Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Offline Goal-Conditioned Reinforcement Learning on cube-octuple-1B
Loading...
3,400
Success Rate
SHARSA
-136
782
1,700
2,618
Dec 11, 2025
Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate
SHARSA
2025.12
3,400
DQC
Method=Decoupled Q-chu...
2025.12
3,400
HFBC
2025.12
2,800
HIQL
2025.12
2,000
NS
Backup=n-step return b...
2025.12
900
DQC-naïve
Execution=partial acti...
2025.12
300
FBC
2025.12
0
IQL
2025.12
0
OS
Backup=1-step TD-backup
2025.12
0
QC
Strategy=Q-chunking
2025.12
0
Feedback
Search any
task
Search any
task
