{"version":1,"type":"rich","provider_name":"Libsyn","provider_url":"https:\/\/www.libsyn.com","height":90,"width":600,"title":"Upside-Down Reinforcement Learning with J\u00fcrgen Schmidhuber - #357","description":"Today we\u2019re joined by J\u00fcrgen Schmidhuber, Co-Founder and Chief Scientist of NNAISENSE, the Scientific Director at IDSIA, as well as a Professor of AI at USI and SUPSI in Switzerland. J\u00fcrgen\u2019s lab is well known for creating the Long Short-Term Memory (LSTM) network which has become a prevalent neural network, used commonly devices such as smartphones, which we discuss in detail in our first conversation with J\u00fcrgen back in 2017. In this conversation, we dive into some of J\u00fcrgen\u2019s more recent work, including his recent paper,&amp;nbsp;Reinforcement Learning Upside Down: Don\u2019t Predict Rewards \u2014 Just Map Them to Actions. Check out the show notes page at twimlai.com\/talk\/357. ","author_name":"The TWIML AI Podcast (formerly This Week in Machine Learning &amp; Artificial Intelligence)","author_url":"https:\/\/twimlai.com","html":"<iframe title=\"Libsyn Player\" style=\"border: none\" src=\"\/\/html5-player.libsyn.com\/embed\/episode\/id\/13564421\/height\/90\/theme\/custom\/thumbnail\/yes\/direction\/forward\/render-playlist\/no\/custom-color\/3e85b1\/\" height=\"90\" width=\"600\" scrolling=\"no\"  allowfullscreen webkitallowfullscreen mozallowfullscreen oallowfullscreen msallowfullscreen><\/iframe>","thumbnail_url":"https:\/\/assets.libsyn.com\/secure\/content\/67289990"}