Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Lamp on FurnitureBench Noisy
Loading...
61.7
SR1 (Success Rate)
TAS
-2.468
14.191
30.85
47.509
Nov 6, 2025
SR1 (Success Rate)
SR2 (Success Rate)
Updated 1mo ago
Evaluation Results
Method
Method
Links
SR1 (Success Rate)
SR2 (Success Rate)
TAS
Policy Architecture=MLP
2025.11
61.7
51.2
TAS
Policy Architecture=DP
2025.11
46.3
36.7
FineTune
Policy Architecture=MLP
2025.11
20
6.8
Vanilla-O
Policy Architecture=MLP
2025.11
18.2
5
EMA
Policy Architecture=MLP
2025.11
10.7
4.8
BID-C
Policy Architecture=DP
2025.11
9.1
2.9
EMA
Policy Architecture=DP
2025.11
7.9
2.1
Vanilla-O
Policy Architecture=DP
2025.11
7.5
2
Vanilla-C
Policy Architecture=MLP
2025.11
0
0
Vanilla-C
Policy Architecture=DP
2025.11
0
0
BID-O
Policy Architecture=DP
2025.11
0
0
Feedback
Search any
task
Search any
task