YouSaid · the spoken record

Marcus Hutter

lines on the record: 123
first: 2020-02-26
most recent: 2020-02-26
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

“I solve the AGI problem In practice, in practice. So, in theory, I've solved it with an Alexi model, but in practice. Then I ask the first question.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Big would I, yeah, yeah. So as a physicist, I was probably trained not to always think in computational terms, you know, just ignore that and think about the fundamental properties which you want to have.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Which is if you coarse granite recovers your original picture, and then I thought about the simplicity concept more in quantitative terms. And then everything developed.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“No, it was much more mundane. So I worked in this company. So in this sense, the four and a half years was not completely wasted. And I worked on an image interpolation. And I developed a quite neat new interpolation techniques and they got patented. And then which happens quite often, I got sort of overboard and thought about, you know, yeah, that's pretty good, but it's not the best. So what is the best possible way of doing interpolation? And then I thought, yeah, you want the simplest picture.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“I will tell you from the future. So from past, I would say. When I discovered my axiom. I mean, it was not in one day, but it was one moment where I realized Komogorov complexity and didn't even know. That it existed, but I recovered sort of this compression idea myself, but immediately I knew I can't be the first one. But I had this idea. And then I knew about sequential decision tree, and I knew if I put it together, this is the right thing. And still, when I think back about this moment, I'm super excited about it.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Yes, yeah, I mean, can religion tell us something about the world? Can science tell us something about the world? Can mathematics, or is it just playing with symbols? And it's open-ended questions. And, I mean, it's for high school students. So they have then resources from Hitchhiker's Guide to the Galaxy and from Star Wars and the Chicken Cross the Road. And it's fun to read, but it's also quite deep.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“No, no, it is, yeah. I mean, there's so many books out there. If you like the information theoretic approach, then there's Kolmogorf complexity by Lee and Bitani, but probably, you know, some short article is enough. You don't need to read a whole book, but it's a great book. You have to mention one all time favorite book, so different flavor, that's a book which is used in the International Baccalaureate for high school students in several countries. That's from Nicolas Alchen, Theory of Knowledge. Second edition or first, not the third place. The third one, they took out all the fun. So this asked. all the interesting or to me interesting philosophical questions about how we acquire knowledge from all perspectives, from math, from art, from physics, and ask how can we know anything. A book is called Theory of Knowledge.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“And then the next book I would recommend, the reinforcement learning book by Satan and Barto. That's a beautiful book. If there's any problem with the book, it makes RL. Feel and look much easier than it actually is. It's a very gentle book, it's very nice to read and exercises. You can very quickly get some RL systems to run, you know, in very toy problems, but it's a lot of fun. And in a couple of days, you feel you know what RL is about, but it's much harder than the book.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, yeah, both, yeah, yeah. I would always start with Russell and Norwich, artificial intelligence, a modern approach. That's the AI Bible. It's an amazing book. It's very broad. It covers all approaches to AI. And even if you focused on one approach, I think that is the minimum you should know about the other approaches out there. So that should be your first book.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Luckily, I have books and not singular book. It's very hard and I try to pin down one book. Then I can do that at the end. Most the books which were most transformative for me or which I can Highly recommend to people interested in AI.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“But if you develop an abstract agent, say we take the mathematical path and we just want to build an agent which can prove theorems and becomes a better and better mathematician, then this agent needs to be able to reason in very abstract spaces and then maybe sort of putting it into 3D environment simulated or not is even harmful. It should sort of, you put it in, I don't know, an environment which it creates itself or so.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Computer games and you train and learn the agent even if you don't intend to later put it sort of this algorithm in a robot brain and leave it forever individual reality getting experience in a Although it's just simulated 3D world is possibly, and I say possibly important to understand things on a similar level as humans do, especially if the agent or primarily if the agent needs to interact with the humans, right? If you talk about objects on top of each other and space and flying and cars and so on, and the agent has no experience with even virtual 3D worlds, it's probably hard to grasp.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Me pick the embodiment maybe so Embodiment is important, yes and no. I don't believe that we need a physical robot walking or rolling around interacting with the real world in order to achieve AGI. And I think it's more of a distraction probably than helpful. It's sort of confusing the body with the mind. For industrial applications or near-term applications, of course we need robotics for all kinds of things, but for solving the big problem, at least at this stage, I think it's not necessary. But the answer is also yes, that I think the most promising approach is that you have an agent and that can be a virtual agent, computer interacting with an environment, possibly a 3D simulated environment like in many.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“It's maybe also harder attacking the general intelligence problem. So I think enough people, I mean, maybe a small number were still interested in informalizing intelligence and thinking of general intelligence. Not much came up, right? Or not much great stuff came up.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“People got disappointed, but Narrow AI, solving particular problems which seem to require intelligence, was always to some extent successful and there were improvements, small steps. And if you build something which is useful for society or industrial useful, then there's a lot of funding. So I guess it was in parts the money which drives people to develop specific system solving specific tasks. But you would think that at least on university, you should be able to do ivory tower research. And that was probably better a long time ago, but even nowadays there's quite some pressure of doing applied research or translational research. It's harder to get grants as a theorist. So that also drives people away.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Okay, from a formal perspective, that's sort of an extra point. So I think there are a couple of reasons. I mean, AI came in waves, right? You know, AI winters and AI summers, and then there were big promises which were not fulfilled.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“It's a good thing Things, but you have heard about this Tamagotchi, which was really, really primitive actually for the And you could raise this, and kids got so attached to it. And didn't want to let it die. And if we would have asked the children, do you think this conscious? And yes, I would guess.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Is rather easy to build systems which people ascribe consciousness. And I give you an analogy. I mean, remember, maybe it was before you were born, the Tamagotchi.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“That some people say if it's just faking consciousness and feelings, then we don't need to be concerned about rights. But if it's real conscious and has feelings, then we need to be concerned.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“I think we don't have to worry about the consciousness problem, especially the heart problem for developing AGI. I think we progress. At some point, we have solved all the technical problems. And this system will behave intelligent and then super intelligent. And this consciousness will emerge. I mean, definitely it will display behavior, which we will interpret as conscious. Then it's a philosophical question, did this consciousness really emerge or is it a zombie which just fakes everything? We still don't have to figure that out, although it may be interesting, at least from a philosophical point of view, it's very interesting, but it may also be sort of practically interesting.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“I think you're. And you explain sort of somehow why, but you infer that from my behavior, right? You can never be sure about that. And I think the same thing will happen with any intelligent agent we develop. If it behaves in a way sufficiently close to humans, or maybe even not humans, I mean, you know, maybe a dog is also sometimes a little bit self-conscious, right? So if it behaves in a way where we attribute typically consciousness, we would attribute consciousness to these intelligent systems. Axi probably in particular. That of course doesn't answer the question whether it's really conscious. And that's the big hard problem of consciousness. Maybe I'm a zombie. I mean, not the movie zombie, but the philosophical zombie.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Well, some flaws, if you think more carefully about it, are actually not flaws, but I think there are still enough flaws.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Say humans are instantiation of an ICE agent. That would be amazing, but I think that's For the smartest and most rational humans, I think maybe we are very crude approximations.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Is optimal in terms of the reward collected over its interaction cycles, but it takes infinite time to produce one action. And the world continues whether you want it or not. So the model is assuming had an oracle which solved this problem and then in the next 100 milliseconds or the reaction time you need gives the answer, then ICE is optimal”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“There is ways of getting computable approximations of the Aixi model. So then it's at least computable. It is still way beyond any resources anybody will ever have. But then the Goodel machine could sort of improve it further and further in an exact way.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Would run Arxy, but that takes forever, but then if it finds approvable speed up of Arxy, it would replace it by this and this and this and maybe eventually it comes up with a model which is still the IXE model. Just for the knowledgeable reader, IX is incomputable. I can prove that therefore there cannot be a computable exact algorithm computers. There needs to be some approximations and this is not dealt with the Girdle machine. So you have to do something about it. But there's the XTL model which is finitely computable which we could put in”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Then it will take part of its resources to run this program and other part of resources to improve this program. And when it finds an improved version which provably computes the same answer. So that's the key part. It needs to prove by itself that this change of program still satisfies the original specification. And if it does so, then it replaces the original program by the improved program. And by definition, it does the same job, but just faster. And then it proves over it and over it. And it's developed in a way that all parts of this girdle machine can self-improve, but it stays provably consistent with the original specification. So from this perspective, it has nothing to do with ICSI. But if you would now put ICC as the starting axiom”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Familiar with it, he developed it while I was in his lab. The girl machine to explain it briefly, you give it a task. It could be a simple task as finding prime factors in numbers, right? You can formally write it down. There's a very slow algorithm to do that. Just all try all the factors. Or play chess, right? Optimally, you write the algorithm to minimax to the end of the game. So you write down what the Girdle machine should do.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“And for the planning part, we essentially just took the ideas from Computer Go from 2006. It was Java Zip Espari, also now I didn't mind, who developed a so-called UCT algorithm Upper Confidence bound for Trees algorithm on top of the Monte Carlo Tree search. So we approximate this planning part by sampling. Successful on some small toy problems. Want to lose the generality, right? And that's sort of the handicap, right? If you want to be general Have to give up something, but this single agent was able to play small games like Kuhn, poker and tick-tock-toe. And even Pac-Man. It's the same architecture, no change. The agent doesn't know the rules of the game, really nothing all by player with these environments.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, we have developed a couple of approximations. And what we do there is that the Saloma of induction part, which was find the shortest program describing your data, we just replaces by standard data compressors. And the better compressors get, you know, the better this part will become. We focused on a particular compressor called context-tree weighting, which is pretty amazing, not so well known. It has beautiful theoretical properties, also works reasonably well in practice. So we use that for the approximation of the induction and the learning and the prediction part.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“This computational focus would be probably significantly less. I mean, think about the induction problem is more in the philosophy department. There's really no paper who cares about, you know, how long it takes to compute the answer. That is completely secondary. Of course, once we have figured out the first problem, so intelligence without computational resources, then The next and very good question is Could we improve it by including computational resources? But nobody was able to do that so far in an even halfway satisfactory manner.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“I would say that an intelligence notion which ignores computational limits is extremely useful. A good intelligence notion which includes these resources would be even more useful, but we don't have that yet. And so look at other fields outside of computer science. Computational aspects never play a fundamental role. You develop biological models for cells something in physics. These theories, I mean, become more and more crazy and harder and harder to compute. Well, in the end, of course, we need to do something with this model, but this is more a nuisance than a feature. And I'm sometimes wondering if artificial intelligence would not sit in a computer science department, but in a”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“That is one of the criticisms about Ike that it ignores computation incompletely. And some people believe that intelligence is inherently tied to what's bounded resources.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“On top of that But this arrival and spreading sort of is, I would say, the goal or the reward function of humans, the core one”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Okay, to the first question the biological reward function is to survive and to spread and very few humans sort of are able to overcome this biological reward function. But we live in a very nice world where we have lots of spare time and can still survive and spread. So we can develop arbitrary other interests, which is quite interesting.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“I think that's a nice definition curiosity is exploration for its own sake. I would accept that. But most curiosity, well, in humans and especially in children, it's not just for its own sake, but for actually learning about the environment and for behaving better. So I think most curiosity is tied in the end towards performing better.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“The first agent had this problem, it would get stuck in front of an old TV screen which has just had white noise. The second version can deal with at least stochasticity.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“How much the agent had learned about the world. And you can rigorously formally uniquely define that in terms of diversions. So if you put that in, you get a completely autonomous agent. And actually, interestingly, for this agent, we can prove much stronger result than for the general agent, which is also nice. And if you let this agent loose, it will be, in a sense, the optimal scientist. It is absolutely curious to learn as much as possible about the world. And of course, it will also have a lot of instrumental goals, right? In order to learn, it needs to at least survive at that agent is not good for anything. So it needs to have self-preservation. And if it builds small helpers acquiring more information, it will do that if exploration, space exploration or whatever is necessary, right, to gather information and develop it. So it has a lot of instrumental goals following on this information gain. And this agent is completely autonomous.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“What does self maintenance mean? What does it mean to build a copy? Should it be the exact copy, an approximate copy? And so that's really hard. But Laurent also at DeepMind developed a beautiful model. So it just took the ICC model and coupled the rewards to information gain. So he said the reward is proportional.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“That should work reasonably well apart from these examples. It becomes critical if they become on a human level. Small children, you have reasonably well under control. They become older. The reward technique doesn't work so well anymore. So then finally, so this would be agents which are just, you could say, slaves to the humans. So if you are more ambitious and just say we want to build a new specious of intelligent beings, we put them on a new planet and we want them to develop this planet or whatever. So we don't give them any reward. So what could we do? And you could try to come up with some reward functions like it should maintain itself, the robot, it should maybe multiply, build more robots, right? And, you know, maybe all kinds of things which you find useful, but that's pretty hard, right?”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“So, even in apparently simple problems, you can make mistakes. And that's in more serious contexts AGI safety researchers consider. So now let's go back to general agents. So assume we want to build an agent which is generally useful to humans. So you have a household robot and it should do all kinds of tasks. So in this case the human should give the reward on the fly. I mean maybe it's pre-trained in the factory and there's some sort of internal reward for the battery level or whatever. But so it does the dishes badly. You punish the robot, you does it good, you rebuild the robot and then train it to a new task like a child, right? So you need the human in the loop. If you want a system which is useful to the human and as long as this agent stays subhuman level,”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Bad. You program it and you do it. And what happens is the elevator eagerly picks up all the people but never drops them off. You realize maybe the time in the elevator also counts, so you minimize the sum, yeah. The Alera does that, but never picks up the people in the 10th floor and the top floor because in expectation it's not on.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Now let's start simple. So let's assume we want to build an agent based on the IXI model which performs a particular task. Let's start with something super simple, like, I mean, super simple, like playing chess or go or something. Then you just, you know, the reward is winning the game is plus one, losing the game is minus one, done. You apply this agent. If you have enough compute, you let it self-play, and it will learn the rules of the game, will play perfect chess after some while problem solved. If you have more complicated problems, then you may believe that you have the right reword, but it's not. So a nice cute example is elevator control that is also in Rich Sutton's book, which is a great book, by the way. So you control the elevator and you think, well, maybe the rewatch should be coupled to how long people wait in front of the elevator, you know, long wait is...”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Okay, that will be a long answer. And that is a very interesting question, and I'm asked a lot about this question. Where do the rewards come from? And that depends. And I give you now a couple of answers. So if we want to build agents,”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“That's very hard, yeah. Not concerned about just storing the whole history. You can calculate human life says 30 or 100 years doesn't matter, right? How much data comes in through the vision system and the auditory system, you compress it a little bit, in this case lossily, and store it. We are soon in the means of just storing it. But you still need to the selection for the planning part and the compression for the understanding part. The raw storage, I'm really not concerned about, and I think we should just store if we develop an agent, preferably just store all the interaction history. And then you build, of course, models on top of it and you compress it and you are selective, but occasionally you go back to the old data and reanalyze it based on your new experience you have. Sometimes you are in school, you learn.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Now, I think it's absolutely crucial. The question is whether there's a way to deal with it in a more holistic and still sufficiently well way. So I have to come with an example and fly, but you have some key event in your life a long time ago in some city or something, you realize that's a really dangerous street or whatever, right? And you want to remember that forever, right? in case you come back there.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“And you can do the mathematics and figure out the optimal strategy, the so-called Bayesian agents, they're also non-Bayesian agents, but it shows that this Bayesian framework by taking a prior over possible worlds, doing the Bayesian mixture, then the base optimal decision with long-term planning that is important automatically implies exploration also to the proper extent not too much exploration and not too little in these very simple settings. In the IXI model, I was also able to prove that it is a self-optimizing theorem or asymptotic optimality theorems, although they're only asymptotic, not finite time bounds.”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, I say the good thing is that there are no parameters to control. Some other people drag knobs to control. And you can do that. I mean, you can modify axes or that you have some knobs to play with if you want to. But the exploration is directly baked in. And that comes from the Bayesian learning and the long-term planning. So these together already imply exploration. You can nicely and explicitly prove that for simple problems like so-called banded problems where you say to give a real world example say you have to medical treatments A and B, you don't know the effectiveness, you try A a little bit, B a little bit, but you don't want to harm too many patients so you have to sort of trade off exploring and at some point you want to explore”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“Quadrantic or whatever. So, and there's no recovery anymore. So the real world is not ergodic, I always say. There are traps and there are situations where you are not recovering from. And very little theory has been developed for this case”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source
“So, for instance, usually you need a goodicity assumption in the MDP frameworks in order to learn. A goodicity essentially means that you can recover from your mistakes and that they are not traps in the environment. And if you make this assumption, then essentially you can go back to a previous state, go there a couple of times and then learn what statistics and what the state is like. And then in the long run, perform well in this state, but there are no fundamental problems. But in real life, we know there can be one single action. One second of being inattentive while driving a car fast can ruin the rest of my life. I can become...”
2020-02-26 · Lex Fridman Podcast · #75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI · IDENTIFIED FROM THE TRANSCRIPT · source