YouSaid · the spoken record

Leslie Kaelbling

lines on the record: 79
first: 2019-03-12
most recent: 2019-03-12
sittings or episodes: 1
sources: podcast

Every line below is reproduced as it was said and linked to the record it came from. Nothing here is summarised or generated. Directory · Search · Corrections

“Right, so now the idea is we still kind of postulate that there exists a state. We think that there is some information about the world out there such that if we knew that we could make good predictions, but we don't know the state. And so then we have to think about how, but we do get observations. Maybe I get images or I hear things or I feel things. And those might be local or noisy. And so therefore they don't tell me everything about what's going on. And then I have to reason about given the history of actions I've taken and observations I've gotten. What do I think is going on in the world? And then given my own kind of uncertainty about what's going on in the world, I can decide what actions to take.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“So market decision process is a model. It's a kind of model that you could make that says I know completely the current state of my system and what it means to be a state is that I have all the information right now that will let me make predictions about the future as well as I can so that remembering anything about my history wouldn't make my predictions any better. But then it also says that then I can take some actions that might change the state of the world and that I don't have a deterministic model of those changes. I have a probabilistic model. Of how the world might change. It's a useful model for some kinds of systems. I think it's certainly not a good model Most problems, I think, because for most problems you don't actually know the state For most problems, it's partially observed. So that's now a different problem class.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“Models some uncertainty. They model. Not present state uncertainty, but they model uncertainty in the way the future will unfold.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“So there's a stance question, right? So, a stance is a position that I take with respect to a problem. So I, as a researcher or a person who designs systems can decide to make a model of the world around me in some terms. So I take this messy world and I say, I'm going to treat it as if it were a problem of this formal kind and then I can apply solution concepts or algorithms or whatever to solve that formal thing, right? So of course the world is not anything. It's not an MDP or a POMDP. I don't know what it is, but I can model aspects of it in some way or some other way. And when I model some aspect of it in a certain way, that gives me some set of algorithms I can use.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“I think eventually, yeah. I mean, I think when we get to be better in machine learning engineers, we'll build algorithms that build awesome abstractions.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“Except for at that moment, at that moment, you do have to reason about the pose of your elbow, maybe. But then maybe you do that in some continuous joint space kind of model. So again, I. My biggest point about all of this is that there should be that dogma is not the thing, right? We shouldn't, it shouldn't be that I am in favor against symbolic reasoning and you're in favor against neural networks. It should be that just computer science tells us what the right answer to all these questions is if we were smart enough to figure it out.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“You talk about doing something during the afternoon instead of at 2.54. And you do that because it makes your reasoning problem easier and also because you don't have enough information to reason in high fidelity about your pose of your elbow at 2.35 this afternoon anyway.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“So you have to reduce the size of the state space and you have to reduce the horizon if you're going to reason about getting a PhD or even buying the ingredients to make dinner. And so how can you reduce the spaces and the horizon of the reasoning you have to do? And the answer is abstraction, spatial abstraction, temporal abstraction. I think abstraction along the lines of goals is also interesting. Like you might, or well, abstraction and decomposition. Goals is maybe more of a decomposition thing. So I think that's where these kinds of, if you want to call it symbolic or discrete models come in, you talk about a room of your house instead of your pose.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“I think the idea about, and even symbolic, I don't even like that terminology because I don't know what it means technically and formally. I do believe in abstractions. So, abstractions are critical, right? You cannot reason completely fine grain about everything in your life, right? You can't make a plan at the level of images and torques. For getting a PhD”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, okay, good. So saying that humans can't provide a description of their reasoning processes, that's okay, fine, but that doesn't mean that it's not good to do reasoning of various styles inside a computer. Those are just two orthogonal points. So then the question is, what kind of reasoning should you do inside a computer? And the answer is I think you need to do all different kinds of reasoning inside a computer depending on what kinds of problems you face.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“Not writing it down. I mean, yes, hard also to write it down for the computer. But I don't think that people can produce it. You can tell me a story about why you do stuff, but I'm not so sure that's the why.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“But even those things, I think people maybe, I think what they found, I'm not sure about this, but I think what they found was that the so-called experts could give explanations that sort of post hoc explanations for how and why they did things, but they weren't necessarily very good. And then they depended on Maybe some kinds of perceptual things, which again, they couldn't really define very well. So I think fundamentally, I think the underlying problem with that was the assumption that people could articulate how and why they make their decisions.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“Right, because we're all experts in vision, right? But totally don't have introspective access into how we do that, right? And it's true that. I mean, I think the idea was well, of course, even people then would know, of course, I wouldn't ask you to please write down the rules that you use for recognizing a water bottle. That's crazy. And everyone understood that. But we might ask you to please write down the rules you use for deciding, I don't know, what tie to put on or how to set up a microphone or something like that.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“Okay, so right. So the fact that I'm not a fan of expert systems doesn't mean that I'm not a fan of some kinds of symbolic reasoning, right? Let's see, roadblocks. Well, the main roadblock, I think, was that the idea that humans could articulate their knowledge effectively into, you know, some kind of logical statements.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“20 years later. Yeah I think that's right. Or you might decide that it's malformed. Like you might say. It's wrong to just try to make something that does superficial symbolic reasoning behave like a doctor. You can't do that until you've had the sensory motor experience of being a doctor or something, right? So there's arguments that say that that's problem was not well formed, or it could be that it is well formed, but we just weren't approaching it well.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“But maybe a little too superficially, right? So, oh, we get this surface understanding of what intelligence is like, because I understand how a steel mill works and I can try to explain it to you and you can write it down in logic and then we can make a computer infer that. And then that didn't work out. But what's interesting, I think, is when a thing starts to not be working very well. It's not only do we change methods, we change problems, right? So it's not like we have better ways of doing the problem that the expert systems people are trying to do. We have no ways of trying to do that problem. Oh, yeah, I know. I think maybe a few. But we kind of give up on that problem and we switch to a different problem. And we work that for a while and we make progress.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“One thing is that it oscillates, right? So things become fashionable and then they go out and then something else becomes cool and it goes out and so on. And I think there's some interesting sociological process that actually drives a lot of what's going on. Early days was kind of cybernetics and control, right? And the idea that of homeostasis, people who made these robots that could, I don't know, try to plug into the wall when they needed power and then come loose and roll around and do stuff. And then I think over time, the thought, well, that was inspiring, but people said, no, no, no, we want to get maybe closer to what feels like real intelligence or human intelligence. And then maybe the expert systems people tried to do that.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“No, I mean, I'm big in favor of wheel reinvention, actually. I mean, I think you learn a lot by doing it. It's important, though, to eventually have the pointers so that you can see what's really going on. But I think you can appreciate much better the good solutions once you've messed around a little bit on your own and found a bad one”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“And so the idea was to kind of use those principles to make a robot do stuff. But a lot of the basic things we had to kind of learn for ourselves, because I had zero background in robotics, I didn't know anything about control. I didn't know anything about sensors. So we reinvented a lot of wheels on the way to getting that robot to do stuff.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, okay. So I showed up at SRI and the. We were building a brand new robot. As I said, none of the people from the previous project were kind of there or involved anymore. So we were kind of starting from scratch. And my advisor was Stan Rosenchein. He ended up being my thesis advisor. And he was That the tools of logical reasoning were important, but possibly only for the engineers or designers to use in the analysis of a system, but not necessarily to be manipulated in the head of the system itself. So, I might use logic to prove a theorem about the behavior of my robot, even if the robot's not using logic in its head to prove theorems, right? So that was kind of the distinction.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“So it had representations at a bunch of different levels of abstraction. So it had, I think, a kind of an occupancy grid of some sort at the lowest level. At the high level, it was abstract symbolic kind of rooms and connectivity.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“So it could, but it, and they had painted the baseboards black. So used vision to localize itself in a map. It detected objects. It could detect objects that were surprising to it. It would plan and replan based on what it saw. It reasoned about whether to look and take pictures. It really had the basics of so many of the things that we think about now”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“Right. Well, so the first robot I worked with was Shaky was a robot that the SRI people had built. But by the time, I think when I arrived, it was sitting in a corner of somebody's office dripping hydraulic fluid into a pan. But it's iconic. And really everybody should read the Shaky Tech report because it has so many good ideas in it. I mean, they invented a star search and symbolic planning and learning macro operators. They had low-level kind of configuration space planning for their robot, they had vision, they had all this the basic ideas of a ton of things.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“Me, that doesn't seem like a philosophical gap at all. To me, there is a big technical gap, there's a huge technical gap. But I don't see any reason why it's more than a technical gap.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“The parts of philosophy that are closest to AI, I think, or at least the closest to AI that I think about are stuff like. Belief and knowledge and denotation and that kind of stuff. And that's, you know, it's quite formal and it's like just one step away from the kinds of computer science work that we do kind of routinely. Think that there are important questions still about. What you can do with a machine and what you can't, and so on, although at least my personal view is that I'm completely a materialist and I don't think that there's any reason why we can't make a robot be behaviorally indistinguishable from a human. And the question of whether it's distinguishable internally, whether it's a zombie or not in philosophy terms, I actually don't. I don't know, and I don't know if I care too much about that.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“There weren't enough people who did that for that even to be at conversation. I mean, I think probably philosophy. I mean, it's interesting. In my class, my graduating class of undergraduate philosophers probably. Maybe slightly less than half went on in computer science, slightly less than half went on in law, and like one or two went on in philosophy. So it was a common kind of connection.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“So it's surprisingly relevant. So I didn't do a computer science undergraduate degree was that there wasn't one at Stanford at the time, but that there's part of philosophy, and in fact Stanford has a special submajor in something called now symbolic systems, which is logic, model theory, formal semantics of natural language. And so that's actually a perfect preparation for work in AI and computer science.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“The robots came because my first job, so I finished an undergraduate degree in philosophy at Stanford and was about to finish master's in computer science and I got hired at SRI in their AI lab and they were building a robot. It was a kind of a follow on to Shaky, but all the shaky people were not there anymore. And so my job was to try to get this robot to do stuff. And that's really kind of what got me interested in robots.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source
“What made me get excited about AI? I can say that is I read Girdle Escher Bach when I was in high school. That was pretty formative for me. Because it exposed The interestingness of primitives and combination and how you can make complex things out of simple parts and ideas of AI and what kinds of programs might generate intelligent behavior.”
2019-03-12 · Lex Fridman Podcast · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics · IDENTIFIED FROM THE TRANSCRIPT · source