List your company

ResearchFormerly WizWand

Swimmer

Benchmarks

TaskDatasetSOTA resultTrendResults

Reinforcement Learning

Swimmer

260.35Average Returns

24

Reinforcement Learning

Swimmer v3

359.79Mean Reward

15

Reinforcement Learning

Swimmer v5

98Average AUC (z-scored)

13

Reinforcement Learning

Swimmer v4

128.5Average Episodic Reward

12

Swimmer

3.59Relative Return Improvement

10

Simulator Benchmark Optimization

Swimmer

-339.62Median Performance

9

Continuous Control

Swimmer v5

119.3Average Episodic Reward

8

Imitation Learning from Observation

Swimmer v4

0.73AER

8

Continuous Control

6-link Swimmer

16.4Training Time (s)

6

Continuous Control

3-link Swimmer

4.6Training Time (s)

6

Multi-objective Reinforcement Learning

Swimmer-2

3.54Hypervolume (HV)

6

Reinforcement Learning

Swimmer-vel online downstream setting

1.65Normalized Reward

6

Safe Reinforcement Learning

Swimmer-vel (offline)

2.39Normalized Reward

6

Quality-Diversity

Swimmer

21.31GT QD Score

6

Continuous Control

Swimmer v2 (test)

354Average Return

6

Imitation Learning

Swimmer

141.1Mean Score

6

Reinforcement Learning

Swimmer (Gymnasium)

294.57Mean Best Reward

5

Continuous Control

Swimmer MuJoCo v5

114Max Return

5

Reinforcement Learning Surrogate Modeling

Swimmer (S) (test)

101Reward Ratio

4

Reinforcement Learning

Swimmer

294.57Mean Best Reward

4

Safe Reinforcement Learning

Swimmer Velocity tasks suite

36.32Average Reward

4

Reinforcement Learning

Swimmer Velocity tasks suite (test)

36.32Average Reward

4

Continuous Control

Swimmer6 (test)

-172Best Test Reward

3

Robot Co-design

Swimmer search phase

9.35D2C Score

3

Policy Improvement

Swimmer S

61Improvement Rate

2