MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

The following platforms are currently supported:

• Linux with Python 3.5.2. See the Dockerfile for the canonical list of system dependencies. Support for Python 3.6 is planned.
• OS X with Python 3.5.2. Support for Python 3.6 is planned.
• Windows (experimental) with Python 3.5.2. See the Appveyor file for the canonical list of dependencies.

Python 2 has been desupported since 1.50.1.0. Python 2 users can stay on the 0.5 branch. The latest release there is 0.5.7 which can be installed with pip install mujoco-py==0.5.7.

1. Obtain a 30-day free trial on the MuJoCo website or free license if you are a student. The license key will arrive in an email with your username and password.
2. Download the MuJoCo version 1.50 binaries for Linux, OSX, or Windows.
3. Unzip the downloaded mjpro150 directory into ~/.mujoco/mjpro150, and place your license key (the mjkey.txt file from your email) at ~/.mujoco/mjkey.txt.

To include mujoco-py in your own package, add it to your requirements like so:

mujoco-py<1.50.2,>=1.50.1

To play with mujoco-py interactively, follow these steps:

$ pip install -U 'mujoco-py<1.50.2,>=1.50.1'
$ python
import mujoco_py
from os.path import dirname
model = mujoco_py.load_model_from_path(dirname(dirname(mujoco_py.__file__))  +"/xmls/claw.xml")
sim = mujoco_py.MjSim(model)

print(sim.data.qpos)
# [ 0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.]

sim.step()
print(sim.data.qpos)
# [  2.09217903e-06  -1.82329050e-12  -1.16711384e-07  -4.69613872e-11
#   -1.43931860e-05   4.73350204e-10  -3.23749942e-05  -1.19854057e-13
#   -2.39251380e-08  -4.46750545e-07   1.78771599e-09  -1.04232280e-08]

See the full documentation for advanced usage.

A number of examples demonstrating some advanced features of mujoco-py can be found in examples/. These include:

• body_interaction.py: shows interactions between colliding bodies
• disco_fetch.py: shows how TextureModder can be used to randomize object textures
• internal_functions.py: shows how to call raw mujoco functions like mjv_room2model
• markers_demo.py: shows how to add visualization-only geoms to the viewer
• serialize_model.py: shows how to save and restore a model
• setting_state.py: shows how to reset the simulation to a given state
• simpool.py: shows how MjSimPool can be used to run a number of simulations in parallel
• tosser.py: shows a simple actuated object sorting robot application

See the full documentation for advanced usage.

To run the provided unit and integrations tests:

make test

mujoco-py is maintained by the OpenAI Robotics team. Contributors include:

• Alex Ray
• Bob McGrew
• Jonas Schneider
• Jonathan Ho
• Peter Welinder
• Wojciech Zaremba