Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

To create a super-intelligent machine, start with an equation

theconversation.com

Post reply on HN
Print view View original

71–80 of 87 posts

Re: To create a super-intelligent machine, start with an equation

#71

Post by xerophtye »

valtron wrote: post #51

Like others have said, this seems to be a generalization of the problem of reinforcement learning. For a good introduction to the subject, check out Reinforcement Learning by Sutton & Barto [1]. After reading the first few chapters, you'll be able to understand most of that equation. [1] http://webdocs.cs.ualberta.ca/~sutton/book/the-book.html

Yeah just looks like Q-Learning to me :/

You just use the rewards to optimize the function that tells you what's the predicted reward at any stage for a given action. And then take those best acions

Re: To create a super-intelligent machine, start with an equation

#72

Post by dwaltrip »

chongli wrote: post #39
humbledrone wrote: post #31

Earlier quoted context omitted.

Pac-Man was designed as a game for humans, with a priori knowledge of what kinds of things humans find rewarding. Thus the goal is obvious because it was designed to be similar to other human goals. Eat the food, don't get eaten. For this reason, it's not at all special that humans can determine the goal of the game.

Yeah. Try sticking a more abstract game like Go in front of a random person and see how that works out. Without being taught the rules, a human will have absolutely no idea how to proceed. This would put a human in pretty much the same boat as a computer.

Secure the largest amount of territory and capture enemy groups? Seems pretty human :p

Re: To create a super-intelligent machine, start with an equation

#73

Post by jmmcd »

maaku wrote: post #70
Houshalter wrote: post #68

Earlier quoted context omitted.

True but the approximations of it are (i.e. limiting the amount of running time each hypothesis has and limiting the number of hypothesis you test.) This is sort of like criticizing the concept of a Turing machine because no one has built one with infinite tape or running time.

Further, you can show with information theory that limiting the number of hypothesis tested or the running time does not reduce generality so long as you test up to a certain amount for a problem domain (e.g. hypothesis sizes up to the maximum representable if the causally observable universe where converted into computium, and maximum number of steps equal to the number of possible combinatorial configurations of pr…

"Constant time" is still wrong even in the approximations. Constant time means O(1). But your comment already refers to a running-time complexity dependence on several parameters of the input, such as the size of the observable universe.

Re: To create a super-intelligent machine, start with an equation

#74

Post by jmmcd »

Houshalter wrote: post #68
jmmcd wrote: post #54

Earlier quoted context omitted.

It's not constant-time. It's not even computable, even in theory, even with infinite resources.

True but the approximations of it are (i.e. limiting the amount of running time each hypothesis has and limiting the number of hypothesis you test.) This is sort of like criticizing the concept of a Turing machine because no one has built one with infinite tape or running time.

I'm not criticising AIXI, I'm just pointing out that calling it "constant time" is about as wrong as you can get, in the world of time complexity. Especially for AIXI, but also (less so) for an approximation like AIXItl.

Re: To create a super-intelligent machine, start with an equation

#75

Post by maaku »

jmmcd wrote: post #73
maaku wrote: post #70

Earlier quoted context omitted.

Further, you can show with information theory that limiting the number of hypothesis tested or the running time does not reduce generality so long as you test up to a certain amount for a problem domain (e.g. hypothesis sizes up to the maximum representable if the causally observable universe where converted into computium, and maximum number of steps equal to the number of possible combinatorial configurations of pr…

"Constant time" is still wrong even in the approximations. Constant time means O(1). But your comment already refers to a running-time complexity dependence on several parameters of the input, such as the size of the observable universe.

Size of the observable universe is constant. And maximization by exhaustive search requires touching every possible state. So yes, it is O(1). This is explained in Marcus' Ph.D. thesis, I believe.

Re: To create a super-intelligent machine, start with an equation

#76

Post by dinkumthinkum »

yetanotherphd wrote: post #63

For those having trouble getting past the hype to the actual content of AIXI, lesswrong has a nice article [1]. From the article: "The AIXI formalism says roughly to consider all possible computable models of the environment, Bayes-update them on past experiences, and use the resulting updated predictions to model the expected sensory reward of all possible strategies." I will add that the prior over models comes fro…

I don't recommend reading anything on that website. That way madness lies.

Re: To create a super-intelligent machine, start with an equation

#77

Post by tvst »

stcredzero wrote: post #45
chongli wrote: post #39

Earlier quoted context omitted.

Yeah. Try sticking a more abstract game like Go in front of a random person and see how that works out. Without being taught the rules, a human will have absolutely no idea how to proceed. This would put a human in pretty much the same boat as a computer.

A friend of mine had a meta-game he'd play with his step father. His step father would buy a new game, but not tell him the rules. They'd play this game until he figured it out and consistently trounced his step dad. Then his step dad would buy a new game.

Wow, that's a great idea. Sounds like loads of fun.

Re: To create a super-intelligent machine, start with an equation

#78

Post by jmmcd »

maaku wrote: post #75
jmmcd wrote: post #73

Earlier quoted context omitted.

"Constant time" is still wrong even in the approximations. Constant time means O(1). But your comment already refers to a running-time complexity dependence on several parameters of the input, such as the size of the observable universe.

Size of the observable universe is constant. And maximization by exhaustive search requires touching every possible state. So yes, it is O(1). This is explained in Marcus' Ph.D. thesis, I believe.

If he says so, I should admit I'm wrong, but maybe not just yet.

This way of thinking (size of the observable universe is constant) avoids the whole question of time complexity. To actually measure the time complexity of the algorithm, you need to consider inputs of different sizes. You could run exactly the same algorithm in a different universe (that is why it's called "universal" after all) and you'd get a different running time. The time complexity is then the relationship between the two running times and the universe sizes.

Re: To create a super-intelligent machine, start with an equation

#80

Post by sampo »

melloclello wrote: post #35

> AIXI now uses this model for approximately predicting the future and bases its decisions on these tentative forecasts. AIXI contemplates possible future behaviour: “If I do this action, followed by that action, etc, this or that will (un)likely happen, which could be good or bad. And if I do this other action sequence, it may be better or worse.” What I want to know, is how long does it spend doing this? Does the d…

> "is the algorithm smart enough to eventually internalise its own model of itself?"

As far as I understood, it's just random search for models ("For the planning component we use standard Monte Carlo"), and some kind of minimum description length (MDL) based method for model selection ("For the learning component we use standard file compression algorithms").

So the probability that it would, by Monte Carlo search, find a model that includes some kind of description for itself, I assume to be astronomically tiny.

(...And even if it did, it would have no way to know that it has stumbled upon a model of itself. Except the experimental performance of the model, which could or could not be better than some other models and variations.)

Post reply on HN