#108 – Sergey Levine: Robotics and Machine Learning

Lex Fridman Podcast

Lex Fridman

Philosophy, Science, Society & Culture, Technology

4.7 • 13.6K Ratings

🗓️ 14 July 2020

⏱️ 98 minutes

🔗️ Recording | iTunes | RSS

🧾️ Download transcript

Summary

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.

Support this podcast by supporting these sponsors:
– ExpressVPN: https://www.expressvpn.com/lexpod
– Cash App – use code “LexPodcast” and download:
– Cash App (App Store): https://apple.co/2sPrUHe
– Cash App (Google Play): https://bit.ly/2MlvP5w

If 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.

Here’s the outline of the episode. On some podcast players you should be able to click the timestamp to jump to that time.

OUTLINE:
00:00 – Introduction
03:05 – State-of-the-art robots vs humans
16:13 – Robotics may help us understand intelligence
22:49 – End-to-end learning in robotics
27:01 – Canonical problem in robotics
31:44 – Commonsense reasoning in robotics
34:41 – Can we solve robotics through learning?
44:55 – What is reinforcement learning?
1:06:36 – Tesla Autopilot
1:08:15 – Simulation in reinforcement learning
1:13:46 – Can we learn gravity from data?
1:16:03 – Self-play
1:17:39 – Reward functions
1:27:01 – Bitter lesson by Rich Sutton
1:32:13 – Advice for students interesting in AI
1:33:55 – Meaning of life

Transcript

Click on a timestamp to play from that location

0:00.0	The following is a conversation with Sergei Levine, a professor at Berkeley and a world-class
0:05.6	researcher in deep learning, reinforcement learning, robotics, and computer vision,
0:10.4	including the development of algorithms for end-to-end training of neural network policies
0:15.1	that combine perception and control, scalable algorithms for inverse reinforcement learning,
0:20.5	and, in general, deep RL algorithms.
0:24.0	Quick summary of the ads, two sponsors, cash app and express VPN.
0:28.7	Please consider supporting the podcast by downloading cash app and using code Lex Podcasts
0:33.7	and signing up at expressvpn.com slash Lex pod.
0:38.7	Click the links by the stuff.
0:40.7	It's the best way to support this podcast and, in general, the journey I'm on.
0:45.2	If you enjoy this thing, subscribe by on YouTube, review it with 5 stars and Apple podcasts,
0:50.8	follow on Spotify, support it on Patreon, or connect with me on Twitter at Lex Friedman.
0:57.6	As usual, I'll do a few minutes of ads now and never any ads in the middle that can break
1:01.5	the flow of the conversation.
1:03.8	This show is presented by cash app, the number one finance app in the app store.
1:08.2	When you get it, use code Lex Podcasts.
1:11.5	Cash app lets you send money to friends by Bitcoin and invest in the stock market with
1:15.9	as little as one dollar. Since cash app does fractional share trading,
1:20.5	let me mention that the order execution algorithm that works behind the scenes to create the
1:25.8	abstraction of the fractional orders is an algorithmic marvel.
1:29.9	So big props to the cash app engineers for taking a step up to the next layer of abstraction
1:34.4	over the stock market, making trading more accessible for new investors and diversification
	...

Please login to see the full transcript.

Previous episode | Next episode

Disclaimer: The podcast and artwork embedded on this page are from Lex Fridman, and are the property of its owner and not affiliated with or endorsed by Tapesearch.

Generated transcripts are the property of Lex Fridman and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.