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

hopper dataset and benchmarks – Page 7 · SOTA2 Research

Research Datasets

hopper

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Reinforcement Learning

Hopper v5

1,005Return

5

Reinforcement Learning

Hopper v5 (strong-drift)

20.24Final Return

5

Continuous Control

Hopper-3d

2Completion Time (hours)

5

Trajectory Optimization

Hopper

26.4Computational Time (s)

5

Reinforcement Learning Surrogate Modeling

Hopper H (test)

89Reward Ratio

4

Continuous Action Prediction Generalization

Hopper 20x (aggregate)

0.744P

4

hopper expert v2

112Normalized Return

4

hopper random D4RL

31.5Normalized Return

4

Dynamics Prediction

Hopper

13.731MAE

4

Offline Reinforcement Learning

hopper kine-e

98.2Normalized Score

4

Offline Reinforcement Learning

hopper kine-me

56.3Normalized Score

4

Offline Reinforcement Learning

hopper kine-m

65.4Normalized Score

4

Offline Reinforcement Learning

hopper medium-expert-morph

78.6Score

4

Offline Reinforcement Learning

hopper medium-expert-kinematic

48.1Score

4

Offline Reinforcement Learning

hopper-expert-morph

100.3Score

4

Offline Reinforcement Learning

hopper expert-kinematic

95.5Score

4

Reinforcement Learning

Hopper

1,520.18Avg Reward

4

Reinforcement Learning

hopper 10-p

94.5Normalized Return

4

Reinforcement Learning

hopper 2-p

106Normalized Return

4

Reinforcement Learning

hopper 4-p

99Normalized Return

4

Safety-constrained control

Hopper deterministic rollout

0Violation Rate

3

Hopper non-stationary MuJoCo

498Final Reward

3

Reinforcement Learning

Hopper discrete-regime, exponential dwell

565Mean Evaluation Return

3

Trajectory Optimization

Hopper

1.265Reward (Per Step)

3

Hopper (In-Distribution)

389.142Mean Reward

3

Page 7 of 8

Popular tasks

Offline Reinforcement Learning Reinforcement Learning Locomotion Continuous Control Locomotion Control

Follow for updates

Join SOTA2 Contact