Online Ranker Evaluation
2 papers with code • 0 benchmarks • 0 datasets
This task has no description! Would you like to contribute one?
Benchmarks
These leaderboards are used to track progress in Online Ranker Evaluation
No evaluation results yet. Help compare methods by
submitting
evaluation metrics.
Most implemented papers
Human Preferences as Dueling Bandits
Based on these simulations, one algorithm stands out for its potential.
MergeDTS: A Method for Effective Large-Scale Online Ranker Evaluation
Our main finding is that for large-scale Condorcet ranker evaluation problems, MergeDTS outperforms the state-of-the-art dueling bandit algorithms.