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 HalfCheetah dataset and benchmarks – Page 2 · SOTA2 Research

Research Datasets

MuJoCo HalfCheetah

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Meta-Reinforcement Learning

MuJoCo HalfCheetah Mass variation (test)

1,259CVaR 0.05 Return

7

Meta-Reinforcement Learning

MuJoCo HalfCheetah Velocity variation (test)

-184CVaR 0.05 Return

7

Continuous Control

MuJoCo HalfCheetah 10-p v4

80.5Normalized Return

6

Continuous Control

MuJoCo HalfCheetah 2-p v4

44.9Normalized Return

6

Continuous Control

MuJoCo HalfCheetah 4-p v4

54.7Normalized Return

6

Reinforcement Learning

Delayed MuJoCo HalfCheetah v2 (test)

8,451.2Average Return

6

Reinforcement Learning

MuJoCo HalfCheetah Sparse v2 (test)

924.9Max Average Return

6

Reinforcement Learning

MuJoCo Halfcheetah epsilon=0.15 (test)

5,048Natural Return

5

Reinforcement Learning

MuJoCo HalfCheetah v4

2,287Return

5

Offline Inverse Reinforcement Learning

MuJoCo halfcheetah (medium-exp)

12,174.61Average Reward

5

Continuous Control

MuJoCo HalfCheetah v3 (1M steps)

11,914Average Return

5

Continuous Control

MuJoCo HalfCheetah v3 (500K steps)

10,139Average Return

5

Policy Optimization

MuJoCo HalfCheetah H=40

49.1Return

5

Policy Optimization

MuJoCo HalfCheetah H=20

13.3Return

5

Policy Optimization

MuJoCo HalfCheetah H=10

2.8Return

5

Continuous Control

MuJoCo HalfCheetah H=40

84.1Normalized Return

5

Continuous Control

MuJoCo HalfCheetah H=20

13.3Normalized Return

5

Continuous Control

MuJoCo HalfCheetah H=10

260Normalized Return

5

Off-dynamics Reinforcement Learning

MuJoCo HalfCheetah 0.5 density dynamics shift (test)

10,308Reward

4

Dynamics Model Prediction

MuJoCo HalfCheetah medium-replay v2 (test)

1.411RMSE

4

Dynamics Model Prediction

MuJoCo HalfCheetah expert v2 (test)

2.287RMSE

4

Dynamics Model Prediction

MuJoCo HalfCheetah medium v2 (train)

0.309RMSE

4

Reinforcement Learning

MuJoCo HalfCheetah Medium

55Normalized Score

3

MuJoCo Halfcheetah (t = T)

2,694.9Average Return

3

MuJoCo Halfcheetah t = T/2 (shift)

1,526.7Average Return

3

Page 2 of 3

Popular tasks

Continuous Control Reinforcement Learning Locomotion Meta-Reinforcement Learning Policy Optimization

Follow for updates

Join SOTA2 Contact