Copeland dueling bandits
A version of the dueling bandit problem is addressed in which a Condorcet winner may not exist. Two algorithms are proposed that instead seek to minimize regret with respect to the Copeland winner, which, unlike the Condorcet winner, is guaranteed to exist. The first, Copeland Confidence Bound (CCB)...
Egile Nagusiak: | Zoghi, M, Karnin, Z, Whiteson, S, Rijke, M |
---|---|
Formatua: | Conference item |
Argitaratua: |
2015
|
Antzeko izenburuak
-
Melancholic Mem in the Third Life of Grange Copeland
nork: Sedehi, Kamelia Talebian, et al.
Argitaratua: (2015) -
Good Outcome Following Copeland Hemiarthroplasty for Acromegalic Arthropathy
nork: S. E. Johnson-Lynn, et al.
Argitaratua: (2011-01-01) -
Synergy in science: an interview with Neal Copeland and Nancy Jenkins
Argitaratua: (2012-11-01) -
Exponential Regret Bounds for Gaussian Process Bandits with Deterministic Observations
nork: de Freitas, N, et al.
Argitaratua: (2012) -
StreamingBandit: Experimenting with Bandit Policies
nork: Jules Kruijswijk, et al.
Argitaratua: (2020-08-01)