Reviews: TopRank: A practical algorithm for online stochastic ranking

This paper tackles the problem of learning to rank items in the online setting. This paper proposes a new algorithm that uses confidence intervals on items preferences ordering in order to decide which item to assign to each position. Results show that the proposed approach empirically outperforms the current state-of-the-art in the re-ranking setting. The paper also provides an upper bound on the regret for the proposed approach, and a lower bound on the regret in ranking problems. Quality: I found the paper of overall good quality.