Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

DeepMind Control Suite dataset and benchmarks – Page 3 · SOTA2 Research

Research Datasets

DeepMind Control Suite

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Finger Turn Hard

DeepMind Control Suite in-distribution

298.73Average Return

7

DeepMind Control Suite (in-distribution)

116.05Average Return

7

Cartpole Swingup

DeepMind Control Suite (in-distribution)

608.38Average Return

7

DeepMind Control Suite Imagined Rewards Latent Imagination (train)

687.1Cheetah-Run Score

6

DeepMind Control Suite (Evaluation Mode)

798.6Cheetah Run Score

6

Finger Turn Easy

DeepMind Control Suite (DMC)

77,300Steps to 80% Return (k)

6

Cartpole Balance Sparse

DeepMind Control Suite (DMC)

158,300Steps to 80% Proficiency

6

DeepMind Control Suite (DMC)

706,700Steps

6

DeepMind Control Suite (DMC)

730.1Steps (k)

6

DeepMind Control Suite (DMC)

205,000Steps to 80% Return (k)

6

Pendulum Swingup

DeepMind Control Suite (DMC)

76,600Steps (k)

6

Finger Turn Hard

DeepMind Control Suite (DMC)

1,493.3Steps (k)

6

Finger Turn Easy

DeepMind Control Suite (DMC)

166.4Steps (k)

6

DeepMind Control Suite (DMC)

102.3Steps to 80% Return (k)

6

Cartpole Swingup

DeepMind Control Suite (DMC)

332,600Steps (k)

6

Cartpole Balance

DeepMind Control Suite (DMC)

1,903.3Steps to 80% Return (k)

6

Acrobot Swingup

DeepMind Control Suite (DMC)

525,500Steps to 80% Return

6

Continuous Control

DeepMind Control Suite (test)

596Acrobot Swingup Score

6

Reinforcement Learning

DeepMind Control Suite hopper_hop medium

6Episode Return

6

Reinforcement Learning

DeepMind Control Suite finger_spin medium

775Episode Return

6

Reinforcement Learning

DeepMind Control Suite cartpole_swingup medium

834Episode Return

6

Reinforcement Learning

DeepMind Control Suite reacher_hard

925Episode Return

6

Reinforcement Learning

DeepMind Control Suite reacher_hard medium

929Episode Return

6

Reinforcement Learning

DeepMind Control Suite reacher_hard, easy

939Episode Return

6

Reinforcement Learning

DeepMind Control Suite cheetah_run hard

472Episode Return

6

Page 3 of 7

Popular tasks

Continuous Control Reinforcement Learning Offline Reinforcement Learning Locomotion Cheetah Run

Follow for updates

Join SOTA2 Contact