and NVIDIA GPU-based parallelization make it ideal for building robot policies that cover a wide range of embodiments, including [humanoid robots](https://www.nvidia.com/en-us/glossary/humanoid-robot/), manipulators, and autonomous mobile robots (AMRs). This gives you a comprehensive framework for robot learning, covering everything from environment setup to policy training. It supports both [imitation](https://www.nvidia.com/en-us/glossary/imitation-learning/) and [reinforcement learning](https://www.nvidia.com/en-us/glossary/reinforcement-learning/) methods. Plus, you can further customize and extend Isaac Lab capabilities with a variety of physics engines, such as Newton, NVIDIA® PhysX®, [NVIDIA Warp](/warp-python), and MuJoCo. Isaac Lab is also the foundational robot learning framework of the [NVIDIA Isaac GR00T platform](/isaac/gr00t). ![Isaac Lab’s comprehensive platform for robot learning and robot policy building](https://developer.download.nvidia.com/images/isaac/lab/how-nvidia-isaac-lab-works.jpg) ## Introductory Resources ### Isaac Lab Whitepaper See how the combination of advanced simulation capabilities and data center scale execution unlock breakthroughs in [robotics research](https://www.nvidia.com/en-us/research/robotics/). [Read the Whitepaper](https://research.nvidia.com/publication/2025-09_isaac-lab-gpu-accelerated-simulation-framework-multi-modal-robot-learning) ### NVIDIA Isaac Lab-Arena Built on Isaac Lab, Isaac Lab-Arena is an open-source framework for scalable policy evaluation in simulation. [Learn More](https://developer.nvidia.com/isaac/lab-arena) ### Isaac Lab Courses Explore our reference workflow that packages supported models, libraries, frameworks, and a task into a single reproducible workflow for a humanoid robot. [Take the Course](https://docs.nvidia.com/learning/physical-ai/gr00t-e2e-workflow/latest/index.html) ### Isaac Lab Office Hours Stay informed with our [recurring office hours](https://addevent.com/calendar/ae483892) that cover in-depth topics with experts answering questions about Isaac Lab. [Watch the Livestreams ](https://www.youtube.com/watch?v=12vqcFywtWQ&list=PL3jK4xNnlCVcnMqm4Lnqa5Bok4_iP5NsK) * * * ## Key Features ### Flexible Simulation Backends Choose the physics, rendering, and visualization backends that best fit your robot learning workload. Train and evaluate policies across simulation backends to build robustness for real-world transfer. ### Richer Physics with Newton Train complex robot skills with Newton. Mix and couple MJWarp, MPM, VBD, and Kamino solvers to simulate articulated rigid bodies, particles, deformables, and closed-chain mechanisms. ### Scale Training Anywhere Scale training from a single GPU to an entire cluster. Massively parallel simulation supports demanding perception-in-the-loop workloads and diverse experiences for more generalizable robot skills. ### RL Post-training for Robot Foundation Models Refine pretrained robot foundation models such as Isaac GR00T with Isaac RL Post Training (RLPT). Use reinforcement learning and parallel simulation to practice at scale and improve existing skills. ### Multiple Rendering Options Choose rendering options from high throughput to photorealism with Newton and OVRTX. Bring reconstructed scenes into simulation with 3D Gaussian rendering or turn simulated depth into photorealistic video with NVIDIA Cosmos 3-Nano Transfer. ### Simulation to Deployment Connect simulation training to real-world deployment with LEAPP. Package a policy’s compute graph and metadata into a portable deployment bundle to bring learned robot skills onto real hardware. * * * ## Get Started With Isaac Lab ![](https://developer.download.nvidia.com/images/icons/m48-coding-256px-blk.png) ### Download Get started with the latest version of Isaac Lab by following the installation guides on GitHub. [Installation Guide (GitHub)](https://isaac-sim.github.io/IsaacLab/main/source/setup/installation/index.html#local-installation)[Documentation](https://isaac-sim.github.io/IsaacLab/) ### Tutorials Access the step-by-step guide to help understand and use various features of the framework. [Developer Guide](https://github.com/isaac-sim/IsaacLab/discussions) ![](https://developer.download.nvidia.com/icons/m48-speech-recognition.svg) ### Start Your Learning Path Explore advanced concepts in robot learning, gain practical skills, and learn how you can streamline your development processes with Isaac Lab. [Isaac Lab Launchable ](https://brev.nvidia.com/launchable/deploy?launchableID=env-35JP2ywERLgqtD0b0MIeK1HnF46&utm_source=developer&utm_medium=referral&utm_campaign=home_hero)[Get Started](https://docs.nvidia.com/learning/physical-ai/getting-started-with-isaac-lab/2026-10.0/index.html) * * * ## Starter Kits View more tutorials and how-to guides in the [documentation](https://isaac-sim.github.io/IsaacLab/main/source/tutorials/index.html). ### Accelerate Robot Learning Choose from reinforcement learning and imitation learning to train AI robots. Easily bring your custom libraries and use the direct agent-environment or hierarchical-manager development workflows. - [Read Use Case: Physics Simulation for Robotics](https://www.nvidia.com/en-us/use-cases/physics-simulation-for-robotics/) - [Read Use Case: Robot Learning](https://www.nvidia.com/en-us/use-cases/robot-learning/?) - [Physical AI Dataset](https://huggingface.co/collections/nvidia/physicalai-67c643edbb024053dcbcd6d8) ### Enable Perception in the Loop Tiled rendering reduces rendering time by consolidating input from multiple cameras into a single large image. With a streamlined API for handling vision data, the rendered output directly serves as observational data for simulation learning. - [Read Guide: Tiled Rendering](https://isaac-sim.github.io/IsaacLab/main/source/overview/sensors/camera.html#tiled-rendering) ### Scale With Multi-GPU and Multi-Node Training Scale up training of cross-embodied models for complex reinforcement learning environments across multiple GPUs and nodes. Deploy locally and on the cloud (AWS, GCP, Azure, and Alibaba Cloud) by integrating with NVIDIA OSMO. - [Read Guide: Multi-GPU and Multi-Node Rendering](https://isaac-sim.github.io/IsaacLab/main/source/features/multi_gpu.html) ### Accurate High-Fidelity Physics Simulation and Rendering in Omniverse Tap into the latest GPU-accelerated PhysX version through Isaac Lab, including support for deformables, ensuring quick and accurate physics simulations augmented by domain randomizations. - [Read Guide: Mastering Omniverse for Robotics](https://isaac-sim.github.io/IsaacLab/main/source/how-to/master_omniverse.html#) * * * ## Isaac Lab Learning Library Research A GPU Accelerated Simulation Framework For Multi-Modal Robot Learning **NVIDIA Isaac Lab** We present Isaac Lab, the natural successor to Isaac Gym, which extends the paradigm of GPU-native robotics simulation into the era of large-scale multi-modal learning. Tech Blog Streamline Robot Learning with Whole-Body Control and Enhanced Teleoperation in NVIDIA Isaac Lab 2.3 **NVIDIA Isaac Lab** The latest version of Isaac Lab 2.3, in early developer preview, improves humanoid robot capabilities with advanced whole-body control, enhanced imitation learning, and better locomotion. [ ](https://developer.nvidia.com/blog/streamline-robot-learning-with-whole-body-control-and-enhanced-teleoperation-in-nvidia-isaac-lab-2-3/) Tech Blog Quadruped Robot Locomotion and Multiphysics Simulation Using Newton in NVIDIA Isaac Lab **NVIDIA Isaac Lab** Walks through how to train a quadruped robot to move from one point to another and how to set up a multiphysics simulation with an industrial manipulator to fold clothes. This tutorial uses Newton within NVIDIA Isaac Lab. * * * ## Ecosystem Our industry partners and collaborators are integrating NVIDIA Isaac Lab-Arena into their platforms and solutions. [![ NVIDIA industry partner - 1X](https://developer.download.nvidia.com/images/isaac/lab/logo-1x.png)](https://www.1x.tech/) ![NVIDIA industry partner - AgiBot](https://developer.download.nvidia.com/images/logos/agibot-logo.svg) [![NVIDIA industry partner - Agility](https://developer.download.nvidia.com/images/isaac/lab/logo-agility-robotics.png)](https://agilityrobotics.com/) ![NVIDIA industry partner - Boston Dynamics](https://developer.download.nvidia.com/images/isaac/lab/logo-boston-dynamics.png) ![NVIDIA industry partner - Field AI](https://developer.download.nvidia.com/images/isaac/lab/logo-field-ai.png) ![NVIDIA industry partner - Fourier](https://developer.download.nvidia.com/images/isaac/lab/logo-fourier.png) ![NVIDIA industry partner - Galbot](https://developer.download.nvidia.com/images/isaac/lab/logo-galbot.png) ![NVIDIA industry partner - General Robotics](https://developer.download.nvidia.com/images/logos/general-robotics-logo.svg) ![](https://developer.download.nvidia.com/images/isaac/lab/logo-mentee-robotics.png) ![NVIDIA industry partner - RAI Institute](https://developer.download.nvidia.com/images/logos/rai-logo.svg) [![ NVIDIA industry partner - Skild AI](https://developer.download.nvidia.com/images/isaac/lab/logo-skild-ai.png)](https://www.skild.ai/) ![NVIDIA industry partner - UCR](https://developer.download.nvidia.com/images/isaac/lab/logo-ucr.svg) ![NVIDIA industry partner - X-Humanoid](https://developer.download.nvidia.com/images/logos/x-humanoid-logo.svg) * * * ## More Resources ![Decorative image representing forums](https://developer.download.nvidia.com/images/omniverse/m48-people-group.svg) ### Explore the Community ![](https://developer.download.nvidia.com/images/isaac/m48-certification-ribbon-2-256px-blk.png) ### Get Training and Certification ![](https://developer.download.nvidia.com/images/isaac/m48-ai-startup-256px-blk.png) ### Join the Program for Startups * * * ## Latest Isaac Lab News ## Get started with NVIDIA Isaac Lab today. [Download Now](https://github.com/isaac-sim/IsaacLab "Download Now")[Documentation](https://isaac-sim.github.io/IsaacLab/ "Documentation") ## FAQs The Isaac Lab framework is open-sourced under the [BSD-3-Clause license](https://opensource.org/licenses/BSD-3-Clause). Isaac Sim™ is a comprehensive robotics simulation platform built on NVIDIA Omniverse that provides high-fidelity simulation with advanced physics and photorealistic rendering. It focuses on synthetic data generation (SDG) and testing and validation (SIL/HIL) and is a reference template for custom robotics simulators. In contrast, Isaac Lab is a lightweight, open-source framework built on top of Isaac Sim, specifically optimized for robot learning workflows and designed to simplify common tasks in robotics research like reinforcement learning, imitation learning, and motion planning. If you’re an existing NVIDIA Isaac Gym (predecessor of Isaac Lab) user, we recommend migrating to Isaac Lab to ensure you have access to the latest advancements in robot learning and a powerful development environment to accelerate your robot training efforts. Check out the [migration guide](https://isaac-sim.github.io/IsaacLab/main/source/migration/migrating_from_isaacgymenvs.html) from Isaac Gym environments to Isaac Lab. Yes, Isaac Lab and MuJoCo are complementary. MuJoCo's ease of use and lightweight design allow for rapid prototyping and deployment of policies and Isaac Lab can complement it when you want to create more complex scenes, scaling massively parallel environments with GPUs and high-fidelity sensor simulations with RTX rendering. NVIDIA and MuJoCo are actively exploring advancing technical collaborations, stay tuned for future announcements.