{"id":98759,"date":"2019-11-18T23:02:32","date_gmt":"2019-11-19T07:02:32","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2019\/11\/an-imitation-learning-approach-to-train-robots-without-the-need-for-real-human-demonstrations"},"modified":"2019-11-18T23:02:32","modified_gmt":"2019-11-19T07:02:32","slug":"an-imitation-learning-approach-to-train-robots-without-the-need-for-real-human-demonstrations","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2019\/11\/an-imitation-learning-approach-to-train-robots-without-the-need-for-real-human-demonstrations","title":{"rendered":"An imitation learning approach to train robots without the need for real human demonstrations"},"content":{"rendered":"<p><\/p>\n<p><iframe style=\"display: block; margin: 0 auto; width: 100%; aspect-ratio: 4\/3; object-fit: contain;\" src=\"https:\/\/www.youtube.com\/embed\/41Heql6isxU?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; encrypted-media; gyroscope;\n   picture-in-picture\" allowfullscreen><\/iframe><\/p>\n<p>Most humans can learn how to complete a given task by observing another person perform it just once. Robots that are programmed to learn by imitating humans, however, typically need to be trained on a series of human demonstrations before they can effectively reproduce the desired behavior.<\/p>\n<p>Researchers were recently able to teach robots to execute new tasks by having them observe a single human demonstration, using meta-learning approaches. However, these learning techniques typically require real-world data that can be expensive and difficult to collect.<\/p>\n<p>To overcome this challenge, a team of researchers at Imperial College London has developed a new approach that enables one-shot imitation learning in robots without the need for real-world human demonstrations. Their approach, presented in <a href=\"https:\/\/arxiv.org\/abs\/1911.01103\">a paper pre-published on arXiv<\/a>, uses algorithms known as task-embedded control networks (TecNets), which allow artificial agents to learn how to complete tasks from a single or multiple demonstrations, as well as artificially generated <a href=\"https:\/\/techxplore.com\/tags\/training+data\/\" rel=\"tag\" class=\"\">training data<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Most humans can learn how to complete a given task by observing another person perform it just once. Robots that are programmed to learn by imitating humans, however, typically need to be trained on a series of human demonstrations before they can effectively reproduce the desired behavior. Researchers were recently able to teach robots to [\u2026]<\/p>\n","protected":false},"author":427,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[41,6],"tags":[],"class_list":["post-98759","post","type-post","status-publish","format-standard","hentry","category-information-science","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/98759","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/427"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=98759"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/98759\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=98759"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=98759"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=98759"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}