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)...
Prif Awduron: | Zoghi, M, Karnin, Z, Whiteson, S, Rijke, M |
---|---|
Fformat: | Conference item |
Cyhoeddwyd: |
2015
|
Eitemau Tebyg
-
Melancholic Mem in the Third Life of Grange Copeland
gan: Sedehi, Kamelia Talebian, et al.
Cyhoeddwyd: (2015) -
Good Outcome Following Copeland Hemiarthroplasty for Acromegalic Arthropathy
gan: S. E. Johnson-Lynn, et al.
Cyhoeddwyd: (2011-01-01) -
Synergy in science: an interview with Neal Copeland and Nancy Jenkins
Cyhoeddwyd: (2012-11-01) -
Exponential Regret Bounds for Gaussian Process Bandits with Deterministic Observations
gan: de Freitas, N, et al.
Cyhoeddwyd: (2012) -
StreamingBandit: Experimenting with Bandit Policies
gan: Jules Kruijswijk, et al.
Cyhoeddwyd: (2020-08-01)