Isaac Sim on Windows - gkgkgk1215/else GitHub Wiki

Download files

• Reference: https://docs.isaacsim.omniverse.nvidia.com/4.5.0/installation/download.html
• Download Isaac Sim 4.5.0
• Download Isaac Sim Assets

Install Isaac Sim

• https://docs.isaacsim.omniverse.nvidia.com/4.5.0/installation/install_workstation.html

• In cmd console,

mkdir C:\isaacsim
cd %USERPROFILE%/Downloads
tar -xvzf "[email protected]+release.19112.f59b3005.gl.windows-x86_64.release.zip" -C C:\isaacsim
cd C:\isaacsim
post_install.bat
isaac-sim.selector.bat

• If error regarding torch, install and upgrade:

cd \isaacsim
python.bat -m pip install --upgrade pip
python.bat -m pip install pillow torch
pip install --upgrade --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/cu128

Install Assets

• https://docs.isaacsim.omniverse.nvidia.com/4.5.0/installation/install_faq.html

• In cmd console,

mkdir C:\isaacsim_assets
cd %USERPROFILE%/Downloads
tar -xvzf "[email protected]+release.19112.f59b3005.zip" -C C:\isaacsim_assets
tar -xvzf "[email protected]+release.19112.f59b3005.zip" -C C:\isaacsim_assets
tar -xvzf "[email protected]+release.19112.f59b3005.zip" -C C:\isaacsim_assets

Isaac Lab 2.0

• Download Git and install: https://git-scm.com/downloads

• Download Miniconda and install: https://www.anaconda.com/download

• While installing, it is required to select "Just Me" and "Add Miniconda3 to my PATH environment variable" option.

• Accept terms of service

conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/main
conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/r
conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/msys2

• Download Isaac Lab: https://github.com/isaac-sim/IsaacLab.git

• Move the files to C:\IsaacLab

• Install Isaac Lab: https://isaac-sim.github.io/IsaacLab/main/source/setup/installation/binaries_installation.html

• Create symbolic link (admin permission might be required):

cd IsaacLab
mklink /D _isaac_sim "C:\isaacsim"

• Create conda env

isaaclab.bat --conda env_isaaclab
conda activate env_isaaclab

• (may not required) Install Cuda Toolkit: https://developer.nvidia.com/cuda-downloads?target_os=Windows&target_arch=x86_64&target_version=11&target_type=exe_local

• Install IsaacLab (ignore the dependency error, nvidia-sri-usd ...)

isaaclab.bat --install

• For 50 series GPUs, please use the latest PyTorch nightly build instead of PyTorch 2.5.1, which comes with Isaac Sim:

pip install --upgrade --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/cu128

• Check the installation of IsaacLab

:: Option 1: Using the isaaclab.bat executable
:: note: this works for both the bundled python and the virtual environment
isaaclab.bat -p scripts\tutorials\00_sim\create_empty.py

:: Option 2: Using python in your virtual environment
python scripts\tutorials\00_sim\create_empty.py

• Test training

isaaclab.bat -p scripts/reinforcement_learning/rsl_rl/train.py --task=Isaac-Ant-v0 --headless
isaaclab.bat -p scripts/reinforcement_learning/rsl_rl/train.py --task=Isaac-Velocity-Rough-Anymal-C-v0 --headless'