Set Up Isaac Sim and Isaac Lab

Basic idea

Isaac Sim is a robotics simulation platform built on NVIDIA Omniverse that enables photorealistic, physically accurate simulations of robots and environments. It provides a comprehensive toolkit for robotics development, including physics simulation, sensor simulation, and visualization capabilities. Isaac Lab is a reinforcement learning framework built on top of Isaac Sim, designed for training and deploying RL policies for robotics applications.

Isaac Sim uses GPU-accelerated physics simulation to enable fast, realistic robot simulations that can run faster than real-time. Isaac Lab extends this with pre-built RL environments, training scripts, and evaluation tools for common robotics tasks like locomotion, manipulation, and navigation. Together, they provide an end-to-end solution for developing, training, and testing robotics applications entirely in simulation before deploying to real hardware.

What you'll accomplish

You'll build Isaac Sim from source on your hardware platform and set up Isaac Lab for reinforcement learning experiments. This includes compiling the Isaac Sim engine, configuring the development environment, and running a sample RL training task to verify the installation.

What to know before starting

Required:

• Experience building software from source using CMake and build systems
• Familiarity with Linux command line operations and environment variables
• Understanding of Git version control and Git LFS for large file management
• Basic knowledge of Python package management and virtual environments

Optional:

• Familiarity with robotics simulation concepts

Supported hardware platforms

Use the matrix below to confirm your hardware platform, recommended default local settings, and whether multi-node applies.

Prerequisites

Hardware requirements

• Supported hardware platform — see Supported hardware platforms matrix above
• At least 50 GB available storage for Isaac Sim build artifacts and dependencies

Software requirements

• OS matching the Supported hardware platforms matrix above
• GCC/G++ 11 compiler: gcc --version shows version 11.x
• Git and Git LFS installed: git --version and git lfs version succeed
• Network access to clone repositories from GitHub and download dependencies
• Pinned versions: Isaac Sim v6.2.0 and Isaac Lab 3.0 at commit 4b081ff69eee56bb65137b762f2d265eb92ec36e from release/3.0.0, as shown in the Instructions. Use this Lab revision, which targets Sim 6.2; the earlier v3.0.0-EA tag targets Sim 6.1. Do not substitute the default develop branches

Ancillary files

All required assets can be found in the Isaac Sim and Isaac Lab repositories on GitHub:

• Isaac Sim repository — Main Isaac Sim source code
• Isaac Lab repository — Isaac Lab RL framework

Time & risk

• Estimated time: 30 MIN (including build time, which typically takes 10–15 minutes)
• Risk level: Medium
  • Large repository clones with Git LFS may fail due to network issues
  • Build process requires significant compilation time and may encounter dependency issues
  • Build artifacts consume substantial disk space
• Rollback: Remove the Isaac Sim build directory to free space. Git repositories can be deleted and re-cloned if needed.
• Last Updated: 10/14/2026
  • Pinned Isaac Sim to v6.2.0 and Isaac Lab to a fixed 3.0 revision, and updated the training commands for the Isaac Lab 3.0 CLI
  • Build Isaac Sim from source and set up Isaac Lab with a sample reinforcement learning training run on supported hardware platforms