List your company

ResearchFormerly WizWand

MuJoCo

Benchmarks

TaskDatasetSOTA resultTrendResults

Offline Reinforcement Learning under Gravity Shift

MuJoCo Hopper

73.4Normalized Return

104

Offline Reinforcement Learning under Gravity Shift

MuJoCo HalfCheetah

83.05Normalized Return

104

Offline Reinforcement Learning

MujoCo halfcheetah

62.86Normalized Return

97

Offline Reinforcement Learning under Gravity Shift

MuJoCo Walker2d

65.2Normalized Return

72

Offline Reinforcement Learning

MuJoCo Hopper

66.82Normalized Score

64

Offline Reinforcement Learning

MuJoCo Walker2d

78.14Normalized Score

64

Offline Reinforcement Learning

MuJoCo Ant

79.25Normalized Score

64

Time Series Reconstruction

MuJoCo (test)

0.285MSE

51

Continuous Control

MuJoCo Ant v4

8,509Average Return

46

Continuous Control

MuJoCo Hopper v4

3,592Normalized Performance

28

Reinforcement Learning

MuJoCo Half-Cheetah

13,907Average Return

28

MuJoCo 70% Dropped (test)

0.008MSE

27

MuJoCo 50% Dropped (test)

0.008MSE

27

MuJoCo 30% Dropped (test)

0.008MSE

27

MuJoCo Regular (test)

0.006MSE

27

Offline Reinforcement Learning

MuJoCo hopper D4RL (medium-replay)

101.6Normalized Return

26

Offline Reinforcement Learning

MuJoCo walker2d-medium D4RL

92.5Normalized Return

26

Continuous Control

MuJoCo Ant

6,336Average Reward

26

Continuous Control

MuJoCo HalfCheetah

13,144Average Reward

25

Reinforcement Learning

MuJoCo HumanoidStandup

130,892Average Performance

24

Reinforcement Learning

MuJoCo Ant

7,889.1Average Return

24

Reinforcement Learning

MuJoCo Hopper

3,876Average Return

24

Offline Reinforcement Learning

MuJoCo hopper-medium D4RL

101.3Normalized Return

22

3D Dynamics Prediction

MuJoCo Fall-and-rebound scenario

0.005Translation Error (m)

20

Offline Reinforcement Learning

MuJoCo halfcheetah-medium-replay D4RL

54.1Normalized Return

20