One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1802.01557/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTOne-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning — mentioned by pickdenishttps://news.ycombinator.com/item?id=20095409urn:hackerpapers:mention:1802.01557:20095409Tue, 04 Jun 2019 14:36:21 GMT<p>Here is a paper that uses meta-learning for quick imitation learning in robots that works across domains: https://arxiv.org/abs/1802.01557 The main sell is that it allows the robot to quickly generalize to new domains (surroundings and objects being manipulated), albeit not tasks.</p><p><a href="https://hackerpaper.kaipfister.de/p/1802.01557/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LGOne-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning — HN submissionhttps://news.ycombinator.com/item?id=16315793urn:hackerpapers:submission:1802.01557:16315793Tue, 06 Feb 2018 12:22:57 GMT<p>One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning [pdf]</p><p></p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/1802.01557/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LG