dm_control
- Software
- Simulators
- Library
A set of Python libraries from Google DeepMind for physics-based simulation and reinforcement learning environments, built on the MuJoCo physics engine.
Made by Google DeepMind.
Source on GitHub: github.com/google-deepmind/dm_control (opens in a new tab). Facts read at commit 773d5b5 (opens in a new tab).
Licenses
- Code
- Apache-2.0 (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (Apache-2.0) at commit 773d5b5 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
What it does
- Provides Python bindings to the MuJoCo physics engine.
- Offers a suite of reinforcement learning environments powered by MuJoCo.
- Includes an interactive environment viewer.
- Lets users compose and modify MuJoCo MJCF models in Python.
- Includes a composer library for building RL environments from reusable components.
- Adds locomotion and multi-agent soccer tasks for more complex control problems.
Written by Robotheca from the project's README (opens in a new tab) at commit 773d5b5.
Getting started
- Difficulty
- Intermediate
- Hardware it needs, as the project states it
- Rendering needs at least one OpenGL backend: GLFW with a windowing system, EGL for headless hardware rendering (EGL driver with EXT_platform_device support, such as recent Nvidia drivers), or OSMesa for software rendering. The viewer works only with GLFW, which does not run on headless machines.
- How to start
- The project's README (opens in a new tab)
Maintenance
- Status
- Active: a commit in the last 90 days
- Newest commit
- 14 Oct 2026 on main
- Latest release
- 1.0.49: Upgrade to MuJoCo 3.16.0 (14 Oct 2026)
Checked on GitHub on 16 Oct 2026.
Links
Robots on Robotheca that use it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.