Walker
Benchmarks
TaskDatasetSOTA resultTrendResults
Walker
1,035.52Average Returns
38
Walker MuJoCo D (test)
0.73MSE
24
Walker IID (test)
1,909Mean Episode Reward
24
Walker sigma 0.1 (test)
1,909Episode Reward
24
Walker Gym-MuJoCo Medium-Expert D4RL
111.6Normalized Score
18
Walker sigma 0.7 (test)
289Episode Reward
18
Walker sigma 0.5 (test)
518Episode Reward
18
Walker sigma 0.3 (test)
908Episode Reward
18
Walker Medium Gym-MuJoCo D4RL
84.7Normalized Score
16
Walker URLB (downstream)
729Flip Success Score
12
Walker fixed linear adversary
5,256Average Performance
12
Walker MuJoCo (test)
1.69Normalized Worst-Case Reward
12
Walker fixed exponential adversary MuJoCo
5,310Average Performance
12
Walker MuJoCo (test)
5,724Worst-case Performance
12
Walker v1 (test)
2,603.59Total Reward
12
Walker Param-Sparse
82Average Return
10
Walker-Param
140Average Return
10
Walker robot
15.3Average Return
9
Walker Run
34.97Mean Performance
8
Walker
0.21Regret
8
Walker (Ceval-in)
849AER
8
Walker C (train)
845AER
8
Walker V
61,227Average Return
6
Walker-P
1,123,176Average Return
6
Walker sigma=0.7
504Reward
6