{"version":"1.0","provider_name":"Microsoft Research","provider_url":"https:\/\/www.microsoft.com\/en-us\/research","author_name":"Laura LoPresti","author_url":"https:\/\/www.microsoft.com\/en-us\/research\/people\/v-lalopr\/","title":"Autonomous soaring \u2013 AI on the fly - Microsoft Research","type":"rich","width":600,"height":338,"html":"<blockquote class=\"wp-embedded-content\" data-secret=\"dNyrUvZNlM\"><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/blog\/autonomous-soaring-ai-on-the-fly\/\">Autonomous soaring \u2013 AI on the fly<\/a><\/blockquote><iframe sandbox=\"allow-scripts\" security=\"restricted\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/blog\/autonomous-soaring-ai-on-the-fly\/embed\/#?secret=dNyrUvZNlM\" width=\"600\" height=\"338\" title=\"&#8220;Autonomous soaring \u2013 AI on the fly&#8221; &#8212; Microsoft Research\" data-secret=\"dNyrUvZNlM\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" class=\"wp-embedded-content\"><\/iframe><script type=\"text\/javascript\">\n\/* <![CDATA[ *\/\n\/*! This file is auto-generated *\/\n!function(d,l){\"use strict\";l.querySelector&&d.addEventListener&&\"undefined\"!=typeof URL&&(d.wp=d.wp||{},d.wp.receiveEmbedMessage||(d.wp.receiveEmbedMessage=function(e){var t=e.data;if((t||t.secret||t.message||t.value)&&!\/[^a-zA-Z0-9]\/.test(t.secret)){for(var s,r,n,a=l.querySelectorAll('iframe[data-secret=\"'+t.secret+'\"]'),o=l.querySelectorAll('blockquote[data-secret=\"'+t.secret+'\"]'),c=new RegExp(\"^https?:$\",\"i\"),i=0;i<o.length;i++)o[i].style.display=\"none\";for(i=0;i<a.length;i++)s=a[i],e.source===s.contentWindow&&(s.removeAttribute(\"style\"),\"height\"===t.message?(1e3<(r=parseInt(t.value,10))?r=1e3:~~r<200&&(r=200),s.height=r):\"link\"===t.message&&(r=new URL(s.getAttribute(\"src\")),n=new URL(t.value),c.test(n.protocol))&&n.host===r.host&&l.activeElement===s&&(d.top.location.href=t.value))}},d.addEventListener(\"message\",d.wp.receiveEmbedMessage,!1),l.addEventListener(\"DOMContentLoaded\",function(){for(var e,t,s=l.querySelectorAll(\"iframe.wp-embedded-content\"),r=0;r<s.length;r++)(t=(e=s[r]).getAttribute(\"data-secret\"))||(t=Math.random().toString(36).substring(2,12),e.src+=\"#?secret=\"+t,e.setAttribute(\"data-secret\",t)),e.contentWindow.postMessage({message:\"ready\",secret:t},\"*\")},!1)))}(window,document);\n\/* ]]> *\/\n<\/script>\n","thumbnail_url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2019\/04\/Autonomous-Soaring-An-Open-World-Challenge-for-AI_Site_04_2019_1400x788-5cc745b40c58f.png","thumbnail_width":1400,"thumbnail_height":788,"description":"The past few years have seen tremendous progress in reinforcement learning (RL). From complex games to robotic object manipulation, RL has qualitatively advanced the state of the art. However, modern RL techniques require a lot for success: a largely deterministic stationary environment, an accurate resettable simulator in which mistakes \u2013 and especially their consequences \u2013 [&hellip;]"}