List your company

ResearchFormerly WizWand

D4RL POMDP Walker2d

Benchmarks

TaskDatasetSOTA resultTrendResults

Offline Reinforcement Learning

D4RL POMDP Walker2d Medium-Replay

66.8Normalized Score

6

Offline Reinforcement Learning

D4RL POMDP Walker2d Medium

74.3Normalized Score

6

Offline Reinforcement Learning

D4RL POMDP Walker2d Medium-Expert

106Normalized Score

6