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 signing up with these sponsors:
- ExpressVPN at 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

EPISODE LINKS:
Sergey's Twitter: https://twitter.com/svlevine
Sergey's Website: http://rail.eecs.berkeley.edu/
Sergey's Papers: https://scholar.google.com/citations?user=8R35rCwAAAAJ

PODCAST INFO:
Podcast website:
https://lexfridman.com/podcast
Apple Podcasts:
https://apple.co/2lwqZIr
Spotify:
https://spoti.fi/2nEwCF8
RSS:
https://lexfridman.com/feed/podcast/
Full episodes playlist:
https://www.youtube.com/playlist?list=PLrAXtmErZgOdP_8GztsuKi9nrraNbKKp4
Clips playlist:
https://www.youtube.com/playlist?list=PLrAXtmErZgOeciFP3CBCIEElOJeitOr41

OUTLINE:
0:00 - Introduction
3:05 - 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

CONNECT:
- Subscribe to this YouTube channel
- Twitter: https://twitter.com/lexfridman
- LinkedIn: https://www.linkedin.com/in/lexfridman
- Facebook: https://www.facebook.com/LexFridmanPage
- Instagram: https://www.instagram.com/lexfridman
- Medium: https://medium.com/@lexfridman
- Support on Patreon: https://www.patreon.com/lexfridman

The following is a conversation with Sergei Lavigne, 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 in general, deep RL algorithms.

Please consider supporting the podcast by downloading Cash App and using code LEXPODCAST and signing up at expressvpn.com slash LexPod.

It's the best way to support this podcast and in general, the journey I'm on.

If you enjoy this thing, subscribe on YouTube, review it with 5 stars on Apple Podcasts, follow on Spotify, support it on Patreon, or connect with me on Twitter at Lex Friedman.

As usual, I'll do a few minutes of ads now and never any ads in the middle that can break the flow of the conversation.

This show is presented by Cash App, the number 1 finance app in the App Store.

Cash App lets you send money to friends, buy Bitcoin, and invest in the stock market with as little as $1.

Since Cash App does fractional share trading, let me mention that the order execution algorithm that works behind the scenes to create the abstraction of the fractional orders is an algorithmic marvel.

So big props to the Cash App engineers for taking a step up to the next layer of abstraction over the stock market, making trading more accessible for new investors and diversification much easier.

So again, if you get Cash App from the App Store or Google Play and use the code LEXPODCAST, you get $10, and Cash App will also donate $10 to FIRST, an organization that is helping to advance robotics and STEM education for young people around the world.

This show is also sponsored by ExpressVPN.

Get it at expressvpn.com slash LexPod to support this podcast and to get an extra 3 months free on a 1 year package.

I've been using ExpressVPN for many years.

I think ExpressVPN is the best VPN out there.

They told me to say it, but it happens to be true in my humble opinion.

It doesn't log your data, it's crazy fast, and it's easy to use, literally just 1 big power on button.

Again, it's probably obvious to you, but I should say it again.

It's really important that they don't log your data.

It works on Linux and every other operating system, but Linux of course is the best operating system.

Shout out to my favorite flavor, Ubuntu Mate 2004.

Once again, get it at ExpressVPN.com slash LexPod to support this podcast and to get an extra 3 months free on a 1 year package.

And now, here's my conversation with Sergei Lavine.

What's the difference between a state-of-the-art human, such as you and I, well I don't know if we qualify as state-of-the-art humans, but a state-of-the-art human and a state-of-the-art robot?

Robot capability is, it's kind of a, I think it's a very tricky thing to understand because there are some things that are difficult that we wouldn't think are difficult and some things that are easy that we wouldn't think are easy.

And there's also a really big gap between capabilities of robots in terms of hardware and their physical capability and capabilities of robots in terms of what they can do autonomously.

There is a little video that I think robotics researchers really like to show, especially robotics learning researchers like myself, from 2004 from Stanford, which demonstrates a prototype robot called the PR1.

And the PR1 was a robot that was designed as a home assistance robot.

And there's this beautiful video showing the PR1 tidying up a living room, putting away toys, and at the end, bringing a beer to the person sitting on the couch, which looks really amazing.

And then the punchline is that this robot is entirely controlled by a person.

So in some ways, the gap between a state-of-the-art human and a state-of-the-art robot, if the robot has a human brain, is actually not that large.

Now obviously like human bodies are sophisticated and very robust and resilient in many ways, but on the whole, if we're willing to like spend a bit of money and do a bit of engineering, we can kind of close the hardware gap almost.

But the intelligence gap, that 1 is very wide.

And when you say hardware, you're referring to the physical, sort of the actuators, the actual body of the robot as opposed to the hardware on which the cognition, the hardware of the nervous system.

Yes, exactly, I'm referring to the body rather than the mind.

So that means that the work is cut out for us.

While we can still make the body better, we know that the big bottleneck right now is really the mind.

How big is the difference in your sense of ability to learn, ability to reason, ability to perceive the world between humans and our best robots?

The gap is very large, and the gap becomes larger the more unexpected events can happen in

So essentially, the spectrum along which you can measure the size of that gap is the spectrum of how open the world is.

If you control everything in the world very tightly, if you put the robot in a factory and you tell it where everything is, and you rigidly program its motion, then it can do things, 1 might even say, in a superhuman way.

It can move faster, it's stronger, it can lift up a car, and things like that.

But as soon as anything starts to vary in the environment, now it'll trip up and if many, many things vary like they would like in your kitchen, for example, then things are pretty much like wide open.

Now again, we're gonna stick a bit on the philosophical questions, but how much on the human side of the cognitive abilities in your sense is nature versus nurture?

So how much of it is a product of evolution and how much of it is something we'll learn from sort of scratch

I'm gonna read into your question as asking about the implications of this for AI.

I'm not a biologist, I can't really speak authoritatively.

it's all about learning, then there's more hope

Yeah, so the way that I look at this is that, you know, well, first, of course, biology is very messy.

And if you ask the question, how does a person do something or how does a person's mind do something, you can come up with a bunch of hypotheses and oftentimes you can find support for many different, often conflicting hypotheses.

1 way that we can approach the question of what the implications of this for AI are, is we can think about what's sufficient.

So, you know, maybe a person is from birth very, very good at some things, like, for example, recognizing faces.

There's a very strong evolutionary pressure to do that.

If you can recognize your mother's face, then you're more likely to survive.

But we can also ask, what's the minimum sufficient thing?

And 1 of the ways that we can study the minimum sufficient thing is we could, for example, see what people do in unusual situations.

If you present them with things that evolution couldn't have prepared them for.

Our daily lives actually do this to us all the time.

We didn't evolve to deal with automobiles and space flight and whatever.

So there are all these situations that we can find ourselves in and we do very well there.

I can give you a joystick to control a robotic arm, which you've never used before, and you might be pretty bad for the first couple of seconds.

But if I tell you like, your life depends on using this robotic arm to like open this door, you'll probably manage it.

Even though you've never seen this device before, you've never used a joystick controller, so you'll kind of muddle through it, and that's not your evolved natural ability, that's your flexibility, your adaptability, and that's exactly where our current robotic systems really kind of fall flat.

But I wonder how much general, almost what we think of as common sense, pre-trained models underneath all that.

So that ability to adapt to a joystick requires you to have a kind of, you know, I'm human, so it's hard for me to introspect all the knowledge I have about the world, but it seems like there might be an iceberg underneath of the amount of knowledge we actually bring to the table.

There's absolutely an iceberg of knowledge that we bring to the table, but I think it's very likely that iceberg of knowledge is actually built up over our lifetimes.

Because we have a lot of prior experience to draw on, and it kind of makes sense that the right way for us to optimize our efficiency, our evolutionary fitness, and so on, is to utilize all that experience to build up the best iceberg we can get.

And that's actually 1 of the, you know, while that sounds an awful lot like what machine learning actually does.

I think that for modern machine learning, it's actually a really big challenge to take this unstructured mass of experience and distill out something that looks like a common sense understanding of the world.

And perhaps part of that is it's not because something about machine learning itself is broken or hard, but because we've been a little too rigid in subscribing to a very supervised, very rigid notion of learning, you know, kind of the input-output, X's go to Y's sort of model.

And maybe what we really need to do is to view the world more as like a massive experience that is not necessarily providing any rigid supervision, but sort of providing many, many instances of things that could be.

And then you take that and you distill it into some sort of common sense understanding.

I see, well, you're painting an optimistic, beautiful picture, especially from the robotics perspective, because that means we just need to invest and build better learning algorithms, figure out how we can get access to more and more data for those learning algorithms to extract signal from and then accumulate that iceberg of knowledge.

I think it's potentially a little bit more than just that.

And this is where we perhaps reach the limits of our current understanding.

But 1 thing that I think that the research community hasn't really resolved in a satisfactory way is how much it matters where that experience comes from.

Like, you know, do you just like download everything on the internet and cram it into essentially the 21st century analog of the giant language model and then see what happens?

Or does it actually matter whether your machine physically experiences the world or in the sense that it actually attempts things, observes the outcome of its actions and kind of augments its experience that way.

That it chooses which parts of the world it gets to interact with and observe and learn from.

Right, it may be that the world is so complex that simply obtaining a large mass of sort of IID samples of the world is a very difficult way to go.

But if you are actually interacting with the world and essentially performing this sort of hard negative mining by attempting what you think might work, observing the sometimes happy and sometimes sad outcomes of that and augmenting your understanding using that experience and you're just doing this continually for many years, maybe that sort of data in some sense is actually much more favorable to obtaining a common sense understanding.

1 reason we might think that this is true is that what we associate with common sense or lack of common sense is often characterized by the ability to reason about counterfactual questions.

Here, this bottle of water is sitting on the table, everything is fine if I were to knock it over, which I'm not going to do.

But if I were to do that, what would happen?

And I know that nothing good would happen from that.

But if I have a bad understanding of the world, I might think that that's a good way for me to gain more utility.

If I actually go about my daily life doing the things that my current understanding of the world suggests will give me high utility, in some ways I'll get exactly the right supervision to tell me not to do those bad things and to keep doing the good things.

So there's a spectrum between IID, random walk through the space of data, and then there's, and what we humans do.

Well, I don't even know if we do it optimal, but that might be beyond.

So this open question that you raised, where do you think systems, intelligent systems that would be able to deal with this world fall?

Can we do pretty well by reading all of Wikipedia, sort of randomly sampling it like language models do, or do we have to be exceptionally selective and intelligent about which aspects of the world we interact with?

So I think this is first an open scientific problem, and I don't have like a clear answer, but I can speculate a little bit.

And what I would speculate is that you don't need to be super, super careful.

I think it's less about being careful to avoid the useless stuff and more about making sure that you hit on the really important stuff.

So perhaps it's okay if you spend part of your day just, you know, guided by your curiosity, visiting interesting regions of the of your state space, but it's important for you to, you know, every once in a while make sure that you really try out the solutions that your current model of the world suggests might be effective and observe whether those solutions are working as you expect or not.

And perhaps some of that is really essential to have kind of a perpetual improvement loop.

Like this perpetual improvement loop is really like, that's really the key, the key that's gonna potentially distinguish the best current methods from the best methods of tomorrow in a sense.

How important do you think is exploration or total out of the box thinking exploration in this space as you jump to totally different domains.

So you kind of mentioned there's an optimization problem.

You kind of explore the specifics of a particular strategy, whatever the thing you're trying to solve.

How important is it to explore totally outside of the strategies that have been working for you so far.

Yeah, I think it's a very problem dependent kind of question and I think that that's actually, you know, in some ways that question gets at 1 of the big differences between sort of the classic formulation of a reinforcement learning problem and some of the sort of more open-ended reformulations of that problem that have been explored in recent years.

So classically, reinforcement learning is framed as a problem of maximizing utility, like any kind of rational AI agent, and then anything you do is in service to maximizing that utility.

But a very interesting kind of way to look at, I'm not necessarily saying this is the best way to look at it, but an interesting alternative way to look at these problems is as something where you first get to explore the world however you please, and then afterwards you will be tasked with doing something.

And that might suggest a somewhat different solution.

So if you don't know what you're going to be tasked with doing, and you just want to prepare yourself optimally for whatever your uncertain future holds, maybe then you will choose to attain some sort of coverage, build up sort of an arsenal of cognitive tools, if you will, such that later on when someone tells you, now your job is to fetch the coffee for me, you'll be well prepared to undertake that task.

And that you see that as the modern formulation of the reinforcement learning problem, as a kind of the more multitask, the general intelligence kind of formulation.

I think that's 1 possible vision of where things might be headed.

I don't think that's by any means the mainstream or standard way of doing things, and it's not like if I had to.

What's the general problem of robotics we're trying to solve?

You actually kind of painted 2 pictures here.

1 of sort of the narrow, 1 of the general.

What in your view is the big problem of robotics?

Again, ridiculously philosophical high level questions.

I think that, you know, maybe there are 2 ways I can answer this question.

1 is there's a very pragmatic problem, which is like, what would make robots, what would sort of maximize the usefulness of robots?

And there the answer might be something like a system where, a system that can perform whatever task a human user sets for it, within the physical constraints, of course.

If you tell it to teleport to another planet, it probably can't do that.

But if you ask it to do something that's within its physical capability, then potentially with a little bit of additional training or a little bit of additional trial and error, it ought to be able to figure it out in much the same way as like a human teleoperator ought to figure out how to drive the robot to do that.

That's kind of the very pragmatic view of what it would take to kind of solve the robotics problem, if you will.

But I think that there is a second answer.

And that answer is a lot closer to why I want to work on robotics, which is that I think it's less about what it would take to do a really good job in the world of robotics, but more the other way around, what robotics can bring to the table to help us understand artificial intelligence.

So your dream fundamentally is to understand intelligence.

Yes, I think that's the dream for many people who actually work in this space.

I think that there's something very pragmatic and very useful about studying robotics, but I do think that a lot of people that go into this field actually, you know, the things that they draw inspiration from are the potential for robots to, like, help us learn about intelligence and about ourselves.

So that's fascinating, that robotics is basically the space by which you can get closer to understanding the fundamentals of artificial intelligence.

So what is it about robotics that's different from some of the other approaches?

So if we look at some of the early breakthroughs in deep learning or in the computer vision space and the natural language processing, there's really nice clean benchmarks that a lot of people competed on and thereby came up with a lot of brilliant ideas.

What's the fundamental difference to you between computer vision, purely defined and ImageNet and kind of the bigger robotics problem?

1 is that with robotics, you kind of have to take away many of the crutches.

So you have to deal with both the particular problems of perception, control, and so on, but you also have to deal with the integration of those things.

And classically, we've always thought of the integration as kind of a separate problem.

So a classic kind of modular engineering approach is that we solve the individual sub-problems, then wire them together, and then the whole thing works.

And 1 of the things that we've been seeing over the last couple of decades is that, well, maybe studying the thing as a whole might lead to just like very different solutions than if we were to study the parts and wire them together.

So the integrative nature of robotics research helps us see, you know, different perspectives on the problem.

Another part of the answer is that with robotics, it casts a certain paradox into very clever relief.

So this is sometimes referred to as a Moravic's paradox, the idea that in artificial intelligence, things that are very hard for people can be very easy for machines, and vice versa, things that are very easy for people can be very hard for machines.

So, you know, integral and differential calculus is pretty difficult to learn for people, but if you program a computer to do it, it can derive derivatives and integrals for you all day long without any trouble.

Whereas some things like drinking from a cup of water, very easy for a person to do, very hard for a robot to deal with.

And sometimes when we see such blatant discrepancies, that gives us a really strong hint that we're missing something important.

So if we really try to 0 in on those discrepancies, we might find that little bit that we're missing.

And it's not that we need to make machines better or worse at math and better at drinking water, but just that by studying those discrepancies we might find some new insight.

So that could be in any space, it doesn't have to be robotics, but you're saying, I mean, I get it's kind of interesting that robotics seems to have a lot of those discrepancies.

So the Hans-Marvik paradox is probably referring to the space of the physical interaction, like you said, object manipulation, walking, all the kind of stuff we do in the physical world.

How do you make sense, if you were to try to disentangle the Marvox paradox, like why is there such a gap in our intuition about it?

Why do you think manipulating objects is so hard from everything you've learned from applying reinforcement learning in

Yeah, I think that 1 reason is maybe that for many of the other problems that we've studied in AI and computer science and so on, the notion of input, output, and supervision is much, much cleaner.

So computer vision, for example, deals with very complex inputs, But it's comparatively a bit easier, at least up to some level of abstraction, to cast it as a very tightly supervised problem.

It's comparatively much, much harder to cast robotic manipulation as a very tightly supervised problem.

You can do it, it just doesn't seem to work all that well.

So you could say that, well, maybe we get a labeled data set where we know exactly which motor commands to send and then we train on that, but for various reasons, that's not actually like such a great solution.

And it also doesn't seem to be even remotely similar to how people and animals learn to do things because we're not told by like our parents, here's how you fire your muscles in order to walk.

We do get some guidance, but the really low level detailed stuff we figure out mostly on our own.

And that's what you mean by tightly coupled that every single little sub action gets a supervised signal of whether it's a good 1 or not.

Right, so while in computer vision, you could sort of imagine up to a level of abstraction that maybe somebody told you this is a car and this is a cat and this is a dog, in motor control it's very clear that that was not the case.

If we look at sort of the sub spaces of robotics, that again, as you said, robotics integrates all of them together and we get to see how this beautiful mess interplays.

But so there's nevertheless still perception.

So it's the computer vision problem, broadly speaking, understanding the environment.

Then there's also, maybe you can correct me on this kind of categorization of the space, then there's prediction in trying to anticipate what things are going to do into the future in order for you to be able to act in that world.

And then there's also this game theoretic aspect of how your actions will change the behavior of others.

In this kind of space, what's, and this is bigger than reinforcement learning, this is just broadly looking at the problem in robotics, what's the hardest problem here?

Or is there, or is what You said true that when you start

to look at all of them together, that's a whole nother thing.

Like you can't even say which 1 individually is harder because all of them together, you should only be looking at them all together.

I think when you look at them all together, some things actually become easier.

And I think that's actually pretty important.

So we had, you know, back in 2014, we had some work, basically our first work on end-to-end reinforcement learning for robotic manipulation skills from vision, which at the time was something that seemed a little inflammatory and controversial in the robotics world.

But other than the inflammatory and controversial part of it, the point that we were actually trying to make in that work is that for the particular case of combining perception and control, you could actually do better if you treat them together than if you try to separate them.

And the way that we tried to demonstrate this is we picked a fairly simple motor control task where a robot had to insert a little red trapezoid into a trapezoidal hole.

And we had our separated solution, which involved first detecting the hole using a pose detector and then actuating the arm to put it in.

And then our intent solution, which just mapped pixels to the torques.

And 1 of the things we observed is that if you use the N10 solution, essentially the pressure on the perception part of the model is actually lower.

Like it doesn't have to figure out exactly where the thing is in 3D space, it just needs to figure out where it is, you know, distributing the errors in such a way that the horizontal difference matters more than the vertical difference, because vertically it just pushes it down all the way until it can't go any further.

And their perceptual errors are a lot less harmful, whereas perpendicular to the direction of motion, perceptual errors are much more harmful.

So the point is that if you combine these 2 things, you can trade off errors between the components, optimally to best accomplish the task, and the components can actually be weaker while still leading to better overall performance.

I mean, in the space of pegs and things like that, it's quite simple.

It almost is tempting to overlook, but that seems to be at least intuitively an idea that should generalize to basically all aspects of perception and control.

Yeah, and we, you know, people who have studied sort of perceptual heuristics in humans and animals find things like that all the time.

So 1 very well-known example of this is something called the gaze heuristic, which is a little trick that you can use to intercept a flying object.

So if you want to catch a ball, for instance, you could try to localize it in 3D space, estimate its velocity, estimate the effect of wind resistance, solve a complex system of differential equations in your head, or you can maintain a running speed so that the object stays in the same position as in your field of view.

So if it dips a little bit, you speed up.

And if you follow the simple rule, you'll actually arrive at exactly the place where the object lands and you'll catch it.

And humans use it when they play baseball.

Human pilots use it when they fly airplanes to figure out if they're about to collide with somebody.

Frogs use this to catch insects and so on and so on.

So this is something that actually happens in nature.

And I'm sure this is just 1 instance of it that we were able to identify just because, well, that scientists were able to identify because it's so prevalent, but there are probably many others.

Do you have a, just so we can zoom in, as we talk about robotics, do you have a canonical problem, sort of a simple, clean, beautiful, representative problem in robotics that you think about when you're thinking about some of these problems?

To me, that seems intuitively, at least the robotics community has converged towards that as a space that's the canonical problem.

If you agree, then maybe do zoom in in some particular aspect of that problem that you just like?

Like if we solve that problem perfectly, it'll unlock a major step towards human level intelligence.

I don't think I have like a really great answer to that.

And I think partly the reason I don't have a great answer kind of has to do with the, it has to do with the fact that the difficulty is really in the flexibility and adaptability rather than in doing a particular thing really, really well.

So it's hard to just say like, oh, if you can, I don't know, like shuffle a deck of cards as fast as like a Vegas casino dealer, then you'll be very proficient?

It's really the ability to quickly figure out how to do some arbitrary new thing well enough to move on to the next arbitrary thing.

But the source of newness and uncertainty, Have you found problems in which it's easy to generate new newnessnesses?

Yeah, so a few years ago, so if you'd asked me this question around like 2016 maybe, I would have probably said that robotic grasping is a really great example of that because it's a task with great real world utility.

Like you will get a lot of money if you can do it well.

of money if you do it well, because lots of people want to run warehouses with robots.

And it's highly non-trivial, because very different objects will require very different grasping strategies.

But actually, since then, people have gotten really good at building systems to solve this problem,

See all Lex Fridman transcripts on Youtube

Sergey Levine: Robotics and Machine Learning | Lex Fridman Podcast #108