BROADCASTS.com

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.
\n
\nSupport this podcast by supporting these sponsors:
\n- ExpressVPN: https://www.expressvpn.com/lexpod
\n- Cash App \u2013 use code "LexPodcast" and download:
\n- Cash App (App Store): https://apple.co/2sPrUHe
\n- Cash App (Google Play): https://bit.ly/2MlvP5w
\n
\nIf you would like to get more information about this podcast go to https://lexfridman.com/ai or connect with @lexfridman on Twitter, LinkedIn, Facebook, Medium, or YouTube where you can watch the video versions of these conversations. If you enjoy the podcast, please rate it 5 stars on Apple Podcasts, follow on Spotify, or support it on Patreon.
\n
\nHere's the outline of the episode. On some podcast players you should be able to click the timestamp to jump to that time.
\n
\nOUTLINE:
\n00:00 - Introduction
\n03:05 - State-of-the-art robots vs humans
\n16:13 - Robotics may help us understand intelligence
\n22:49 - End-to-end learning in robotics
\n27:01 - Canonical problem in robotics
\n31:44 - Commonsense reasoning in robotics
\n34:41 - Can we solve robotics through learning?
\n44:55 - What is reinforcement learning?
\n1:06:36 - Tesla Autopilot
\n1:08:15 - Simulation in reinforcement learning
\n1:13:46 - Can we learn gravity from data?
\n1:16:03 - Self-play
\n1:17:39 - Reward functions
\n1:27:01 - Bitter lesson by Rich Sutton
\n1:32:13 - Advice for students interesting in AI
\n1:33:55 - Meaning of life