Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline Goal-Conditioned Reinforcement Learning on cube-triple 100M
Loading...
98
Success Rate
DQC
16.88
37.94
59
80.06
Dec 11, 2025
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
DQC
Method=Decoupled Q-chu...
2025.12
98
NS
Backup=n-step return b...
2025.12
93
SHARSA
2025.12
83
IQL
2025.12
66
HFBC
2025.12
56
FBC
2025.12
54
OS
Backup=1-step TD-backup
2025.12
47
HIQL
2025.12
35
DQC-naïve
Execution=partial acti...
2025.12
27
QC
Strategy=Q-chunking
2025.12
20
Feedback
Search any
task
Search any
task
