{"id":14451,"date":"2015-05-29T15:00:18","date_gmt":"2015-05-29T22:00:18","guid":{"rendered":"http:\/\/lifeboat.com\/blog\/?p=14451"},"modified":"2015-05-27T20:04:00","modified_gmt":"2015-05-28T03:04:00","slug":"robot-learns-skills-through-trial-and-error-like-you-do-blogger-by-jon-fingas-engadget","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2015\/05\/robot-learns-skills-through-trial-and-error-like-you-do-blogger-by-jon-fingas-engadget","title":{"rendered":"Robot learns skills through trial and error, like you do \u2014 by Jon Fingas Engadget"},"content":{"rendered":"<p><iframe loading=\"lazy\" src=\"https:\/\/www.youtube.com\/embed\/JeVppkoloXs\" width=\"630\" height=\"354\" frameborder=\"0\" allowfullscreen=\"allowfullscreen\"><\/iframe><\/p>\n<p>As a rule, robots have to learn through explicit instruction, whether it\u2019s through new programming, <a href=\"http:\/\/www.engadget.com\/2015\/01\/30\/darpa-robot-videos\/\">watching videos<\/a> or <a href=\"http:\/\/www.engadget.com\/2015\/03\/19\/rethink-robotics-sawyer\/\">holding their hands<\/a>. UC Berkeley\u2019s <a href=\"http:\/\/newscenter.berkeley.edu\/2015\/05\/21\/deep-learning-robot-masters-skills-via-trial-and-error\/\" target=\"_blank\">BRETT<\/a> (Berkeley Robot for the Elimination of Tedious Tasks) isn\u2019t nearly that dependent, however. The machine uses neural network-based <a href=\"http:\/\/www.engadget.com\/2014\/09\/25\/neighborhood-algorithm\/\">deep learning<\/a> algorithms to master tasks through trial and error, much like humans do. Ask it to assemble a toy and it\u2019ll keep trying until it understands what works. In theory, you\u2019d rarely need to give the robot new code \u2014 you\u2019d just make requests and give the automaton enough time to figure things out.<\/p>\n<p><a href=\"http:\/\/www.engadget.com\/2015\/05\/25\/brett-deep-learning-robot\/\" target=\"_blank\">Read more<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>As a rule, robots have to learn through explicit instruction, whether it\u2019s through new programming, watching videos or holding their hands. UC Berkeley\u2019s BRETT (Berkeley Robot for the Elimination of Tedious Tasks) isn\u2019t nearly that dependent, however. The machine uses neural network-based deep learning algorithms to master tasks through trial and error, much like humans [\u2026]<\/p>\n","protected":false},"author":76,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-14451","post","type-post","status-publish","format-standard","hentry","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/14451","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\/76"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=14451"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/14451\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=14451"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=14451"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=14451"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}