List your company
ResearchFormerly WizWand

D4RL

Benchmarks

TaskDatasetSOTA resultTrendResults
Offline Reinforcement Learning
D4RL halfcheetah-medium-expert
110Normalized Score
Offline Reinforcement Learning on D4RL halfcheetah-medium-expert performance trend
169
Offline Reinforcement Learning
D4RL hopper-medium-expert
119.2Normalized Score
Offline Reinforcement Learning on D4RL hopper-medium-expert performance trend
161
Offline Reinforcement Learning
D4RL walker2d-medium-expert
116.1Normalized Score
Offline Reinforcement Learning on D4RL walker2d-medium-expert performance trend
140
Offline Reinforcement Learning
D4RL Medium-Replay Hopper
110.6Normalized Score
Offline Reinforcement Learning on D4RL Medium-Replay Hopper performance trend
109
Offline Reinforcement Learning
D4RL Medium-Replay HalfCheetah
95.8Normalized Score
Offline Reinforcement Learning on D4RL Medium-Replay HalfCheetah performance trend
97
Offline Reinforcement Learning
D4RL halfcheetah-random
45.4Normalized Score
Offline Reinforcement Learning on D4RL halfcheetah-random performance trend
94
Locomotion
D4RL walker2d-medium-expert
5,421.3Normalized Score
90
walker2d locomotion
D4RL walker2d medium-replay
106.2Normalized Score
Walker2d Locomotion Control on D4RL walker2d medium-replay performance trend
78
Offline Reinforcement Learning
D4RL antmaze-umaze (diverse)
93.5Normalized Score
Offline Reinforcement Learning on D4RL antmaze-umaze (diverse) performance trend
74
hopper locomotion
D4RL hopper medium-replay
105.12Normalized Score
Hopper Locomotion on D4RL hopper medium-replay performance trend
71
Locomotion
D4RL walker2d-medium
88.1Normalized Score
Locomotion on D4RL walker2d-medium performance trend
70
Locomotion
D4RL halfcheetah-medium
63.5Normalized Score
70
Locomotion
D4RL halfcheetah-medium-replay
0.887Normalized Score
68