Datasets › DeepMind Control Suite

DeepMind Control Suite

Introduced by Yuval Tassa et al. in DeepMind Control Suite1 Jan 2018 archive 2025-07-28

The DeepMind Control Suite (DMCS) is a set of simulated continuous control environments with a standardized structure and interpretable rewards. The tasks are written and powered by the MuJoCo physics engine, making them easy to identify. Control Suite tasks include Pendulum, Acrobot, Cart-pole, Cart-k-pole, Ball in cup, Point-mass, Reacher, Finger, Hooper, Fish, Cheetah, Walker, Manipulator, Manipulator extra, Stacker, Swimmer, Humanoid, Humanoid_CMU and LQR.

Source: Unsupervised Learning of Object Structure and Dynamics from Videos Image Source: https://arxiv.org/abs/1801.00690

Benchmarks archive 2025-07-28

All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Continuous Control DeepMind Cheetah Run (Images) DreamerV1 Return 800 — — 4 Compare
Continuous Control DeepMind Cup Catch (Images) DrQ Return 963 Image Augmentation Is All You Need: Regularizing Deep... denisyarats/drq +3 2 Compare
Continuous Control DeepMind Walker Walk (Images) DrQ Return 921 Image Augmentation Is All You Need: Regularizing Deep... denisyarats/drq +3 2 Compare

Papers archive 2025-07-28

3 shown of 3 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 364. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels 4 3 28 Apr 2020 ran 6 of 10 samples (4 unverified; 8 pointer-only for licence)
Learning Latent Dynamics for Planning from Pixels 9 2 12 Nov 2018 ran 2 of 7 samples (5 unverified; 1 pointer-only for licence)
007: Democratically Finding The Cause of Packet Drops 1 1 not harvested

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Apache 2.0

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • DeepMind Cartpole Balance (Images)
  • DeepMind Cartpole Swingup (Images)
  • DeepMind Finger Spin (Images)
  • DeepMind Cheetah Run (Images)
  • DeepMind Cup Catch (Images)
  • DeepMind Walker Walk (Images)
  • DeepMind Control Suite

7 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections