Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline Reinforcement Learning on cube-double-play OGBench 5 tasks v0
Loading...
69
Average Success Rate
Value Flows
-2.76
15.87
34.5
53.13
Oct 9, 2025
Oct 19, 2025
Oct 29, 2025
Nov 8, 2025
Nov 18, 2025
Nov 28, 2025
Dec 8, 2025
Average Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Success Rate
Value Flows
Policy Type=Flow Policies
2025.10
69
CODAC
Policy Type=Flow Policies
2025.10
61
MAC
Model Paradigm=Model-B...
2025.12
53
IQN
Policy Type=Flow Policies
2025.10
42
FQL
Model Paradigm=Model-Free
2025.12
29
FQL
Policy Type=Flow Policies
2025.10
29
IDQL
Model Paradigm=Model-Free
2025.12
15
FBRAC
Policy Type=Flow Policies
2025.10
15
IFQL
Policy Type=Flow Policies
2025.10
14
ReBRAC
Model Paradigm=Model-Free
2025.12
12
ReBRAC
Policy Type=Gaussian P...
2025.10
12
IQL
Model Paradigm=Model-Free
2025.12
7
IQL
Policy Type=Gaussian P...
2025.10
6
FMPC
Model Paradigm=Model-B...
2025.12
3
BC
Policy Type=Gaussian P...
2025.10
2
C51
Policy Type=Flow Policies
2025.10
2
MOPO
Model Paradigm=Model-B...
2025.12
1
MOBILE
Model Paradigm=Model-B...
2025.12
1
LEQ
Model Paradigm=Model-B...
2025.12
0
Feedback
Search any
task
Search any
task
