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

MuJoCo dataset and benchmarks – Page 4 · SOTA2 Research

Research Datasets

MuJoCo

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Reinforcement Learning

MuJoCo (test)

1Fraction of Teacher Score

9

Offline Reinforcement Learning

MuJoCo D4RL (Aggregate)

82.9Mean Normalized Score

9

Continuous Control

MuJoCo

4,828Ant-v5

9

Optical Flow Estimation

MuJoCo In-distribution

4.88EPE (First-Frame)

8

MuJoCo In-distribution

91Segmentation Map IoU (First-Frame)

8

Object Composition

MuJoCo In-distribution

99Object Composition Accuracy

8

Black-box Optimization

MuJoCo Control

98.2Normalized Performance

8

Cross-domain Offline Reinforcement Learning

MuJoCo Ant

55.4Performance (ant-m to m)

8

Cross-domain Offline Reinforcement Learning

MuJoCo Hopper

66Hopper Performance (m -> m)

8

Humanoid Motion Tracking

MuJoCo 101 held-out motion sequences (test)

90.6CR (%)

8

Continuous Control

MuJoCo Hopper v5

3,671.77Average Return

8

Offline Reinforcement Learning

MuJoCo hopper-e-kinematic

57.8Normalized Score

8

Irregular-to-regular Time Series Generation

MuJoCo (70% missing)

0.393DS

8

Irregular-to-regular Time Series Generation

MuJoCo (50% missing)

0.375DS

8

Irregular-to-regular Time Series Generation

MuJoCo (30% missing)

0.293Distribution Score (DS)

8

Non-Stationary Reinforcement Learning

MuJoCo Non-Stationary

1.24nAUC (Steady)

8

MuJoCo

7.5Recovery Time (%)

8

MuJoCo

4.7Recovery Time (%)

8

MuJoCo

4.4Recovery Time (%) (Abrupt Change)

8

MuJoCo

4.7Recovery Time (%)

8

Circular trajectory tracking under step force

MuJoCo Menagerie Franka FR3 model Benchmark I

11.5RMS Total Error (mm)

7

Inverse Reinforcement Learning

MuJoCo Walker

73Normalized Return

7

Inverse Reinforcement Learning

MuJoCo Half Cheetah

1.07Normalized Return

7

Inverse Reinforcement Learning

MuJoCo Ant

1.03Normalized Return

7

Multi-objective Reinforcement Learning

MuJoCo 8 continuous-action tasks MO-Gymnasium (aggregated)

3.25Hypervolume (HV)

7

Page 4 of 10

Popular tasks

Continuous Control Reinforcement Learning Locomotion Offline Reinforcement Learning Inverse Reinforcement Learning

Follow for updates

Join SOTA2 Contact