OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Dm Control

Dm Control is a Python software stack for physics-based simulation and reinforcement-learning environments using MuJoCo. It includes MuJoCo bindings, a suite of RL environments, an interactive viewer, and tools for composing models and creating custom control tasks.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Dm Control — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Dm Control when a Python workflow needs MuJoCo physics, ready-made RL environments, interactive viewing, or components for defining custom control tasks.

Who it is for

  • Researchers training or evaluating reinforcement-learning agents in physics-based environments.
  • Robotics developers prototyping and inspecting control policies in simulation.
  • Educators creating tutorials or experiments around MuJoCo and reinforcement learning.

Documented uses

  • Use MuJoCo-backed reinforcement-learning environments for control experiments.
  • Compose or modify MJCF models in Python.
  • Build richer environments from reusable components.
  • View a simulation interactively or render it through a configured OpenGL backend.
  • Create additional locomotion tasks, including multi-agent soccer tasks.
Before you choose

Requirements & limits

The repository lists an Apache-2.0 license. Installation is documented through pip; editable installation is unsupported.

  • Choose a rendering backend before relying on rendered output: EGL, GLFW and OSMesa are supported, and at least one must be available.
  • The interactive viewer only works with GLFW; GLFW is not suitable for headless machines.
  • The package cannot be installed in editable mode because generated legacy components are incompatible with that installation method.
  • The Colaboratory tutorial offers an introductory learning route.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Dm Control from PyPI

Install the package using its documented standard pip route.

Before you start

  • A Python environment with pip.

Steps

  1. Run the command below.

    Documented command
    pip install dm_control

  2. Avoid editable installation with the command below; the package documents incompatibility with this mode.

    Documented command
    pip install -e

Expected outcome

The package is installed through the documented PyPI installation command.

Guide limitations

  • This is an installation guide; it does not cover running an environment.
  • Rendering requires at least one OpenGL backend. The interactive viewer requires GLFW, which does not work on headless machines.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
30 September 2026
Original website title
google-deepmind/dm_control · Official homepage title · retained in its source language
How we review sourcesSuggest a correction