D4RL MuJoCo
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
D4RL MuJoCo hopper-medium-expert
112.3Normalized Score
47
D4RL MuJoCo Hopper-mr v2 (medium-replay)
104.4Avg Normalized Score
36
D4RL MuJoCo Walker2d medium-expert v2
117.2Average Normalized Score
31
D4RL MuJoCo Hopper-m v2 (medium)
107.4Avg Normalized Score
31
D4RL MuJoCo Walker2d-mr v2 (medium-replay)
95.6Average Normalized Score
29
D4RL MuJoCo Halfcheetah-mr v2 (medium-replay)
72.1Avg Normalized Score
24
D4RL Mujoco Hopper-Medium-Expert v2
111.9Normalized Score
22
D4RL MuJoCo hopper-medium-replay v2
99.7Normalized Score
19
D4RL MuJoCo v2 (test)
77.6HalfCheetah-Medium Score
19
D4RL Mujoco Halfcheetah-Medium-Expert v2
94.3Normalized Score
17
D4RL MuJoCo Walker2d-e v2 (expert)
110.2Normalized Score
14
D4RL MuJoCo Walker2d-m medium v2
86.8Average Normalized Score
14
D4RL MuJoCo Halfcheetah-m v2 (medium)
48.3Average Normalized Score
14
D4RL MuJoCo Hopper-e v2 (expert)
110Average Normalized Score
14
D4RL MuJoCo Locomotion Domain v2
96Return (HalfCheetah, M-E)
10
D4RL MuJoCo walker2d-medium-expert v0
108.4Normalized Score
8
D4RL MuJoCo hopper-medium-expert v0
112.7Normalized Avg Score
8
D4RL MuJoCo hopper-medium v0
100.4Avg Score (Normalized)
8
D4RL MuJoCo hopper-random v0
11.9Normalized Score
8
D4RL MuJoCo hopper
3,281Return
7
D4RL MuJoCo walker
6,081Return
7
D4RL MuJoCo halfcheetah-medium-replay v2
70.7Normalized Score
7
D4RL MuJoCo reward-free v2 (medium, medium-replay, medium-expert)
58.4Hopper-v2 Return (medium)
7
D4RL MuJoCo reward-free v2 (medium, medium-replay, medium-expert)
110.4Hopper-v2 (m) Score
7
D4RL MuJoCo (medium-expert)
86.5Normalized Return
4