List your company

ResearchFormerly WizWand

D4RL MuJoCo walker2d

Benchmarks

TaskDatasetSOTA resultTrendResults

Offline Reinforcement Learning

D4RL MuJoCo walker2d medium v2

95.5Normalized Score

17

Offline Reinforcement Learning

D4RL MuJoCo walker2d random v2

23.6Normalized Score

17

Offline Reinforcement Learning

D4RL MuJoCo Walker2d medexp standard

115.5Normalized Score

8

Offline Reinforcement Learning

D4RL MuJoCo Walker2d medium standard

92.5Normalized Score

8