Bradley-Terry preference probability, vectorised (Kamath Ch 5)

Stable sigmoid of the winner-minus-loser reward difference.

Usage

morie_kamath_bradley_terry_preference(r_w, r_l)

Arguments

r_w, r_l

Winner and loser scores.

Value

List with estimate, p_pref, reward_difference.

Examples

V <- c(1, 2, 3, 4, 5, 6, 7, 8)
morie_kamath_bradley_terry_preference(V, V)
#> $estimate
#> [1] 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5
#> 
#> $p_pref
#> [1] 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5
#> 
#> $reward_difference
#> [1] 0 0 0 0 0 0 0 0
#> 
#> $n
#> [1] 8
#> 
#> $method
#> [1] "Bradley-Terry preference probability (Kamath Ch 5)"
#>