0

DeepMind Control Suite

Active

A set of MuJoCo-based continuous-control RL tasks (cartpole, cheetah, walker, humanoid) - the standard benchmark for continuous-action policy learning.

Open
Publisher
Google DeepMind
Capabilities
EmbodiedPlanning
Domain
robotics
Format
Openenv
Size
28 tasks
License
Apache-2.0
Published
Jan 2018
Notable for
Benchmark for evaluating embodied and planning in the robotics domain.
Canonical
github.com/google-deepmind/dm_control
Also on
shimmy.farama.org/environments/dm_control

Cite

Notes

Only stored in your browser.

Related tools

1
View all

Implementations, trainers, datasets and scaffolds linked to this eval.

DM Control RL Env (Hugging Face)

Hugging Face

OpenEnv port of DeepMind's dm_control - MuJoCo-powered continuous control tasks (cartpole, walker, humanoid, dog, quadruped, manipulation) for embodied RL.

Trains towardRL EnvPlanningEmbodiedRobotics

Papers

2

DeepMind Control Suite

preprint · 2018

DeepMind's standardized MuJoCo-based continuous-control RL benchmark suite, the canonical evaluation for policy-gradient and model-based RL.

introduces

DeepMind Control Suite

preprint · 2018

DeepMind's standardized MuJoCo-based continuous-control RL benchmark suite, the canonical evaluation for policy-gradient and model-based RL.

FAQ

What is DeepMind Control Suite?
A set of MuJoCo-based continuous-control RL tasks (cartpole, cheetah, walker, humanoid) - the standard benchmark for continuous-action policy learning.
What capabilities does DeepMind Control Suite test?
DeepMind Control Suite evaluates embodied, planning.
How can a model improve its DeepMind Control Suite score?
Tools linked to DeepMind Control Suite on Sophon include DM Control RL Env (Hugging Face) - RL environments, datasets, and scaffolds that target this eval.
What license is DeepMind Control Suite under?
DeepMind Control Suite is available under Apache-2.0.