Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reinforcement Learning on PROCGEN HEIST 1.0 (test)
Loading...
98.57
Accuracy (%)
LAOF-Action
71.1764
78.2882
85.4
92.5118
Nov 20, 2025
Accuracy (%)
Return
Updated 26d ago
Evaluation Results
Method
Method
Links
Accuracy (%)
Return
LAOF-Action
Action Supervision=true
2025.11
98.57
0.91
LAOM-Action
Action Supervision=true
2025.11
98.14
0.91
CoMo w/ OF
Optical Flow (OF) cons...
2025.11
95.05
0.89
LAOF
Action Supervision=false
2025.11
94.19
0.88
CoMo
2025.11
75.58
0.78
LAPO
2025.11
72.23
0.76
Feedback
Search any
task
Search any
task