Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Offline Goal-conditioned Reinforcement Learning on puzzle 3x3-play-oraclerep v0
Loading...
99
task1
IQL
-0.84
25.08
51
76.92
Oct 26, 2025
task1
task2
task3
task4
task5
overall
Updated 4d ago
Evaluation Results
Method
Method
Links
task1
task2
task3
task4
task5
overall
IQL
2025.10
99
99
99
98
95
98
TRL
2025.10
99
99
100
98
99
99
CRL
2025.10
15
6
1
1
2
5
FBC
2025.10
10
1
1
1
2
3
COE
2025.10
7
2
1
1
0
2
TDP
2025.10
5
1
0
2
1
2
BC
2025.10
4
1
1
0
1
1
IVL
2025.10
4
2
2
1
1
2
QRL
2025.10
3
0
0
0
0
1
Feedback
Search any
task
Search any
task
