Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Preference Learning on Simulated Matchmaking Environment (p_flip=0.2, T=6,400)
Loading...
80
Like Rate
TK
76
78
80
82
Apr 11, 2026
Like Rate
Align@20
Delta S (Δs)
Updated 5d ago
Evaluation Results
Method
Method
Links
Like Rate
Align@20
Delta S (Δs)
TK
α=1
2026.04
80
71
94.8
Block-TK
α=1
2026.04
80
69.8
96.8
Block-NK
2026.04
80
69.8
99.4
NK
η=0.5
2026.04
80
62.6
73.8
K-NoNorm
2026.04
80
71
94.8
OGD-0.1
parameter=0.1
2026.04
80
71.6
93.3
Feedback
Search any
task
Search any
task
