mujoco-warp 0.0.2

MuJoCo Warp (MJWarp)

MuJoCo Warp (MJWarp)

MJWarp is a GPU-optimized version of the MuJoCo physics simulator, designed for NVIDIA hardware.

[!NOTE] MJWarp is in Beta and under active development:

• MJWarp developers will triage and respond to bug report and feature requests.
• MJWarp is mostly feature complete but requires performance optimization, documentation, and testing.
• The intended audience during Beta are physics engine enthusiasts and learning framework integrators.

MJWarp uses NVIDIA Warp to circumvent many of the sharp bits in MuJoCo MJX. MJWarp is integrated into both MJX and Newton.

MJWarp is maintained by Google DeepMind and NVIDIA.

Getting started

There are a few ways to jump into using MuJoCo Warp:

• For a quick overview of MJWarp's API and design, please see our colab that introduces the basics.
• For more details and advanced topics on using MJWarp, see the MuJoCo Warp documentation.

If you would like to train robot policies using MJWarp, consider using a robotics research toolkit that integrates it:

• MuJoCo Playground integrates MJWarp via MJX
• Isaac Lab integrates MJWarp via Newton
• mjlab integrates MJWarp directly

Installing for development

MuJoCo Warp is currently supported on Windows or Linux on x86-64 architecture (to be expanded to more platforms and architectures soon).

CUDA

The minimum supported CUDA version is 12.4.

Linux

git clone https://github.com/google-deepmind/mujoco_warp.git
cd mujoco_warp
python3 -m venv env
source env/bin/activate
pip install --upgrade pip
pip install uv

Windows (native Python only, not MSYS2 or WSL)

git clone https://github.com/google-deepmind/mujoco_warp.git
cd mujoco_warp
python -m venv env
.\env\Scripts\Activate.ps1  # For MSYS2 Python: env\bin\activate
pip install --upgrade pip
pip install uv

Then install MJWarp in editable mode for local development:

uv pip install -e .[dev,cuda]

Now make sure everything is working:

pytest

Should print out something like XX passed in XX.XXs at the end!

If you plan to write Warp kernels for MJWarp, please use the kernel_analyzer vscode plugin located in contrib/kernel_analyzer. Please see the README.md there for details on how to install it and use it. The same kernel analyzer will be run on any PR you open, so it's important to fix any issues it reports.

Compatibility

The following features are implemented:

Category	Feature
Dynamics	Forward, Inverse
Transmission	All
Actuator Dynamics	All except USER
Actuator Gain	All except USER
Actuator Bias	All except USER
Geom	All
Constraint	All
Equality	All
Integrator	All except IMPLICIT
Cone	All
Condim	All
Solver	All except PGS, noslip
Fluid Model	All
Tendon Wrap	All
Sensors	All except GEOMDIST, GEOMNORMAL, and GEOMFROMTO with BOX-BOX; PLUGIN, USER
Flex	VERTCOLLIDE, ELASTICITY
Mass matrix format	Sparse and Dense
Jacobian format	DENSE only (row-sparse, no islanding yet)

Differentiability via Warp is not currently available.

Viewing simulations

Explore MuJoCo Warp simulations using an interactive viewer:

mjwarp-viewer benchmark/humanoid/humanoid.xml

This will open a window on your local machine that uses the MuJoCo native visualizer.

Benchmarking

Benchmark as follows:

mjwarp-testspeed benchmark/humanoid/humanoid.xml

To get a full trace of the physics steps (e.g. timings of the subcomponents) run the following:

mjwarp-testspeed benchmark/humanoid/humanoid.xml --event_trace=True

mjwarp-testspeed has many configuration options, see mjwarp-testspeed --help for details.