Relative Upper Confidence Bound for the K-Armed Dueling Bandit Problem · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1312.3393/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTRelative Upper Confidence Bound for the K-Armed Dueling Bandit Problem — mentioned by noelwelshhttps://news.ycombinator.com/item?id=8856324urn:hackerpapers:mention:1312.3393:8856324Thu, 08 Jan 2015 13:49:37 GMT<p>Yes, I think so. It might be of interest to you that there is now some published work on bandit algorithms for when all you have is ranking, not absolute ordering. This is close to what we were talking about: http://arxiv.org/pdf/1312.3393.pdf</p><p><a href="https://hackerpaper.kaipfister.de/p/1312.3393/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG