This workshop was designed to be able to work fully in collab notebooks with internet access. If you would like to install on your local computer see install instructions at the bottom.
-
Introduction to MuJoCo
- This notebook introduces the basics of MuJoCo models, simultation and rendering:
-
Flybody Example
- The flybody notebook covers the basics of working with the biomechanical model of the fruitfly created by Janelia:
- MuJoCo MJX
- MJX is the version of MuJoCo that runs JAX in the backend and enables GPU simulations and environments:
- MJX is the version of MuJoCo that runs JAX in the backend and enables GPU simulations and environments:
-
DM_control tutorial:
-
The LQR tutorial synthesizes a linear-quadratic controller, balancing a humanoid on one leg:
-
The least-squares tutorial explains how to use the Python-based nonlinear least-squares solver:
-
The differentiable physics tutorial trains locomotion policies with analytical gradients automatically derived from MuJoCo's physics step:
Clone the git repo from:
git clone https://github.com/elliottabe/mujoco_workshop2024.git
Enter the mujoco_workshop2024 folder:
cd mujoco_workshop2024
To install the repo there is a conda environment that will install the necessary packages. Make sure you are in the pytorchGLM Github directory.
Use command:
conda env create -f environment.yaml
After installing activate the conda environment:
conda activate mujoco_workshop
After installing the conda environment. Run this command to install pip reqruirements:
pip install -r requirements.txt