Search Results for author:
Found 2 papers, 0 papers with code
UniRank: Unimodal Bandit Algorithm for Online Ranking
The semi-bandit version, where a full matching is sampled at each iteration, has been addressed by \cite{ADMA}, creating an algorithm with an expected regret matching $O(\frac{L\log(L)}{\Delta}\log(T))$ with $2L$ players, $T$ iterations and a minimum reward gap $\Delta$.
Position-Based Multiple-Play Bandits with Thompson Sampling
Multiple-play bandits aim at displaying relevant items at relevant positions on a web page.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
