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 6 · SOTA2 Research

Research Datasets

hopper

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Continuous Control

Hopper v2 (test)

2,711Average Return

6

Robotic Control

Hopper

93.85AP

6

Offline multitask Reinforcement Learning

Hopper jump

832Average Episodic Return

6

Offline multitask Reinforcement Learning

Hopper stand

800Average Episodic Return

6

Offline multitask Reinforcement Learning

Hopper hopper-forward

982Average Episodic Return

6

Hopper v2

4,408Average Return

6

Robotic Control

Hopper V

1,545,104Average Return

6

Hopper sigma=0.7

643Reward

6

Hopper sigma=0.5

1,017Reward

6

Hopper sigma=0.1

1,272Cumulative Reward

6

Hopper Complex

100Safety Rate

5

Hopper Simple

100Safety Rate

5

Hopper Hard (test)

0.456Max Velocity Magnitude

5

Hopper-Simple (test)

0.033Max Velocity Magnitude

5

Constrained Sample Generation

Hopper-Simple

1Safety

5

Action Generation

Hopper Hard

0.005Safety Violation Rate

5

Locomotion control

Hopper v5

35.64Evaluation Cost

5

Continuous Control (MuJoCo)

Hopper v4

3,240Mean Episodic Return

5

Goal-conditioned Reinforcement Learning (G3_efficient)

hopper medium v2

31.8Goal-conditioned Return

5

Goal-conditioned Reinforcement Learning (G2_balanced)

hopper medium v2

1.564Goal-conditioned Return

5

Goal-conditioned Reinforcement Learning (G1_speed)

hopper medium v2

2.184Goal-conditioned Return

5

Goal-conditioned Reinforcement Learning (G3_efficient)

hopper medium-expert v2

0.336Goal-conditioned Return

5

Goal-conditioned Reinforcement Learning (G2_balanced)

hopper medium-expert v2

1.678Goal-Conditioned Return

5

Goal-conditioned Reinforcement Learning (G1_speed)

hopper medium-expert v2

2.455Goal-conditioned Return

5

Continuous Control

Hopper v4

3,515.3Maximum Average Return

5

Page 6 of 8

Popular tasks

Offline Reinforcement Learning Reinforcement Learning Locomotion Continuous Control Locomotion Control

Follow for updates

Join SOTA2 Contact