Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Offline Reinforcement Learning on MujoCo halfcheetah

60.8Normalized Return

Real Dataset

-5.96811.36628.746.034Dec 8, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
60.8
2025.12
48.8
2025.12
48.5
2025.12
48.3
2025.12
45.2
2025.12
38.7
2025.12
36.9
2025.12
27.4
2025.12
25.2
2025.12
5.6
2025.12
5.3
2025.12
4.5
2025.12
4
2025.12
3.6
2025.12
3
2025.12
3
2025.12
2.5
2025.12
2.4
2025.12
1.8
2025.12
1.8
2025.12
1.7
2025.12
1.6
2025.12
1.5
2025.12
1.3
2025.12
0.4
2025.12
0.2
2025.12
0
2025.12
0
2025.12
0
2025.12
0
2025.12
0
2025.12
-2.8
2025.12
-3.4