Re: [agi] Breaking AIXI-tl
Eliezer S. Yudkowsky wrote:
Bill Hibbard wrote:
On Fri, 14 Feb 2003, Eliezer S. Yudkowsky wrote:
It *could* do this but it *doesn't* do this. Its control process is such
that it follows an iterative trajectory through chaos which is forbidden
to arrive at a truthful solution, though it may converge to a stable
attractor.
This is the heart of the fallacy. Neither a human nor an AIXI
can know that his synchronized other self - whichever one
he is - is doing the same. All a human or an AIXI can know is
its observations. They can estimate but not know the intentions
of other minds.
The halting problem establishes that you can never perfectly understand
your own decision process well enough to predict its decision in advance,
because you'd have to take into account the decision process including the
prediction, et cetera, establishing an infinite regress.
However, Corbin doesn't need to know absolutely that his other self is
synchronized, nor does he need to know his other self's decision in
advance. Corbin only needs to establish a probabilistic estimate, good
enough to guide his actions, that his other self's decision is correlated
with his *after* the fact. (I.e., it's not a halting problem where you
need to predict yourself in advance; you only need to know your own
decision after the fact.)
AIXI-tl is incapable of doing this for complex cooperative problems
because its decision process only models tl-bounded things and AIXI-tl is
not *remotely close* to being tl-bounded.
Now you are using a different argument. You previous argument was:
Lee Corbin can work out his entire policy in step (2), before step
(3) occurs, knowing that his synchronized other self - whichever one
he is - is doing the same.
Now you have Corbin merely estimating his clone's intentions.
While it is true that AIXI-tl cannot completely simulate itself,
it also can estimate another AIXI-tl's future behavior based on
observed behavior.
Your argument is now that Corbin can do it better. I don't
know if this is true or not.
. . .
Let's say that AIXI-tl takes action A in round 1, action B in round 2, and
action C in round 3, and so on up to action Z in round 26. There's no
obvious reason for the sequence {A...Z} to be predictable *even
approximately* by any of the tl-bounded processes AIXI-tl uses for
prediction. Any given action is the result of a tl-bounded policy but the
*sequence* of *different* tl-bounded policies was chosen by a t2^l process.
Your example sequence is pretty simple and should match a
nice simple universal turing machine program in an AIXI-tl,
well within its bounds. Furthermore, two AIXI-tl's will
probably converge on a simple sequence in prisoner's
dilemma. But I have no idea if they can do it better than
Corbin and his clone.
Bill
---
To unsubscribe, change your address, or temporarily deactivate your subscription,
please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] unFriendly Hibbard SIs
Eliezer S. Yudkowsky wrote: . . . Yes. Laws (logical constraints) are inevitably ambiguous. Does that include the logical constraints governing the reinforcement process itself? There is a logic of the reinforcement process, but it is a behavior rather than a constraint on a behavior. By ambiguity, I mean for example the ambiguity of Asimov's first law that says A robot may not injure a human being, or, through inaction, allow a human being to come to harm. This is ambiguous in the situation where one human is harming another, and the law requires the robot to intervene for the victim but prohibits it from intervening against the attacker. Like, the complexity of everything the SI needs to do is some very high quantity, while the complexity of the principles that are supposed to entail it is small, right? As wonderfully demonstrated by Eric Baum's papers, complex behaviors are learned via simple values. *Some* complex behaviors can be learned via *some* simple values. The question is understanding *which* simple values result in the learning of which complex behaviors; for example, Eric Baum's system had to be created with simple values that behave in a very precise way in order to achieve its current level of learning ability. That's why Eric Baum had to write the paper, instead of just saying Aha, I can produce complex behaviors via simple values. Baum's algorithm is very carefully worked out, but the reinforcement values it learns from are simple. And a successful reinforcement learning algorithm is one that can work from any reinforcement values in any situation. . . . Yes, reinforcement learning generates very complex behaviors from there. The question is *which* complex behaviors - whether you see all the complex behaviors you want to see, and none of the complex behaviors you don't want to see. Can I take it from the above that you believe that AI morality can be created by reinforcing behaviors using a predicate P that acts on incoming video sensory information to recognize smiles and laughter and generate a reward signal? Is this adequate for a superintelligence too? The key for intelligence is a good reinforcement learning algorithm, that can work from any reinforcement values and efficiently learn behaviors that maximize those values. So the values can be simple, like recognizing smiles and laughter, and the learned behaviors can be complex, even to the point of making billions of humans happy. That qualifies as super-intelligent. Despite the wonderful work of Eric Baum and others, developing really robust reinforcement learning is a really hard challenge. Which is why my estimate for the arrival of SI is 2100 rather than 2010 or 2020. I hope I'm wrong, because I want to meet a SI. Bill --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] Breaking AIXI-tl
Eliezer/Ben, When you've had time to draw breath can you explain, in non-obscure, non-mathematical language, what the implications of the AIXI-tl discussion are? Thanks. Cheers, Philip --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
RE: [agi] Breaking AIXI-tl
Hi, There's a physical challenge which operates on *one* AIXI-tl and breaks it, even though it involves diagonalizing the AIXI-tl as part of the challenge. OK, I see what you mean by calling it a physical challenge. You mean that, as part of the challenge, the external agent posing the challenge is allowed to clone the AIXI-tl. An intuitively fair, physically realizable challenge, with important real-world analogues, formalizable as a computation which can be fed either a tl-bounded uploaded human or an AIXI-tl, for which the human enjoys greater success measured strictly by total reward over time, due to the superior strategy employed by that human as the result of rational reasoning of a type not accessible to AIXI-tl. It's really the formalizability of the challenge as a computation which can be fed either a *single* AIXI-tl or a *single* tl-bounded uploaded human that makes the whole thing interesting at all... I'm sorry I didn't succeed in making clear the general class of real-world analogues for which this is a special case. OK I don't see how the challenge you've described is formalizable as a computation which can be fed either a tl-bounded uploaded human or an AIXI-tl. The challenge involves cloning the agent being challenged. Thus it is not a computation feedable to the agent, unless you assume the agent is supplied with a cloning machine... If I were to take a very rough stab at it, it would be that the cooperation case with your own clone is an extreme case of many scenarios where superintelligences can cooperate with each other on the one-shot Prisoner's Dilemna provided they have *loosely similar* reflective goal systems and that they can probabilistically estimate that enough loose similarity exists. Yah, but the definition of a superintelligence is relative to the agent being challenged. For any fixed superintelligent agent A, there are AIXItl's big enough to succeed against it in any cooperative game. To break AIXI-tl, the challenge needs to be posed in a way that refers to AIXItl's own size, i.e. one has to say something like Playing a cooperative game with other intelligences of intelligence at least f(t,l) where if is some increasing function If the intelligence of the opponents is fixed, then one can always make an AIXItl win by increasing t and l ... So your challenges are all of the form: * For any fixed AIXItl, here is a challenge that will defeat it ForAll AIXItl's A(t,l), ThereExists a challenge C(t,l) so that fails_at(A,C) or alternatively ForAll AIXItl's A(t,l), ThereExists a challenge C(A(t,l)) so that fails_at(A,C) rather than of the form * Here is a challenge that will defeat any AIXItl ThereExists a challenge C so that ForAll AIXItl's A(t,l), fails_at(A,C) The point is that the challenge C is a function C(t,l) rather than being independent of t and l This of course is why your challenge doesn't break Hutter's theorem. But it's a distinction that your initial verbal formulation didn't make very clearly (and I understand, the distinction is not that easy to make in words.) Of course, it's also true that ForAll uploaded humans H, ThereExists a challenge C(H) so that fails_at(H,C) What you've shown that's interesting is that ThereExists a challenge C, so that: -- ForAll AIXItl's A(t,l), fails_at(A,C(A)) -- for many uploaded humans H, succeeds_at(H,C(H)) (Where, were one to try to actually prove this, one would substitute uploaded humans with other AI programs or something). The interesting part is that these little natural breakages in the formalism create an inability to take part in what I think might be a fundamental SI social idiom, conducting binding negotiations by convergence to goal processes that are guaranteed to have a correlated output, which relies on (a) Bayesian-inferred initial similarity between goal systems, and (b) the ability to create a top-level reflective choice that wasn't there before, that (c) was abstracted over an infinite recursion in your top-level predictive process. I think part of what you're saying here is that AIXItl's are not designed to be able to participate in a community of equals This is certainly true. --- Ben G --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
RE: [agi] unFriendly Hibbard SIs
Hi, Baum's algorithm is very carefully worked out, but the reinforcement values it learns from are simple. And a successful reinforcement learning algorithm is one that can work from any reinforcement values in any situation. Yeah, I don't think that Baum's algorithm need special reinforcement values. However, it is VERY slow and seems to require very careful parameter tuning. As Moshe pointed out to me, Marcus Hutter and his students tried to replicate Baum's work, with mixed results: go to http://www.idsia.ch/~marcus/ click on Artificial Intelligence and scroll down to Market-Based Reinforcement Learning in Partially Observable Worlds (with I. Kwee J. Schmidhuber) Proceedings of the 11th International Conference on Artificial Neural Networks (ICANN-2001) 865-873 Despite the wonderful work of Eric Baum and others, developing really robust reinforcement learning is a really hard challenge. Which is why my estimate for the arrival of SI is 2100 rather than 2010 or 2020. I hope I'm wrong, because I want to meet a SI. Bill, I think that *thinking about* the AGI problem as a problem of developing really robust reinforcement learning is CORRECT but UNPRODUCTIVE. I think that if you think about the problem as one of creating an integrated mind-system, and build the integrated mind-system, you will find that the robust reinforcement learning comes along due to coordinated emergent behaviors of various components. So ultimately, I don't think that ultra-clever pure-reinforcement-learning schemes like Baum's are the road to AGI, although they may play a role. It wouldn't be the first time in the history of science that a problem looked close-to-impossible from one perspective, but became manageable via a perspective-shift. -- Ben G --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
RE: [agi] Breaking AIXI-tl
hi, No, the challenge can be posed in a way that refers to an arbitrary agent A which a constant challenge C accepts as input. But the problem with saying it this way, is that the constant challenge has to have an infinite memory capacity. So in a sense, it's an infinite constant ;) No, the charm of the physical challenge is exactly that there exists a physically constant cavern which defeats any AIXI-tl that walks into it, while being tractable for wandering tl-Corbins. No, this isn't quite right. If the cavern is physically constant, then there must be an upper limit to the t and l for which it can clone AIXItl's. If the cavern has N bits (assuming a bitistic reduction of physics, for simplicity ;), then it can't clone an AIXItl where t 2^N, can it? Not without grabbing bits (particles or whatever) from the outside universe to carry out the cloning. (and how could the AIXItl with t2^N even fit inside it??) You still need the quantifiers reversed: for any AIXI-tl, there is a cavern posing a challenge that defeats it... I think part of what you're saying here is that AIXItl's are not designed to be able to participate in a community of equals This is certainly true. Well, yes, as a special case of AIXI-tl's being unable to carry out reasoning where their internal processes are correlated with the environment. Agreed... (See, it IS actually possible to convince me of something, when it's correct; I'm actually not *hopelessly* stubborn ;) ben --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] who is this Bill Hubbard I keep reading about?
Ed, I agree that it was very decent of Philip to admit to starting the mis-spelling of my name. My general complaint abou the mis-spelling was sent hours before I even read Eliezer's message, but due to the vagaries of email was delivered hours after my reply to Eliezer, giving the impression that I was fuming about it. Not so, I just wanted to let folks know it was an error. Bill, I've looked at some of your work...it's both plentiful and powerful! Personally, I like your Götterdämmerung text and the VisAD applied stuff. It seems you're the lead architect on VisAD. Is the system presently used for any gaming applications, i.e. game (3D) development platforms, e.g. OpenGL? Its not used for gaming. Its strength is that it integrates metadata such as units, coordinate systems, sampling topologies and geometries, missing data indicators, error estimates into a data model that express pretty much any numerical data. Also, it supports interfaces to a variety of scientific file and server formats, and earth navigation for a variety of earth satellites. This probably doesn't help games much, but is good for science. It does use OpenGL via Java3D. Cheers, Bill --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] Breaking AIXI-tl
Ben Goertzel wrote:
hi,
No, the challenge can be posed in a way that refers to an arbitrary agent
A which a constant challenge C accepts as input.
But the problem with saying it this way, is that the constant challenge
has to have an infinite memory capacity.
So in a sense, it's an infinite constant ;)
Infinite Turing tapes are a pretty routine assumption in operations like
these. I think Hutter's AIXI-tl is supposed to be able to handle constant
environments (as opposed to constant challenges, a significant formal
difference) that contain infinite Turing tapes. Though maybe that'd
violate separability? Come to think of it, the Clone challenge might
violate separability as well, since AIXI-tl (and hence its Clone) builds
up state.
No, the charm of the physical challenge is exactly that there exists a
physically constant cavern which defeats any AIXI-tl that walks into it,
while being tractable for wandering tl-Corbins.
No, this isn't quite right.
If the cavern is physically constant, then there must be an upper limit to
the t and l for which it can clone AIXItl's.
Hm, this doesn't strike me as a fair qualifier. One, if an AIXItl exists
in the physical universe at all, there are probably infinitely powerful
processors lying around like sunflower seeds. And two, if you apply this
same principle to any other physically realized challenge, it means that
people could start saying Oh, well, AIXItl can't handle *this* challenge
because there's an upper bound on how much computing power you're allowed
to use. If Hutter's theorem is allowed to assume infinite computing
power inside the Cartesian theatre, then the magician's castle should be
allowed to assume infinite computing power outside the Cartesian theatre.
Anyway, a constant cave with an infinite tape seems like a constant
challenge to me, and a finite cave that breaks any {AIXI-tl, tl-human}
contest up to l=googlebyte also still seems interesting, especially as
AIXI-tl is supposed to work for any tl, not just sufficiently high tl.
Well, yes, as a special case of AIXI-tl's being unable to carry out
reasoning where their internal processes are correlated with the
environment.
Agreed...
(See, it IS actually possible to convince me of something, when it's
correct; I'm actually not *hopelessly* stubborn ;)
Yes, but it takes t2^l operations.
(Sorry, you didn't deserve it, but a straight line like that only comes
along once.)
--
Eliezer S. Yudkowsky http://singinst.org/
Research Fellow, Singularity Institute for Artificial Intelligence
---
To unsubscribe, change your address, or temporarily deactivate your subscription,
please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
RE: [agi] unFriendly Hibbard SIs
Ben, As Moshe pointed out to me, Marcus Hutter and his students tried to replicate Baum's work, with mixed results: go to http://www.idsia.ch/~marcus/ click on Artificial Intelligence and scroll down to Market-Based Reinforcement Learning in Partially Observable Worlds (with I. Kwee J. Schmidhuber) Proceedings of the 11th International Conference on Artificial Neural Networks (ICANN-2001) 865-873 Thanks. Despite the wonderful work of Eric Baum and others, developing really robust reinforcement learning is a really hard challenge. Which is why my estimate for the arrival of SI is 2100 rather than 2010 or 2020. I hope I'm wrong, because I want to meet a SI. Bill, I think that *thinking about* the AGI problem as a problem of developing really robust reinforcement learning is CORRECT but UNPRODUCTIVE. I think that if you think about the problem as one of creating an integrated mind-system, and build the integrated mind-system, you will find that the robust reinforcement learning comes along due to coordinated emergent behaviors of various components. In my book I say that consciousness is part of the way the brain implements reinforcement learning, and I think something like that is necessary for a really robust solution. That's why I think it will take 100 years. I try to give short answers, which sometimes gives the mistaken impression that I think things are simple. So ultimately, I don't think that ultra-clever pure-reinforcement-learning schemes like Baum's are the road to AGI, although they may play a role. It wouldn't be the first time in the history of science that a problem looked close-to-impossible from one perspective, but became manageable via a perspective-shift. I hope that when I say something will take 100 years, that indicates that I think it is not straightforward and will require a number of major conceptual leaps. Bill --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
RE: [agi] Breaking AIXI-tl
Anyway, a constant cave with an infinite tape seems like a constant
challenge to me, and a finite cave that breaks any {AIXI-tl, tl-human}
contest up to l=googlebyte also still seems interesting, especially as
AIXI-tl is supposed to work for any tl, not just sufficiently high tl.
It's a fair mathematical challenge ... the reason I complained is that the
physical-world metaphor of a cave seems to me to imply a finite system.
A cave with an infinite tape in it is no longer a realizable physical
system!
(See, it IS actually possible to convince me of something, when it's
correct; I'm actually not *hopelessly* stubborn ;)
Yes, but it takes t2^l operations.
(Sorry, you didn't deserve it, but a straight line like that only comes
along once.)
;-)
ben
---
To unsubscribe, change your address, or temporarily deactivate your subscription,
please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] Breaking AIXI-tl
Eliezer S. Yudkowsky wrote: Let's imagine I'm a superintelligent magician, sitting in my castle, Dyson Sphere, what-have-you. I want to allow sentient beings some way to visitme, but I'm tired of all these wandering AIXI-tl spambots that script kiddies code up to brute-force my entrance challenges. I don't want to tl-bound my visitors; what if an actual sentient 10^10^15 ops/sec big wants to visit me? I don't want to try and examine the internal state of the visiting agent, either; that just starts a war of camouflage between myself and the spammers. Luckily, there's a simple challenge I can pose to any visitor, cooperation with your clone, that filters out the AIXI-tls and leaves only beings who are capable of a certain level of reflectivity, presumably genuine sentients. I don't need to know the tl-bound of my visitors, or the tl-bound of the AIXI-tl, in order to construct this challenge. I write the code once. Oh, that's trivial to break. I just put my AIXI-t1 (whatever that is) in a human body and send it via rocket-ship... There would no way to clone this being so you would have no way to carry out the test. -- I WANT A DEC ALPHA!!! =) 21364: THE UNDISPUTED GOD OF ALL CPUS. http://users.rcn.com/alangrimes/ [if rcn.com doesn't work, try erols.com ] --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
RE: [agi] unFriendly Hibbard SIs
On Sat, 15 Feb 2003, Ben Goertzel wrote: In my book I say that consciousness is part of the way the brain implements reinforcement learning, and I think something like that is necessary for a really robust solution. That's why I think it will take 100 years. I would say, rather, that consciousness and reinforcement learning are BOTH consequences of having the right kind of integrative AGI system... I look at it from the perspective of evolution of minds. There is a simple reinforcement learning mechanism in brains, as described in: HOW THE BASAL GANGLIA USE PARALLEL EXCITATORY AND INHIBITORY LEARNING PATHWAYS TO SELECTIVELY RESPOND TO UNEXPECTED REWARDING CUES. Brown, J., Bullock, D., and Grossberg, S. (1999). Journal of Neuroscience. on-line at http://cns-web.bu.edu/pub/diana/BroBulGro99.pdf But this solves the credit assignment problem in only very limited cases. I think that consciousness (and other things) evolved in order to do reinforcement learning in more general situations. That is, the need for robust reinforcement learning provided the selection pressure for consciousness. Bill --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
RE: [agi] unFriendly Hibbard SIs
But this solves the credit assignment problem in only very limited cases. I think that consciousness (and other things) evolved in order to do reinforcement learning in more general situations. That is, the need for robust reinforcement learning provided the selection pressure for consciousness. Bill Clearly, this is part of the story. But I tend to be skeptical of neo-Darwinist just so stories when applied to very complex systems. I think that spontaneous self-organization (building on evolved and self-organized components) is just as important. Consciousness (i.e. intensive focused attention, as in human consciousness) was presumably the a result of self-organization, of spontaneous emergence between evolved subsystems that evolved for specific purposes. Then, once it was there, it was reinforced by evolution because of its usefulness in reinforcement learning and other things. But consciousness also has many aspects that are not directly explicable by evolutionary selection, in my view... Ben G --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
RE: [agi] unbreakable data encryption
A few days ago this article came out: http://www.israel21c.org/bin/en.jsp?enPage=BlankPageenDisplay=viewenDi spWhat=objectenDispWho=Articles%5El306enZone=TechnologyenVersion=0 A company called Meganet is claiming that their VME encryption is unbreakable and even offering prizes such as a Ferrari or $1m. to anyone who could break into a VME-protected file. Cool huh? * Daniel Colonnese Computer Science Dept. NCSU 2718 Clark Street Raleigh NC 27670 Voice: (919) 451-3141 Fax: (775) 361-4495 http://www4.ncsu.edu:8030/~dcolonn/ * --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] Breaking AIXI-tl
Ben Goertzel wrote: In a naturalistic universe, where there is no sharp boundary between the physics of you and the physics of the rest of the world, the capability to invent new top-level internal reflective choices can be very important, pragmatically, in terms of properties of distant reality that directly correlate with your choice to your benefit, if there's any breakage at all of the Cartesian boundary - any correlation between your mindstate and the rest of the environment. Unless, you are vastly smarter than the rest of the universe. Then you can proceed like an AIXItl and there is no need for top-level internal reflective choices ;) Actually, even if you are vastly smarter than the rest of the entire universe, you may still be stuck dealing with lesser entities (though not humans; superintelligences at least) who have any information at all about your initial conditions, unless you can make top-level internal reflective choices. The chance that environmental superintelligences will cooperate with you in PD situations may depend on *their* estimate of *your* ability to generalize over the choice to defect and realize that a similar temptation exists on both sides. In other words, it takes a top-level internal reflective choice to adopt a cooperative ethic on the one-shot complex PD rather than blindly trying to predict and outwit the environment for maximum gain, which is built into the definition of AIXI-tl's control process. A superintelligence may cooperate with a comparatively small, tl-bounded AI, but be unable to cooperate with an AIXI-tl, provided there is any inferrable information about initial conditions. In one sense AIXI-tl wins; it always defects, which formally is a better choice than cooperating on the oneshot PD, regardless of what the opponent does - assuming that the environment is not correlated with your decisionmaking process. But anyone who knows that assumption is built into AIXI-tl's initial conditions will always defect against AIXI-tl. A small, tl-bounded AI that can make reflective choices has the capability of adopting a cooperative ethic; provided that both entities know or infer something about the other's initial conditions, they can arrive at a knowably correlated reflective choice to adopt cooperative ethics. AIXI-tl can learn the iterated PD, of course; just not the oneshot complex PD. -- Eliezer S. Yudkowsky http://singinst.org/ Research Fellow, Singularity Institute for Artificial Intelligence --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] unbreakable data encryption
Saturday, February 15, 2003, 1:25:19 PM, Daniel Colonnese wrote: DC A few days ago this article came out: DC http://www.israel21c.org/bin/en.jsp?enPage=BlankPageenDisplay=viewenDi DC spWhat=objectenDispWho=Articles%5El306enZone=TechnologyenVersion=0 DC A company called Meganet is claiming that their VME encryption is DC unbreakable and even offering prizes such as a Ferrari or $1m. to anyone DC who could break into a VME-protected file. DC Cool huh? On closer inspection, not really. The company and its claims have been around for a while. (And the challenge has expired). As to those claims, having recently been reading about Kolmogorov complexity, Chaitin's omega and AIT I was immediately struck by this quote from http://www.meganet.com/technology/intro.htm : The basis of VME is a Virtual Matrix, a matrix of binary values which is, in theory, infinite in size and therefore contains no redundant values. The data to be encrypted is compared to the data in the Virtual Matrix. Once a match is found, a set of pointers that indicate how to navigate inside the Virtual Matrix is created. Infinite matrix, therefore no redundant values...uhuh...just figure out the pointers -- sure. It gets worse, much worse (the data never gets sent! just some pointers! and we triple-encrypt those! etc.), and Bruce Schneier has devoted some non-too-kind words to this and other security companies' snake oil at http://www.counterpane.com/crypto-gram-9902.html -- Cliff --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] Breaking AIXI-tl
Ben Goertzel wrote: AIXI-tl can learn the iterated PD, of course; just not the oneshot complex PD. But if it's had the right prior experience, it may have an operating program that is able to deal with the oneshot complex PD... ;-) Ben, I'm not sure AIXI is capable of this. AIXI may inexorably predict the environment and then inexorably try to maximize reward given environment. The reflective realization that *your own choice* to follow that control procedure is correlated with a distant entity's choice not to cooperate with you may be beyond AIXI. If it was the iterated PD, AIXI would learn how a defection fails to maximize reward over time. But can AIXI understand, even in theory, regardless of what its internal programs simulate, that its top-level control function fails to maximize the a priori propensity of other minds with information about AIXI's internal state to cooperate with it, on the *one* shot PD? AIXI can't take the action it needs to learn the utility of... -- Eliezer S. Yudkowsky http://singinst.org/ Research Fellow, Singularity Institute for Artificial Intelligence --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
RE: [agi] Breaking AIXI-tl
I guess that for AIXI to learn this sort of thing, it would have to be rewarded for understanding AIXI in general, for proving theorems about AIXI, etc. Once it had learned this, it might be able to apply this knowledge in the one-shot PD context But I am not sure. ben -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]]On Behalf Of Eliezer S. Yudkowsky Sent: Saturday, February 15, 2003 3:36 PM To: [EMAIL PROTECTED] Subject: Re: [agi] Breaking AIXI-tl Ben Goertzel wrote: AIXI-tl can learn the iterated PD, of course; just not the oneshot complex PD. But if it's had the right prior experience, it may have an operating program that is able to deal with the oneshot complex PD... ;-) Ben, I'm not sure AIXI is capable of this. AIXI may inexorably predict the environment and then inexorably try to maximize reward given environment. The reflective realization that *your own choice* to follow that control procedure is correlated with a distant entity's choice not to cooperate with you may be beyond AIXI. If it was the iterated PD, AIXI would learn how a defection fails to maximize reward over time. But can AIXI understand, even in theory, regardless of what its internal programs simulate, that its top-level control function fails to maximize the a priori propensity of other minds with information about AIXI's internal state to cooperate with it, on the *one* shot PD? AIXI can't take the action it needs to learn the utility of... -- Eliezer S. Yudkowsky http://singinst.org/ Research Fellow, Singularity Institute for Artificial Intelligence --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED] --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] Breaking AIXI-tl
I guess that for AIXI to learn this sort of thing, it would have to be rewarded for understanding AIXI in general, for proving theorems about AIXI, etc. Once it had learned this, it might be able to apply this knowledge in the one-shot PD context But I am not sure. For those of us who have missed a critical message or two in this weekend's lengthy exchange, can you explain briefly the one-shot complex PD? I'm unsure how a program could evaluate and learn to predict the behavior of its opponent if it only gets 1-shot. Obviously I'm missing something. -Brad --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] AIXI and Solomonoff induction
The other text book that I know is by Cristian S. Calude, the Prof. of complexity theory that I studied under here in New Zealand. A new version of this book just recently came out. Going by the last version, the book will be somewhat more terse than the Li and Vitanyi book and thus more appropriate for professional mathematicans who are used to that sort of style. The Li and Vitanyi book is also a lot broader in its content thus for you I'd recommend the Li and Vitanyi book which is without doubt THE book in the field, as James already pointed out. There should be a new verson (third edition) of Li and Vitanyi sometime this year which will be interesting. Li and Vitanyi have also written quite a few introductions to the basics of the field many of which you should be able to find on the internet. Cheers Shane The Li and Vitanyi book is actually intended to be a graduate-level text in theoretical computer science (or so it says on the cover) and is formatted like a math textbook. It assumes little and pretty much starts from the beginning of the field; you should have no problems accessing the content. It is a well-written book, which is a good thing since it is sort of THE text for the field with few other choices. Cheers, -James Rogers [EMAIL PROTECTED] --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED] --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] AIXI and Solomonoff induction
Hi Cliff, Sorry about the delay... I've been out sailing watching the America's Cup racing --- just a pity my team keeps losing to the damn Swiss! :( Anyway: Cliff Stabbert wrote: SL This seems to be problematic to me. For example, a random string SL generated by coin flips is not compressible at all so would you SL say that it's alive? No, although it does take something living to flip the coins; but presumably it's non-random (physically predictable by observing externals) from the moment the coin has been flipped. The decision to call heads or tails however is not at all as *easily* physically predictable, perhaps that's what I'm getting at. But I understand your point about compressibility (expanded below). Well I could always build a machine to flip coins... Or pulls lottery balls out of a spinning drum for that matter. Is such a thing predictable, at least in theory? I have read about this sort of thing before but to be perfectly honest I don't recall the details... perhaps the Heisenberg principle makes it impossible even in theory. You would need to ask a quantum physicist I suppose. more and more quickly: the tides are more predictable than the behaviour of an ant, the ants are more predictable than a wolf, the wolves are more predictable than a human in 800 B.C., and the human in 800 B.C. is more predictable than the human in 2003 A.D. In that sense, Singularity Theory seems to be a statement of the development of life's (Kolmogorov?) complexity over time. Well it's hard to say actually. An ant is less complex than a human, but an ant really only makes sense in the context of the nest that it belongs to and, if I remember correctly, the total neural mass of some ants nests is about the same as that of a human brain. Also whales have much larger brains than humans and so are perhaps more complex in some physical sense at least. A lot of people in complexity believed that there was an evolutionary pressure driving system to become more complex. As far as I know there aren't any particularly good results in this direction -- though I don't exactly follow it much. Cheers Shane --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
