Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Planners for human Assistance on COIN (test)
Loading...
25.5
SR (T=3)
PDPP
-1.02
5.865
12.75
19.635
Mar 26, 2023
SR (T=3)
mAcc (T=3)
mIoU (T=3)
SR (T=4)
mAcc (T=4)
mIoU (T=4)
Updated 1mo ago
Evaluation Results
Method
Method
Links
SR (T=3)
mAcc (T=3)
mIoU (T=3)
SR (T=4)
mAcc (T=4)
mIoU (T=4)
PDPP
Protocol=protocol1
2023.03
25.5
52.9
67.3
19.2
51
71.5
PDPP
Protocol=protocol2
2023.03
21.6
47.2
65.1
16.2
46.9
69.5
VLaMP
Protocol=protocol1
2023.03
18.3
39.2
56.6
9
35.2
54.2
DDN
Protocol=protocol1
2023.03
10.1
22.3
32.2
7
21
37.3
Random w/goal
Protocol=protocol1
2023.03
1.7
21.4
42.7
0.3
20.1
47.7
Random
Protocol=protocol1
2023.03
0
0.1
0.2
0
0.1
0.2
Feedback
Search any
task
Search any
task
