List your company

ResearchFormerly WizWand

hopper

Benchmarks

TaskDatasetSOTA resultTrendResults

Reinforcement Learning

Hopper v5

3,732.5Average Return

101

Offline Reinforcement Learning

hopper medium

3,729Normalized Score

68

Offline Reinforcement Learning

hopper medium-replay

113Normalized Score

55

Offline Reinforcement Learning

Hopper medium-expert

114Normalized Score

35

Offline Reinforcement Learning

Hopper D4RL v2 (offline)

100.8Average Score

32

Reinforcement Learning

Hopper v4

27,721,263Average Return

30

Offline Reinforcement Learning

Hopper Medium JointNoise Shift

109.803Average Return

27

Offline Reinforcement Learning

Hopper Medium BodyMass Shift

82.786Average Return

27

Offline Reinforcement Learning

1T10S Hopper (Medium-Expert)

111.587Score

26

Offline Reinforcement Learning

1T10S Hopper (Medium-Replay)

98.988Score

26

Offline Reinforcement Learning

Hopper 1T10S (Medium)

101.244Score

26

Reinforcement Learning

Hopper v3

4,104Average Final Return

26

Time Series Forecasting

Hopper MuJoCo D (test)

0.43MSE

24

Offline Reinforcement Learning

hopper Mixed Dataset

108Normalized Reward

24

Hopper IID (test)

1,859Mean Episode Reward

24

Locomotion Control

Hopper sigma 0.3 (test)

1,368Episode Reward

24

Hopper

100Convergence (%)

20

Offline Reinforcement Learning

Hopper expert

112.8Normalized Score

19

Offline Reinforcement Learning

Hopper Medium-Expert BodyMass Shift

77.279Average Return

18

Offline Reinforcement Learning

Hopper Medium-Replay JointNoise Shift

93.704Average Return

18

Offline Reinforcement Learning

Hopper Medium-Expert 1T10S

109.803Average Return

18

Offline Reinforcement Learning

Hopper Medium-Replay 1T10S

93.704Average Return

18

Offline Reinforcement Learning

Hopper Medium 1T10S

78.325Average Return

18

Continuous Control

Hopper 3-Dof

2,735Final Return

18

Locomotion Control

Hopper sigma 0.7 (test)

443Episode Reward

18