Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Offline Reinforcement Learning on D4RL Hopper random (Mean Normalized Score)
Loading...
33.4
Mean Normalized Score
VIPO
4.176
11.763
19.35
26.937
Dec 4, 2025
Mean Normalized Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Mean Normalized Score
VIPO
Method Category=Conser...
2025.12
33.4
ADMPO
Method Category=Conser...
2025.12
32.7
LEQ
Method Category=Conser...
2025.12
32.4
MOBILE
Method Category=Conser...
2025.12
31.9
MOPO
Method Category=Conser...
2025.12
31.7
CBOP
Method Category=Bayesi...
2025.12
31.4
APE-V
Method Category=Conser...
2025.12
31.3
SUMO
Method Category=Conser...
2025.12
30.8
EDAC
Method Category=Model-...
2025.12
25.3
NEUBAY
Method Category=Ours
2025.12
24.5
RAMBO
Method Category=Model-...
2025.12
21.6
MoMo
Method Category=Conser...
2025.12
18.3
COMBO
Method Category=Model-...
2025.12
17.9
MAPLE
Method Category=Bayesi...
2025.12
10.7
MoDAP
Method Category=Bayesi...
2025.12
8.9
CQL
Method Category=Model-...
2025.12
5.3
Feedback
Search any
task
Search any
task