#108 – Sergey Levine: Robotics and Machine Learning
0:001:37:59
Speed
Listening elsewhere? Jump this view to your spot.
About this episode
<p>Sergey Levine is a professor at Berkeley and a world-class researcher in deep learning, reinforcement learning, robotics, and computer vision, including the development of algorithms for end-to-end training of neural network policies that combine perception and control, scalable algorithms for inverse reinforcement learning, and deep RL algorithms.</p>
<p>Support this podcast by supporting these sponsors:<br />
– ExpressVPN: <a href="https://www.expressvpn.com/lexpod">https://www.expressvpn.com/lexpod</a><br />
– Cash App – use code “LexPodcast” and download:<br />
– Cash App (App Store): <a href="https://apple.co/2sPrUHe">https://apple.co/2sPrUHe</a><br />
– Cash App (Google Play): <a href="https://bit.ly/2MlvP5w">https://bit.ly/2MlvP5w</a></p>
<p>If you would like to get more information about this podcast go to <a href="https://lexfridman.com/ai">https://lexfridman.com/ai</a> or connect with @lexfridman on <a href="https://twitter.com/lexfridman">Twitter</a>, <a href="https://www.linkedin.com/in/lexfridman/">LinkedIn</a>, <a href="https://www.facebook.com/lexfridman">Facebook</a>, <a href="https://medium.com/@lexfridman">Medium</a>, or <a href="https://www.youtube.com/lexfridman">YouTube</a> where you can watch the video versions of these conversations. If you enjoy the podcast, please rate it 5 stars on <a href="https://podcasts.apple.com/us/podcast/artificial-intelligence/id1434243584">Apple Podcasts</a>, follow on <a href="https://open.spotify.com/show/2MAi0BvDc6GTFvKFPXnkCL">Spotify</a>, or support it on <a href="https://www.patreon.com/lexfridman">Patreon</a>.</p>
<p>Here’s the outline of the episode. On some podcast players you should be able to click the timestamp to jump to that time.</p>
<p>OUTLINE:<br />
00:00 – Introduction<br />
03:05 – State-of-the-art robots vs humans<br />
16:13 – Robotics may help us understand intelligence<br />
22:49 – End-to-end learning in robotics<br />
27:01 – Canonical problem in robotics<br />
31:44 – Commonsense reasoning in robotics<br />
34:41 – Can we solve robotics through learning?<br />
44:55 – What is reinforcement learning?<br />
1:06:36 – Tesla Autopilot<br />
1:08:15 – Simulation in reinforcement learning<br />
1:13:46 – Can we learn gravity from data?<br />
1:16:03 – Self-play<br />
1:17:39 – Reward functions<br />
1:27:01 – Bitter lesson by Rich Sutton<br />
1:32:13 – Advice for students interesting in AI<br />
1:33:55 – Meaning of life</p>