A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1011.0686/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTA Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning — mentioned by kotachhttps://news.ycombinator.com/item?id=11304068urn:hackerpapers:mention:1011.0686:11304068Thu, 17 Mar 2016 13:08:14 GMT<p>Checkout Dagger [2], SEARN [3] and LOLS [1] (LOLS is available in vowpal wabbit search capabilities). A lot of interesting stuff on mimicking optimal policies, local optimality, joint learning and similar stuff :D The whole point of playing is doing your decisions jointly, dependent on the previous decisions. If you learn your model that way it&#x27;ll make its decisions trying to minimize future regret. Local optimality is a very nice property. It means that if you play out a game, not a single change of any of the previous moves could lead you to a better result. Of course, local optimality is…</p><p><a href="https://hackerpaper.kaipfister.de/p/1011.0686/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG