#11 · Primary category： Robotics & Embodied AI Simulation
dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Project last updated：08/29/26
GitHub Stars
4.7K
Forks
761
Contributors
61
License
Apache-2.0
Why we included this project
dm_control is the environment stack Google DeepMind built on top of the MuJoCo physics engine, and years of RL research have hardened both the Python bindings and the bundled benchmark tasks. If you train policies for simulated robots, the included suite covers the classic continuous control problems, while mjcf and composer let you build your own environments by composing reusable parts instead of hand-writing each scene. The interactive viewer and headless rendering backends (EGL, GLFW, OSMesa) mean you can debug in a window or run the same task across a training cluster without changing code. One quirk worth knowing before you start: it installs from PyPI but not in editable mode, so plan your setup accordingly.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
genesis-world
Simulation platform for general-purpose robotics & embodied AI learning.
lerobot
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
ml-agents
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
AirSim
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
carla
Open-source simulator for autonomous driving research.