Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline Reinforcement Learning on OGBench State-based Singletask Offline v0
Loading...
97
Success Rate
Value Flows
4.44
28.47
52.5
76.53
Oct 9, 2025
Success Rate
Updated 4mo ago
Evaluation Results
Method
Method
Links
Success Rate
Value Flows
Policy Architecture=Fl...
2025.10
97
CODAC
Policy Architecture=Fl...
2025.10
80
IQN
Policy Architecture=Fl...
2025.10
70
FQL
Policy Architecture=Fl...
2025.10
61
FBRAC
Policy Architecture=Ga...
2025.10
47
ReBRAC
Policy Architecture=Ga...
2025.10
45
IFQL
Policy Architecture=Ga...
2025.10
35
IQL
Policy Architecture=Ga...
2025.10
27
C51
Policy Architecture=Fl...
2025.10
9
BC
Policy Architecture=Ga...
2025.10
8
Feedback
Search any
task
Search any
task
