Beat the Mean Bandit

@inproceedings{Yue2011BeatTM,
  title={Beat the Mean Bandit},
  author={Yisong Yue and Thorsten Joachims},
  booktitle={ICML},
  year={2011}
}
The Dueling Bandits Problem is an online learning framework in which actions are restricted to noisy comparisons between pairs of strategies (also called bandits). It models settings where absolute rewards are difficult to elicit but pairwise preferences are readily available. In this paper, we extend the Dueling Bandits Problem to a relaxed setting where preference magnitudes can violate transitivity. We present the first algorithm for this more general Dueling Bandits Problem and provide… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 54 CITATIONS

Bandits in the Plackett-Luce Model

VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

PAC Battling Bandits in the Plackett-Luce Model

VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Dueling bandits for online ranker evaluation

VIEW 27 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

MergeRUCB: A Method for Large-Scale Online Ranker Evaluation

VIEW 17 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Double Thompson Sampling for Dueling Bandits

VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2011
2019

CITATION STATISTICS

  • 25 Highly Influenced Citations

  • Averaged 7 Citations per year from 2017 through 2019

Similar Papers

Loading similar papers…