Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Offline Goal-conditioned Reinforcement Learning on D4RL AntMaze large-play v2
Loading...
48.6
Normalized Score
Contrastive RL + BC
-1.944
11.178
24.3
37.422
Jun 15, 2022
Normalized Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Normalized Score
Contrastive RL + BC
TD Learning=false, Num...
2022.06
48.6
Contrastive RL + BC
TD Learning=false, Num...
2022.06
41.6
IQL*
TD Learning=true
2022.06
39.6
GCBC
TD Learning=false
2022.06
32.4
TD3+BC*
TD Learning=true
2022.06
0.2
BC
TD Learning=false
2022.06
0
DT
TD Learning=false
2022.06
0
Feedback
Search any
task
Search any
task