Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline Goal-Conditioned Reinforcement Learning on AntMaze Giant-Stitch v0
Loading...
32
Success Rate
ARLi
-1.28
7.36
16
24.64
Apr 19, 2026
Apr 24, 2026
Apr 29, 2026
May 5, 2026
May 10, 2026
May 15, 2026
May 21, 2026
Success Rate
Updated 12d ago
Evaluation Results
Method
Method
Links
Success Rate
ARLi
Size=1M, Dim.=29
2026.05
32
ARLe
Size=1M, Dim.=29
2026.05
21
HIQL2vr
Size=1M, Dim.=29
2026.05
20
HIQL2v
Size=1M, Dim.=29
2026.05
15
HIQL1vr
Size=1M, Dim.=29
2026.05
7
HIQL
2026.04
2
GCBC
2026.04
0
GCIVL
2026.04
0
GCIQL
2026.04
0
QRL
2026.04
0
CRL
2026.04
0
HSVL
2026.04
0
IQL
Size=1M, Dim.=29
2026.05
0
Feedback
Search any
task
Search any
task
