Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline Reinforcement Learning on D4RL Gym MuJoCo walker2d-random v2
Loading...
37.3
Normalized Average Return
MOReL
-1.492
8.579
18.65
28.721
Apr 16, 2025
Normalized Average Return
Updated 25d ago
Evaluation Results
Method
Method
Links
Normalized Average Return
MOReL
2025.04
37.3
VIPO-MOBILE
2025.04
20
MOBILE
2025.04
17.9
DQL
2025.04
14.1
VIPO-MOPO
2025.04
9.5
IQL
2025.04
7.7
MOPO*
Retrained on v2=true
2025.04
7.4
COMBO
2025.04
7
CQL
2025.04
5.4
TD3+BC
2025.04
1.4
RAMBO
2025.04
0
Feedback
Search any
task
Search any
task
