Principia Discordia

Principia Discordia => Techmology and Scientism => Topic started by: Iason Ouabache on January 29, 2010, 03:42:23 AM

Title: Altruistic robots produced through evolution
Post by: Iason Ouabache on January 29, 2010, 03:42:23 AM
http://www.tgdaily.com/general-sciences-features/48222-altruistic-robots-produced-through-evolution

QuoteA Swiss team has applied Darwinian selection to robot development, producing robots that can walk, cooperate and even hunt each other.

"Just a few hundred generations of selection are sufficient to allow robots to evolve collision-free movement, homing, sophisticated predator versus prey strategies, coadaptation of brains and bodies, cooperation, and even altruism," say the Ecole Polytechnique Fédérale de Lausanne and University of Lausanne researchers.

"In all cases this occurred via selection in robots controlled by a simple neural network, which mutated randomly."

The input neurons of the neural network were activated by the robot's sensors, and the output neurons controlled its motors.

Each robot had a different 'genome', describing different connections between neurons. This resulted in unique behaviour and fitness - how fast and straight it moved, for example, or how often it collided with obstacles.

At the beginning, the robots had random values for their genes, leading to completely random behaviours.

But Darwinian selection was then imitated, by choosing the genomes of the robots with the highest fitness to produce the next generation.

To do this, genomes were paired, and random mutations such as character substitution, insertion, deletion, or duplication were applied.

The team found that within 100 generations, robots were able to move without collisions in a maze.

When 'breeding' for predator behaviour, a range of strategies evolved, including lying in wait and circling the walls.

And, astonishingly, the robots were even able to evolve altruistic behaviour, in a task that involved pushing tokens around. Some could be pushed single-handed, earning the robot one 'fitness point'; others required two robots, gaining the whole group one point.

It was found that groups of unrelated robots - those with randomly differing genomes - invariably took the selfish approach and went for the small tokens. But those with similar genomes generally pushed the larger tokens, cooperating to raise the fitness of the whole group - and thus reducing their own chances of 'winning'.

"These examples of experimental evolution with robots verify the power of evolution by mutation, recombination, and natural selection," conclude the authors.

"The ability of robots to orientate, escape predators, and even cooperate is particularly remarkable given that they had deliberately simple genotypes directly mapped into the connection weights of neural networks comprising only a few dozen neurons."
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on January 29, 2010, 04:40:09 AM
That is the coolest motherfucking thing ever.  Holy hot dicks from hell.
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on January 29, 2010, 04:43:45 AM
What needs to happen next is evolving robot programs for specific purposes. 

This is damn cool.  I mentioned that, right?

I want to research the evolutionary pressures that helped us evolve consciousness and apply those to the brain breeding process. 

Oh damn.

I want this. 
Title: Re: Altruistic robots produced through evolution
Post by: Triple Zero on January 29, 2010, 11:42:29 AM
evolutionary programming is balls.

awesome balls.

(meaning, really good)
Title: Re: Altruistic robots produced through evolution
Post by: LMNO on January 29, 2010, 02:19:18 PM
AWESOME.  BALLS.
Title: Re: Altruistic robots produced through evolution
Post by: Captain Utopia on January 29, 2010, 04:44:07 PM
Quote from: Iason Ouabache on January 29, 2010, 03:42:23 AM
And, astonishingly, the robots were even able to evolve altruistic behaviour, in a task that involved pushing tokens around. Some could be pushed single-handed, earning the robot one 'fitness point'; others required two robots, gaining the whole group one point.
I get confused where the line between mutually beneficial and altruistic is drawn at the species level.  At a genetic level, isn't it all selfish?

For example, I think a better test for altruism would be if helping another bot (for simplicity, of the same species - not a widely differing genome) push their token didn't necessarily grant a direct benefit to the individual who was helping.
Title: Re: Altruistic robots produced through evolution
Post by: Triple Zero on January 29, 2010, 06:53:06 PM
Quote from: LMNO on January 29, 2010, 02:19:18 PM
AWESOME.  BALLS.

Yes. I should write some evolutionary programming things.

Maybe this is what I should do with all this reading abotu SVG I've been doing lately.
Title: Re: Altruistic robots produced through evolution
Post by: Reginald Ret on January 29, 2010, 10:34:44 PM
Quote from: FP on January 29, 2010, 04:44:07 PM
Quote from: Iason Ouabache on January 29, 2010, 03:42:23 AM
And, astonishingly, the robots were even able to evolve altruistic behaviour, in a task that involved pushing tokens around. Some could be pushed single-handed, earning the robot one 'fitness point'; others required two robots, gaining the whole group one point.
I get confused where the line between mutually beneficial and altruistic is drawn at the species level.  At a genetic level, isn't it all selfish?

For example, I think a better test for altruism would be if helping another bot (for simplicity, of the same species - not a widely differing genome) push their token didn't necessarily grant a direct benefit to the individual who was helping.

example is not altruism.
example is selfish.
robot that tries to push 2robot tokens gets more points than if the same robot didn't try to push 2robot token.
if robot benefits, robot not altruistic.
indirect benefits count.
it would be altruism if the robot did not benefit, but other robots did.
evolutionary pressure can't create altruism. because pressure only exists if there is benefit.

for the rest:
AWESOME. BALLS.



PS i know people will be difficult about this 'altruism can't evolve' point so let me quote a respected expert:
Quote from: Regretindirect benefits count.
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on January 29, 2010, 11:04:09 PM
Doesn't make this any less awesome.  Who cares if it's not really real altruism?  The point is that these guys have figured out how to breed robotic AI.
Title: Re: Altruistic robots produced through evolution
Post by: Kai on January 29, 2010, 11:13:32 PM
I thought this was pretty cool, until I read the journal article and realized the title said "Darwinian Selection" aka Natural Selection. What's going on in this is artificial selection. In other words, the robots aren't selected by environment, or predation, or actual fitness (ie ability to produce offspring). Humans do the selecting, discarding those with the "worst performance".
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on January 29, 2010, 11:15:30 PM
Yeah, it's closer to animal husbandry.  Again though, are labels a big deal?  This is a great idea.
Title: Re: Altruistic robots produced through evolution
Post by: Reginald Ret on January 30, 2010, 02:49:14 AM
Let me quote a respected expert:
QuoteAWESOME. BALLS.
Title: Re: Altruistic robots produced through evolution
Post by: Captain Utopia on January 30, 2010, 04:35:21 PM
Quote from: Felix on January 29, 2010, 11:15:30 PM
Yeah, it's closer to animal husbandry.  Again though, are labels a big deal?  This is a great idea.
It is awesome, although Artificial Life (http://en.wikipedia.org/wiki/Artificial_life) (rather than AI) has a semi-quack history, it's a fascinating way to play around with emergence.  I would say labels are important, however, otherwise how do you hope to understand what's really going on?


Quote from: Regret on January 29, 2010, 10:34:44 PM
Quote from: FP on January 29, 2010, 04:44:07 PM
Quote from: Iason Ouabache on January 29, 2010, 03:42:23 AM
And, astonishingly, the robots were even able to evolve altruistic behaviour, in a task that involved pushing tokens around. Some could be pushed single-handed, earning the robot one 'fitness point'; others required two robots, gaining the whole group one point.
I get confused where the line between mutually beneficial and altruistic is drawn at the species level.  At a genetic level, isn't it all selfish?

For example, I think a better test for altruism would be if helping another bot (for simplicity, of the same species - not a widely differing genome) push their token didn't necessarily grant a direct benefit to the individual who was helping.

example is not altruism.
example is selfish.
robot that tries to push 2robot tokens gets more points than if the same robot didn't try to push 2robot token.
if robot benefits, robot not altruistic.
indirect benefits count.
I agree this far.


Quote from: Regret on January 29, 2010, 10:34:44 PM
it would be altruism if the robot did not benefit, but other robots did.
The behaviour which is influenced by the genetic code is what is being used to drive the selection mechanism though.  So if robot 1 chooses to help robot 2 instead of choosing a more lucrative activity - it will end up lower on the league table as an individual, but the genes which prompted that behaviour will be higher up on the genetic league table.  I hope I'm not mangling it too much to use the metaphor of individual vs. manufacturer leaderboards in Formula One racing.

A problem I have is how did the robots identify those with similar genomes?  If it's an innate sense then that's pretty much cheating.

So an individual can still benefit from an altruistic act, as long as there is a strong expectation that they benefit less than they would have otherwise done if the individual had pursued a more selfish goal.


Although, by both our definitions, playing the lottery is altruistic.  :?


Quote from: Regret on January 29, 2010, 10:34:44 PM
evolutionary pressure can't create altruism. because pressure only exists if there is benefit.
I think you have to separate the individual (performs the actions) from the genetic (exists in multiple individuals and makes some actions more likely than others).   Otherwise, altruism doesn't exist and is a meaningless concept.
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on January 30, 2010, 05:12:21 PM
Quote from: Kai on January 29, 2010, 11:13:32 PM
I thought this was pretty cool, until I read the journal article and realized the title said "Darwinian Selection" aka Natural Selection. What's going on in this is artificial selection. In other words, the robots aren't selected by environment, or predation, or actual fitness (ie ability to produce offspring). Humans do the selecting, discarding those with the "worst performance".

I'd argue that this is splitting hairs. At what point does selection cease being natural? That's an old point, though, and it's probably been rehashed too much.

Quote from: regretAWESOME BALLS
I concur.
Title: Re: Altruistic robots produced through evolution
Post by: Triple Zero on January 30, 2010, 05:45:39 PM
Quote from: Kai on January 29, 2010, 11:13:32 PM
I thought this was pretty cool, until I read the journal article and realized the title said "Darwinian Selection" aka Natural Selection. What's going on in this is artificial selection. In other words, the robots aren't selected by environment, or predation, or actual fitness (ie ability to produce offspring). Humans do the selecting, discarding those with the "worst performance".

No not humans, computers do. This whole experiment could have run at night without humans present, until they come back the next morning and find a baby skynet in their lab. But you are correct in that the environment/"natural" selection does not.

The artificial life simulation Tierra does have something more akin to natural selection. In that simulation machine code programs have to evolve their reproduction routines themselves as well*, so the ones that do this most efficient and fast reproduce more. That would not be artificial selection, right? In this simulation, only the mutation is artificial, a tiny percentage of random bitflips in computer memory.

*except the initial organism, which is clumsily hand-coded, but replaced very quickly by more advanced automatically evolved species. but that's somewhat similar to the idea of earth life originating from a meteorite with some tiny single cellular proto fungus on it.
Title: Re: Altruistic robots produced through evolution
Post by: Mesozoic Mister Nigel on January 30, 2010, 05:54:33 PM
I keep thinking the title says "Autistic robots produced through evolution".

Anyway, to address the subject of Darwinian selection, which I suspect they used to differentiate it from "natural" selection, (and could have refined further to call "Darwinian-modeled selection) in a sense, it IS the robot's natural environment, as both robots and environment were created by humans.

And either way, it's really damn neat that the robots evolved in an unexpected manner.
Title: Re: Altruistic robots produced through evolution
Post by: Triple Zero on January 30, 2010, 05:58:16 PM
evolutionary computing is full of awesome surprises like this.
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on January 30, 2010, 06:02:40 PM
Quote from: Triple Zero on January 30, 2010, 05:58:16 PM
evolutionary computing is full of awesome surprises like this.

Like that time that the two FPGAs learned to use each other's circuits through electromagnetic resonance
Title: Re: Altruistic robots produced through evolution
Post by: Requia ☣ on January 30, 2010, 08:20:34 PM
Quote from: Regret on January 29, 2010, 10:34:44 PM
Quote from: FP on January 29, 2010, 04:44:07 PM
Quote from: Iason Ouabache on January 29, 2010, 03:42:23 AM
And, astonishingly, the robots were even able to evolve altruistic behaviour, in a task that involved pushing tokens around. Some could be pushed single-handed, earning the robot one 'fitness point'; others required two robots, gaining the whole group one point.
I get confused where the line between mutually beneficial and altruistic is drawn at the species level.  At a genetic level, isn't it all selfish?

For example, I think a better test for altruism would be if helping another bot (for simplicity, of the same species - not a widely differing genome) push their token didn't necessarily grant a direct benefit to the individual who was helping.

example is not altruism.
example is selfish.
robot that tries to push 2robot tokens gets more points than if the same robot didn't try to push 2robot token.
if robot benefits, robot not altruistic.
indirect benefits count.
it would be altruism if the robot did not benefit, but other robots did.
evolutionary pressure can't create altruism. because pressure only exists if there is benefit.

for the rest:
AWESOME. BALLS.



PS i know people will be difficult about this 'altruism can't evolve' point so let me quote a respected expert:
Quote from: Regretindirect benefits count.

The robot does not get more points if it takes the 'altruistic' path.  It gets the same number of points, but it benefits other robots, not just the two involved.  This *actively harms* the robots taking the 'altruistic' option, since it hurts their reproduction chances as individuals, but increases it for the group.
Title: Re: Altruistic robots produced through evolution
Post by: Captain Utopia on January 30, 2010, 09:43:11 PM
Quote from: Triple Zero on January 30, 2010, 05:45:39 PM
The artificial life simulation Tierra does have something more akin to natural selection. In that simulation machine code programs have to evolve their reproduction routines themselves as well*, so the ones that do this most efficient and fast reproduce more. That would not be artificial selection, right? In this simulation, only the mutation is artificial, a tiny percentage of random bitflips in computer memory.
Tierra is interesting because it evolved parasites, which would consume resources from the hosts, which then evolved to almost defeat the parasites, but then the parasites evolved yet again, to defend themselves, etc.

At that point they realised that they had forgotten to implement the mutation routine -- all this sophistication was achieved through nothing more than splicing genes.  They were surprised as their assumption was that mutation was required for any interesting behaviour to occur.
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on January 31, 2010, 06:58:15 AM
I would like to see these people work with the people who made this:

http://www.technologyreview.com/computing/22339/?a=f

Quote from: MITIn fact, the current prototype can operate about 100,000 times faster than a real human brain. "We can simulate a day in a second," says Karlheinz.
Title: Re: Altruistic robots produced through evolution
Post by: Requia ☣ on January 31, 2010, 08:22:14 AM
They already are using one of those.  Just not in hardware form.  Simulated neural nets are nothing new.

Also, I really wish people would stop comparing simulated neural nets to brains.  It's not the same thing.
Title: Re: Altruistic robots produced through evolution
Post by: Bu🤠ns on January 31, 2010, 08:32:25 AM
QuoteDespite efforts to make the chips as biologically plausible as possible, Markram admits they are still crude compared to what can be achieved in simulation. "It's not a brain. It's a more of a computer processor that has some of the accelerated parallel computing that the brain has," he says.
Title: Re: Altruistic robots produced through evolution
Post by: Reginald Ret on January 31, 2010, 11:47:57 AM
Quote from: Requia ☣ on January 30, 2010, 08:20:34 PM
Quote from: Regret on January 29, 2010, 10:34:44 PM
Quote from: FP on January 29, 2010, 04:44:07 PM
Quote from: Iason Ouabache on January 29, 2010, 03:42:23 AM
And, astonishingly, the robots were even able to evolve altruistic behaviour, in a task that involved pushing tokens around. Some could be pushed single-handed, earning the robot one 'fitness point'; others required two robots, gaining the whole group one point.
I get confused where the line between mutually beneficial and altruistic is drawn at the species level.  At a genetic level, isn't it all selfish?

For example, I think a better test for altruism would be if helping another bot (for simplicity, of the same species - not a widely differing genome) push their token didn't necessarily grant a direct benefit to the individual who was helping.

example is not altruism.
example is selfish.
robot that tries to push 2robot tokens gets more points than if the same robot didn't try to push 2robot token.
if robot benefits, robot not altruistic.
indirect benefits count.
it would be altruism if the robot did not benefit, but other robots did.
evolutionary pressure can't create altruism. because pressure only exists if there is benefit.

for the rest:
AWESOME. BALLS.



PS i know people will be difficult about this 'altruism can't evolve' point so let me quote a respected expert:
Quote from: Regretindirect benefits count.

The robot does not get more points if it takes the 'altruistic' path.  It gets the same number of points, but it benefits other robots, not just the two involved.  This *actively harms* the robots taking the 'altruistic' option, since it hurts their reproduction chances as individuals, but increases it for the group.
it accepts a new source of points, is this not an increase in potential points?
2 foodsources are better than 1.
in a medium with glucose and fructose bacteria that can use both do better than those that use only glucose.
i cant make it any clearer.
Title: Re: Altruistic robots produced through evolution
Post by: Requia ☣ on January 31, 2010, 02:02:07 PM
A) It's not food.

B) It hurts the robot to go down this path rather than be selfish.

Title: Re: Altruistic robots produced through evolution
Post by: Reginald Ret on January 31, 2010, 04:49:16 PM
Quote from: Requia ☣ on January 31, 2010, 02:02:07 PM
A) It's not food.

B) It hurts the robot to go down this path rather than be selfish.


hurt?
how?

because if that is the case you are completely right ofcourse.
Title: Re: Altruistic robots produced through evolution
Post by: Requia ☣ on January 31, 2010, 05:25:05 PM
according to the article, giving points to the other robots increases their odds of reproduction, which in turn hurts the cooperative bots since only so many get to reproduce each round, only the bots that are selfish have a high chance to reproduce.
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on January 31, 2010, 05:38:48 PM
Quote from: Requia ☣ on January 31, 2010, 08:22:14 AM
They already are using one of those.  Just not in hardware form.  Simulated neural nets are nothing new.

Also, I really wish people would stop comparing simulated neural nets to brains.  It's not the same thing.

They are similar, if simpler.  Anyway the advantage with those chips I linked is that they're physical neural nets.  Simulations require a great deal of computation to run on normal procs, this doesn't.   The article said the  robots being tested were using only a few dozen "neurons", while these chips employ hundreds.  And they're scalable.  So, no, they weren't using one of these.   Stop thinking about "neural nets aren't brains" and "really real altruism for realness" and start to think about the meaning of a robot that had a physical neural net with orders of magnitude more sophistication.
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on January 31, 2010, 05:40:25 PM
Also, altruism isn't a matter of game theory, which is how these robots are operating.  Altruism comes from intentionality (and sentimentality), which these robots tend to lack.
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on January 31, 2010, 06:02:05 PM
In the context of game theory, altruism tends to be modeled as a form of naiive and culturally-induced enlightened self interest -- since the superorganism (the community as a whole) benefits from particular types of altruism, they are encouraged regardless of the effects on the individual since if most of the individuals in the community engage in the altruistic behavior most of them likewise get the benefits of the altruism of the others.
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on January 31, 2010, 06:15:48 PM
I still see honest altruism as less a matter of whom benefits whom.  To me it is doing good things for people regardless of whether it is useful to anybody.  If I hold the door for a complete stranger for no other reason than they were a few steps behind me, that's altruism.

And that's the difference between humanistic and GT altruism, for me.
Title: Re: Altruistic robots produced through evolution
Post by: Requia ☣ on January 31, 2010, 06:26:21 PM
Yes, sentimentality and emotion are clearly more important, because in no way are those mechanisms for genes to influence behavior.
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on January 31, 2010, 06:33:01 PM
Yes, and it is so important that we think of each other like genetic mechanisms.

Fuck this, it's getting nowhere.  This thread is supposed to be about excellent technologies.

YOU LACK VISION!!!!!

(Five exclamation marks, mind you.)

*waves hands maniacally*

And stop ignoring the sheer potential here.  You people will drive me to drink.
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on January 31, 2010, 07:47:01 PM
Quote from: Requia ☣ on January 31, 2010, 06:26:21 PM
Yes, sentimentality and emotion are clearly more important, because in no way are those mechanisms for genes to influence behavior.

Emphasis added.
Title: Re: Altruistic robots produced through evolution
Post by: Requia ☣ on January 31, 2010, 08:57:39 PM
This thread is about whatever we feel like its supposed to be about, and outside of you, *nobody* brought up technology, this is science, brought about by application of old (at least in terms of computers and robotics) tech.

And yes, in the context of (some kinds of) science, its damned useful to think of people as gene mechanisms, because that brings understanding how we (and pretty much everything else that moves) work.

As for the potential, there isn't much, those chips lack the flexibility for this kind of experiment (if they had it they'd be FPGAs).  They're a bit more interesting for other applications where the general structure needed is known ahead of time, but I'd prefer the slower-but-bigger nets I could get with cheaper hardware for most applications I can think of these being useful for.
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on January 31, 2010, 09:39:40 PM
Quote from: Requia ☣ on January 31, 2010, 08:57:39 PM
This thread is about whatever we feel like its supposed to be about, and outside of you, *nobody* brought up technology, this is science, brought about by application of old (at least in terms of computers and robotics) tech.

QuoteA Swiss team has applied Darwinian selection to robot development, producing robots that can walk, cooperate and even hunt each other.

The way I see it, the development of robots with specific purposes is technology, not science.

QuoteAnd yes, in the context of (some kinds of) science, its damned useful to think of people as gene mechanisms, because that brings understanding how we (and pretty much everything else that moves) work.

You're right.  In this thread, there is a question of whether the robots are genuinely altruistic however, and I am arguing that values of altruism are different for nonsentient agents.  This research has about as much to do with biology as cellular automata, so your argument doesn't fit here.

QuoteAs for the potential, there isn't much, those chips lack the flexibility for this kind of experiment (if they had it they'd be FPGAs).  They're a bit more interesting for other applications where the general structure needed is known ahead of time, but I'd prefer the slower-but-bigger nets I could get with cheaper hardware for most applications I can think of these being useful for.

Then you simply lack vision.  Sorry.
Title: Re: Altruistic robots produced through evolution
Post by: Triple Zero on January 31, 2010, 11:01:48 PM
Quote from: FP on January 30, 2010, 09:43:11 PM
Quote from: Triple Zero on January 30, 2010, 05:45:39 PM
The artificial life simulation Tierra does have something more akin to natural selection. In that simulation machine code programs have to evolve their reproduction routines themselves as well*, so the ones that do this most efficient and fast reproduce more. That would not be artificial selection, right? In this simulation, only the mutation is artificial, a tiny percentage of random bitflips in computer memory.
Tierra is interesting because it evolved parasites, which would consume resources from the hosts, which then evolved to almost defeat the parasites, but then the parasites evolved yet again, to defend themselves, etc.

At that point they realised that they had forgotten to implement the mutation routine -- all this sophistication was achieved through nothing more than splicing genes.  They were surprised as their assumption was that mutation was required for any interesting behaviour to occur.

I have never heared the second part of that story? Are you sure? Because, since I was young I always wanted to write my own Tierra (never finished the project though) and I read a lot about it and the virtual programming language it used ... I don't quite see how that would work.

For starters, there are no genes, the genotype is the data and the code and therefore the organism. First organism was hand coded to reproduce itself without error. If you'd let it run, it would simply fill up the available memory, following your run-of-the-mill limited-growth curve.

There is no recombination, or splicing of genes. The reproduction is asexual. A program just copies itself.

The variation (and therefore evolution) happened due to two factors:

first, every clock tick there is a tiny probability that execution of a machine-instruction would fail. so a byte would copy double, some variable get incremented with the wrong value, etc.

second, there is some "radiation" type mutation going on that, with a very low probability, flips random bits in the memory.

without either of these mechanisms, reproduction would be perfect. so I assume your story refers to them forgetting to implement one of these two mechanisms? cause yeah I can imagine just the probability that an instruction would give the wrong value would give enough variation for an evolutionary battle to emerge. [assuming the second one is most like "mutation"]
Title: Re: Altruistic robots produced through evolution
Post by: Captain Utopia on February 01, 2010, 01:42:08 AM
That particular anecdote about forgetting to implement mutation comes from my twelve year old memory of Artificial Life by Steven Levy.  I looked into it a bit more for my final year uni project, although it sounds like you've spent more time looking into it than me.

I thought they could copy memory around too?  So if a program can copy a few lines of program code around, then you can end up with new functionality without any random elements or mutation or mistakes.


Meh, I should try sourcing.. I found this, though it sounds a little different from my recollection.

Quote from: http://www.infidels.org/library/modern/meta/getalife/coretierra.htmlThe power of evolution had been demonstrated, but Ray was curious to see which elements of the system were required for evolution to work, and what ranges of frequency of mutation resulted in rapid evolution. He tried turning off mutation completely, out of curiosity--and was amazed to find that evolution carried on happening anyway!

It turned out that sometimes, two programs attempting to reproduce would choose the same location for their offspring, and would interact during reproduction. One of the programs might be overwriting the same memory as the other, slightly behind, and then die from old age or be killed by another program. The result would be a hybrid, with part of the code of one program and part of the code of the other. Similar hybrids would occur if a parasite was busy reproducing using a host program, and that host program died.

Although - even though the "mutation" routine was disabled, it now looks to me as if the environment is buggy in that the above splicing is a form of mutation?
Title: Re: Altruistic robots produced through evolution
Post by: Requia ☣ on February 01, 2010, 03:33:21 AM
It evolved a new reproduction strategy that the designers never intended.

Holy shit thats awesome.

Quote
Then you simply lack vision.  Sorry.

No, i have an understanding of whats required to do anything interesting with neural nets.  See, these things are above all else *learning* programs., you can teach them to do things we aren't otherwise able to program easily, like object recognition.  But doing that requires an extremely flexible package, which means either an entirely software setup, or use FPGAs.

If you already have the net in the shape you want, then the limited flexibility these chips have isn't necessary, older techs are an option, or you can just use cheap off the shelf hardware and run a simulation.  FFS, I spent 50 dollars on enough hardware to blow away the supercomputer my university built in the  90s, special hardware to run 80s software isn't necessary.
Title: Re: Altruistic robots produced through evolution
Post by: Iason Ouabache on February 01, 2010, 08:35:33 AM
Quote from: Sigmatic on January 31, 2010, 09:39:40 PM

You're right.  In this thread, there is a question of whether the robots are genuinely altruistic however, and I am arguing that values of altruism are different for nonsentient agents.  This research has about as much to do with biology as cellular automata, so your argument doesn't fit here.
Maybe we should first prove that humans are capable of genuine altruism. ;)
Title: Re: Altruistic robots produced through evolution
Post by: Reginald Ret on February 01, 2010, 11:28:53 AM
Quote from: Requia ☣ on January 31, 2010, 05:25:05 PM
according to the article, giving points to the other robots increases their odds of reproduction, which in turn hurts the cooperative bots since only so many get to reproduce each round, only the bots that are selfish have a high chance to reproduce.
Ah thanks, i missed that.
You win this one.
Title: Re: Altruistic robots produced through evolution
Post by: Triple Zero on February 01, 2010, 11:31:57 AM
Quote from: FP on February 01, 2010, 01:42:08 AM
Quote from: http://www.infidels.org/library/modern/meta/getalife/coretierra.htmlThe power of evolution had been demonstrated, but Ray was curious to see which elements of the system were required for evolution to work, and what ranges of frequency of mutation resulted in rapid evolution. He tried turning off mutation completely, out of curiosity--and was amazed to find that evolution carried on happening anyway!

It turned out that sometimes, two programs attempting to reproduce would choose the same location for their offspring, and would interact during reproduction. One of the programs might be overwriting the same memory as the other, slightly behind, and then die from old age or be killed by another program. The result would be a hybrid, with part of the code of one program and part of the code of the other. Similar hybrids would occur if a parasite was busy reproducing using a host program, and that host program died.

Although - even though the "mutation" routine was disabled, it now looks to me as if the environment is buggy in that the above splicing is a form of mutation?

wow, okay. that IS awesome :D thanks for the source, I would not have guessed.

I do remember that one of the instructions* was some sort of equivalent to C's MALLOC function. So it would allocate a piece of free (not-alive) memory and return a pointer to it.

Another instruction which could have been called SPARK* would let the virtual machine know the just-allocated piece of memory was now to be considered "alive" and it would start being executed and get a slice of CPU time [yes this part is a bit artificial IMO, as well. he could have used a more traditional fork instruction perhaps].

Anyway, what *could* be the case, is that the MALLOC instruction would only return pointers to pieces of "dead" memory, with enough space for 1-2 times the length of the parent organism. But that means if two organism issue a MALLOC before they issue a SPARK, there is a possibility that they get pointers to partially overlapping memory ranges. It's also a typical kind of coding mistake that's easily to overlook at first, so I can see how that would happen.

Either way, AWESOME BALLS :-)

(*from a 5-bit instruction set numbering about 24 different instructions, having some duplicates to mimic the redundancy as found in DNA coding for amino-acids. which is a funny idea, but I'm not really sure whether there was any solid reasoning behind that decision or whether it might have been a kind of cargo-cultish "let's put that in here, too" choice. but from a "that's pretty cool"-point-of-view, either works)

(**except it wasn't because in those days people believed assembly language instructions had to be cryptic abbreviations, so it might have been called MFB or something. FORK would have been a cool name too)

Quote from: FPAlthough - even though the "mutation" routine was disabled, it now looks to me as if the environment is buggy in that the above splicing is a form of mutation?

well yes, sort of. of course if they'd be writing to overlapping memory locations, you'd get some kind of weird hybrid conjoined twin result program. and with those being buggy, that could also prompt more incorrect copying and just general weirdness, like how you'd call someone with a conjoined twin extra leg a "mutant" as well, perhaps ;)
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on February 01, 2010, 02:28:40 PM
Quote from: Requia ☣ on February 01, 2010, 03:33:21 AM
No, i have an understanding of whats required to do anything interesting with neural nets.  See, these things are above all else *learning* programs., you can teach them to do things we aren't otherwise able to program easily, like object recognition.  But doing that requires an extremely flexible package, which means either an entirely software setup, or use FPGAs.

Did I miss where ANNs were mentioned or was that a typo?
Title: Re: Altruistic robots produced through evolution
Post by: Requia ☣ on February 01, 2010, 02:45:27 PM
The tierra robots use them, but in the specific, Sigmatic keeps harping on about dedicated ANN chips.
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on February 01, 2010, 03:06:08 PM
Dedicated ANN chips are probably a bad idea at the moment. Analog ANN chips that use memristors and have built-in DACs and ADCs may change that situation. But, I'll admit that to dedicated ANN chips *sound* like a good idea until you take some time to think about their flaws.
Title: Re: Altruistic robots produced through evolution
Post by: Triple Zero on February 01, 2010, 03:16:55 PM
Quote from: Requia ☣ on February 01, 2010, 02:45:27 PM
The tierra robots use them, but in the specific, Sigmatic keeps harping on about dedicated ANN chips.

now you're confused?

Tierra is an artificial life simulation, sort of inspired by a "primordial soup" metaphor, using organisms running concurrently as virtual machine language processes. It does not feature ANNs [Artificial Neural Networks], nor robots.

The robots in the OP were controlled by neural nets, although it didn't say what kind.

Once one learns the math behind an ANN and how it learns and does pattern recognition, one might get the same sort of desillusionment as I did, as an ANN--while roughly based on the idea of a brain--it not so much like a brain, as more it is a stochastical method to numerically approximate a transformation from a high dimensional space to a lower dimensional one.

That doesn't mean, however, that there aren't awesome balls things to do and discover in artificial intelligence research, just that the neural network direction is probably not the place. Even if you want to equip one of your AI bots with some sort of basic pattern recognition self-learning module, most of the time there are better [and often simpler] algorithms available than neural nets. It's just that "neural network" is a term that has a lot of appeal, as opposed to Kohonen Self-Organizing Map, Learning Vector Quantization or k-Nearest Neighbour classification.
Title: Re: Altruistic robots produced through evolution
Post by: Requia ☣ on February 01, 2010, 03:25:22 PM
Er, ok, not the Tierra thing, I thought this was a continuation of the old program.

And yes, I was bitching about the comparison to brains earlier.
Title: Re: Altruistic robots produced through evolution
Post by: Captain Utopia on February 01, 2010, 03:42:37 PM
Quote from: Horrendous Foreign Love Stoat on February 01, 2010, 03:33:15 PM
so. how do we make an insane neural network then eh?
Sometimes I fear that AI will always be more breathtakingly sane than humans.  But then again, eradicating a mindless parasite intent on aimlessly consuming all of the resources it can reach, seems an eminently sane decision.
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on February 01, 2010, 06:11:17 PM
I've seen crazy bots (not crazy ANN based bots, mind you, but other kinds). They tend to be more thought-disorder/mild-schizophrenia crazy, rather than get-the-spiders-out-of-my-brain-or-the-kid-gets-it/serial-killer crazy -- which is to say they act like automated pinealists. That said, who knows what toobparts or ZalGOS would do with a tactile manipulator.
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on February 01, 2010, 08:17:56 PM
The reason I brought up analog neural networks is because they appear to be a much more sophisticated version of what the robots in the OP were using.  I linked to an MIT Technology review article (http://www.technologyreview.com/computing/22339/page2/) that talks about a separate invention that is tangentially related to the OP.  I wanted to remark that combining these technologies would be interesting, but it came across poorly.
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on February 01, 2010, 08:19:34 PM
ANN typically stands for artificial neural network, not analog neural network. There is a very different term for an analog electronic neuron simulation.
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on February 01, 2010, 08:23:34 PM
Quote from: Enki v. 2.0 on February 01, 2010, 08:19:34 PM
ANN typically stands for artificial neural network, not analog neural network. There is a very different term for an analog electronic neuron simulation.

I never even mentioned artificial neural networks, jeez.  Did you even click the link?  Do you think it's a rickroll or something?
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on February 01, 2010, 08:29:23 PM
Quote from: Sigmatic on February 01, 2010, 08:17:56 PM
The reason I brought up analog neural networks

Quote from: ENKI-2
ANN typically stands for artificial neural network, not analog neural network. There is a very different term for an analog electronic neuron simulation.

We were talking about ANNs for the last page, with the implicit understanding that ANN stood for artificial neural network. I was making this explicit, since you brought up analog neural networks (which would of course also be abbreviated ANN, and given the context, implied strongly that you were expanding the acronym differently from the rest of us).
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on February 01, 2010, 08:32:42 PM
Okay, okay.  I get that you were talking about artificial neural networks.  Here's what I'm getting at.  The OP article said

Quote"The ability of robots to orientate, escape predators, and even cooperate is particularly remarkable given that they had deliberately simple genotypes directly mapped into the connection weights of neural networks comprising only a few dozen neurons."

While the link I provided says these other guys have produced a chip that has

Quote200,000 neurons linked up by 50 million synaptic connections, the chip is able to mimic the brain's ability to learn more closely than any other machine.

Please tell me you can see why I mentioned this.
Title: Re: Altruistic robots produced through evolution
Post by: Requia ☣ on February 01, 2010, 09:03:45 PM
I can see why, and as I've said, that chip is *completely useless* no matter how many neurons are on it, ANNs require flexibility to be useful, for an experiment like the one the OP posted this is doubly true, and according to TFA you posted, the chip isn't as flexible as the simulations are.
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on February 01, 2010, 09:31:16 PM
On top of that, these days people want to actually SAVE their neural nets. If the power goes out or the backup battery goes on that chip, pop goes the brain.
Title: Re: Altruistic robots produced through evolution
Post by: Triple Zero on February 01, 2010, 11:32:09 PM
Quote from: Sigmatic on February 01, 2010, 08:23:34 PM
Quote from: Enki v. 2.0 on February 01, 2010, 08:19:34 PM
ANN typically stands for artificial neural network, not analog neural network. There is a very different term for an analog electronic neuron simulation.

I never even mentioned artificial neural networks, jeez.  Did you even click the link?  Do you think it's a rickroll or something?

no, it's worse, it's a popular science article without any explanation whatsoever about what the researchers actually DID.

Quote from: Sigmatic on February 01, 2010, 08:32:42 PM
Okay, okay.  I get that you were talking about artificial neural networks.  Here's what I'm getting at.  The OP article said

Quote"The ability of robots to orientate, escape predators, and even cooperate is particularly remarkable given that they had deliberately simple genotypes directly mapped into the connection weights of neural networks comprising only a few dozen neurons."

While the link I provided says these other guys have produced a chip that has

Quote200,000 neurons linked up by 50 million synaptic connections, the chip is able to mimic the brain's ability to learn more closely than any other machine.

Please tell me you can see why I mentioned this.

well yes, I see why you mentioned this.

and I don't like what I see.

because you seem to imply that more neurons = smarter AI.

I tried to explain in my previous post, but you;re really stuck on your concept of what you think are "neural networks".

see, the things that consist of a few dozen neurons in the robot controllers are completely different things than the stuff in the 200,000 neuron simulation.

for starters, apart from some superficial similarities, the neurons these two systems consist of aren't even the same things, so it doesn't really make any sense to compare them.

the robot controller neural nets are the pattern recognition algorithms I somewhat explained in my previous post, which are commonly known as Artificial Neural Networks, abbreviated as ANNs. using the abbreviation for something else is really confusing. [and yes it is a pretty standard abbreviation, just check how many scientific AI symposia there are with ANN in their title, and notice it always means "artificial"]

now the 200,000 neuron thing. while probably really impressive, as far as I've understood these things are only useful from a sort of neuro/bio/physiological point of view. they're basically bruteforce simulating parts of the brain. usually rat brains, it seems. now these things may do some kind of pattern recognition, if you try hard enough, but that's not really what they're made for, and I wouldn't even know if they'd be any better at it than the (mathematically proven) traditional algorithms.

no they are used for completely different kinds of research. think of it more like a dummy. basically they got this simulation of a part of the brain (afaik they got up to a beam of synapses in the cortex by now) which is built to mimic the physiological/biological original as close as possible. yep, that is including differential equations to model the reaction and diffusion of neurotransmitter chemicals. the cool thing about this, is if you want to test it, and/or figure out how it works, you don't need to cut open a rat every time, and most importantly, you can look at it while it's running.

and yes, those things do exhibit aspects of learning. but probably not the kind of reasoning-learning you are thinking of. that's a bit too high level for a beam of synapses in a rat's cortex. actually I wonder if rats can even reason? anyway that;s not the point, the kind of learning it displays is more like a few levels below classic pavlov conditioning. neurons that get excited more often, get stronger pathways and therefore excite even more often, and that's basically the building block for learning.

but that doesn;t make a cool popular science article. and that is why, if you're really serious about this stuff, you should avoid those articles and click through until you find something written in LaTeX, with formulas in it, that gives you the deep rundown of what they actually do instead of what the scientific journalists make of it.

anyway if you want to make a cool AI like what you're aiming at, i'm not saying it can't be done, but I think it's kind of cumbersome to make a simulation that low level. if you want to replicate the biological functions so that you can learn more about our own brains, sure. but if you just need the behaviour, you're wasting resources on accuracy that is unnecessary. it's already a computer, after all. you could jam much more artificial neurons into a chip if you took some liberties and they dont have to function exactly numerically like biological neurons. after all, the intelligence is not in the matter that it's made of, but in the patterns that appear/emerge in that matter, right?
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on February 02, 2010, 02:32:29 AM
Thanks for taking to time to write a comprehensive clarification, 000.  I think I need to spend more time reading academic works on the things I profess to be interested in.
Title: Re: Altruistic robots produced through evolution
Post by: BabylonHoruv on February 04, 2010, 08:26:24 AM
Quote from: Sigmatic on January 31, 2010, 05:40:25 PM
Also, altruism isn't a matter of game theory, which is how these robots are operating.  Altruism comes from intentionality (and sentimentality), which these robots tend to lack.

How do you know?
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on February 04, 2010, 08:37:39 AM
How do I know what?
Title: Re: Altruistic robots produced through evolution
Post by: BabylonHoruv on February 04, 2010, 08:41:16 AM
Quote from: Sigmatic on February 04, 2010, 08:37:39 AM
How do I know what?

That they lack intentionality and sentimentality.
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on February 04, 2010, 08:54:16 AM
That is a very simple question, and the answer is unfortunately not.

Determining intentionality in other beings is an inductive practice, due to the limits of describability of multimodal experiences, including conscious states such as intentionality. 

In one sense you could say that intentionality is the quality of an agent's behavior towards an objective with special regard to an expected outcome (e.g. I threw the ball with the intention that the dog fetch it.)

However due to the lack of dialog between man and robot, we cannot verify this intention verbally.  It is not likely that the researchers made a robot that can answer the question, "What did you intend by this action?"   In fact, the capacity to even act with special regard to an expected outcome implies a certain amount of metacognition. 

In the end, we can predict how the robots will act by assigning intentionality to their actions by saying "the robot is trained to want this outcome, so it will do x behavior", but we have no good evidence that they are intentional agents.
Title: Re: Altruistic robots produced through evolution
Post by: BabylonHoruv on February 04, 2010, 09:04:12 AM
Quote from: Sigmatic on February 04, 2010, 08:54:16 AM
That is a very simple question, and the answer is unfortunately not.

Determining intentionality in other beings is an inductive practice, due to the limits of describability of multimodal experiences, including conscious states such as intentionality. 

In one sense you could say that intentionality is the quality of an agent's behavior towards an objective with special regard to an expected outcome (e.g. I threw the ball with the intention that the dog fetch it.)

However due to the lack of dialog between man and robot, we cannot verify this intention verbally.  It is not likely that the researchers made a robot that can answer the question, "What did you intend by this action?"   In fact, the capacity to even act with special regard to an expected outcome implies a certain amount of metacognition. 

In the end, we can predict how the robots will act by assigning intentionality to their actions by saying "the robot is trained to want this outcome, so it will do x behavior", but we have no good evidence that they are intentional agents.

We don't have any particular evidence that dogs are intentional agents for that matter, but we do tend to assume it.  Sentimentality as well.  We assume robots are not.  We don't really have any reason to do so in either case, so far as I can tell, except that dogs, like us, are made out of meat and robots aren't.
Title: Re: Altruistic robots produced through evolution
Post by: Captain Utopia on February 04, 2010, 09:11:37 AM
Moreover, I disagree with the premise that altruism requires "intentionality (and sentimentality)".  Or either, even.  Certainly, in this context, having a sentient AI which could answer questions like those posed above would be a far greater achievement than altruism.
Title: Re: Altruistic robots produced through evolution
Post by: BabylonHoruv on February 04, 2010, 09:18:14 AM
Quote from: FP on February 04, 2010, 09:11:37 AM
Moreover, I disagree with the premise that altruism requires "intentionality (and sentimentality)".  Or either, even.  Certainly, in this context, having a sentient AI which could answer questions like those posed above would be a far greater achievement than altruism.

Not really.  iGod can answer questions like that.  On the other hand it can't do any of the things the "altruistic" robots can do.
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on February 04, 2010, 11:51:32 AM
Isn't the status quo in cognitive science currently that humans lack intentionality, and that the reasoning behind our actions is just rationalization made up after the fact?
Title: Re: Altruistic robots produced through evolution
Post by: Captain Utopia on February 04, 2010, 02:11:34 PM
Quote from: BabylonHoruv on February 04, 2010, 09:18:14 AM
Quote from: FP on February 04, 2010, 09:11:37 AM
Moreover, I disagree with the premise that altruism requires "intentionality (and sentimentality)".  Or either, even.  Certainly, in this context, having a sentient AI which could answer questions like those posed above would be a far greater achievement than altruism.

Not really.  iGod can answer questions like that.  On the other hand it can't do any of the things the "altruistic" robots can do.
I assume you're joking - iGod is just A.L.I.C.E. (http://en.wikipedia.org/wiki/Artificial_Linguistic_Internet_Computer_Entity) -  it matches against patterns in sentence structure but has no comprehension of the conversation, other than a few pre-programmed responses on predictable subjects.  It's a clever trick, but it's not sentience.
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on February 04, 2010, 07:41:22 PM
Quote from: FP on February 04, 2010, 02:11:34 PM
Quote from: BabylonHoruv on February 04, 2010, 09:18:14 AM
Quote from: FP on February 04, 2010, 09:11:37 AM
Moreover, I disagree with the premise that altruism requires "intentionality (and sentimentality)".  Or either, even.  Certainly, in this context, having a sentient AI which could answer questions like those posed above would be a far greater achievement than altruism.

Not really.  iGod can answer questions like that.  On the other hand it can't do any of the things the "altruistic" robots can do.
I assume you're joking - iGod is just A.L.I.C.E. (http://en.wikipedia.org/wiki/Artificial_Linguistic_Internet_Computer_Entity) -  it matches against patterns in sentence structure but has no comprehension of the conversation, other than a few pre-programmed responses on predictable subjects.  It's a clever trick, but it's not sentience.

It can answer questions like that. It can't necessarily answer them CORRECTLY. (Answering questions has no bearing on sentience OR sapience, of course...)
Title: Re: Altruistic robots produced through evolution
Post by: Captain Utopia on February 04, 2010, 07:46:41 PM
Let's not go into the chinese room.
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on February 04, 2010, 07:49:32 PM
 :argh!: Motherfucking chinese room  :argh!:

Bitches don't know about the Church-Turing Computability Theorem!
Title: Re: Altruistic robots produced through evolution
Post by: Captain Utopia on February 04, 2010, 07:52:15 PM
 :lulz:
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on February 04, 2010, 10:17:20 PM
Quote from: Enki v. 2.0 on February 04, 2010, 11:51:32 AM
Isn't the status quo in cognitive science currently that humans lack intentionality, and that the reasoning behind our actions is just rationalization made up after the fact?

I heard about this a while ago, and ever since then I keep checking my own behaviors against this, and so far I can't find any evidence to prove it wrong.

Title: Re: Altruistic robots produced through evolution
Post by: Requia ☣ on February 05, 2010, 02:40:11 AM
Quote from: Enki v. 2.0 on February 04, 2010, 11:51:32 AM
Isn't the status quo in cognitive science currently that humans lack intentionality, and that the reasoning behind our actions is just rationalization made up after the fact?

No.

Not that there aren't people who argue that, but its based on a gross misinterpretation of an experiment on quick responses (if you don't give someone time to think about their response, they will give a response then rationalize it afterwards, there's no evidence this occurs if people have time to think things over.)
Title: Re: Altruistic robots produced through evolution
Post by: Iason Ouabache on February 05, 2010, 08:47:29 AM
Quote from: BabylonHoruv on February 04, 2010, 09:04:12 AM
Quote from: Sigmatic on February 04, 2010, 08:54:16 AM
That is a very simple question, and the answer is unfortunately not.

Determining intentionality in other beings is an inductive practice, due to the limits of describability of multimodal experiences, including conscious states such as intentionality. 

In one sense you could say that intentionality is the quality of an agent's behavior towards an objective with special regard to an expected outcome (e.g. I threw the ball with the intention that the dog fetch it.)

However due to the lack of dialog between man and robot, we cannot verify this intention verbally.  It is not likely that the researchers made a robot that can answer the question, "What did you intend by this action?"   In fact, the capacity to even act with special regard to an expected outcome implies a certain amount of metacognition. 

In the end, we can predict how the robots will act by assigning intentionality to their actions by saying "the robot is trained to want this outcome, so it will do x behavior", but we have no good evidence that they are intentional agents.

We don't have any particular evidence that dogs are intentional agents for that matter, but we do tend to assume it.  Sentimentality as well.  We assume robots are not.  We don't really have any reason to do so in either case, so far as I can tell, except that dogs, like us, are made out of meat and robots aren't.
TITCM. I see intentionality a bit like sincerity: if you can fake that, you've got it made. A simulation of intentionality would be indistinguishable from real intentionality. There is no test you can run on intentionality that can't be cheated. Same thing with a simulation of altruism. If you can program a robot to appear to be altruistic then it would be altruistic. Altruism isn't a state of mind, it is an action.

IMHO, altruism is over-rated anyways. More often then not it is pure illusion. What appears to be selfless behavior is really meant to protect a gene or meme. Plus no one would be altruistic if it didn't give us an over-inflated sense of self-righteousness, you fucking hedonists.
Title: Re: Altruistic robots produced through evolution
Post by: Captain Utopia on February 05, 2010, 03:05:31 PM
Quote from: Iason Ouabache on February 05, 2010, 08:47:29 AM
IMHO, altruism is over-rated anyways. More often then not it is pure illusion. What appears to be selfless behavior is really meant to protect a gene or meme. Plus no one would be altruistic if it didn't give us an over-inflated sense of self-righteousness, you fucking hedonists.
From a zoological perspective, altruism is a useful pattern in studying genetically-influenced behaviour in individuals.  So to say that a potentially altruistic individual hastens their own death only to protect genetics present in a group, or because they exist in a society where this is mutually beneficial, is both restating the obvious and missing the point.

I assumed, given the subject matter, we were talking about zoological altruism?
Title: Re: Altruistic robots produced through evolution
Post by: Freeky on February 05, 2010, 06:19:49 PM
Quote from: Iason Ouabache on February 05, 2010, 08:47:29 AM
IMHO, altruism is over-rated anyways. More often then not it is pure illusion. What appears to be selfless behavior is really meant to protect a gene or meme. Plus no one would be altruistic if it didn't give us an over-inflated sense of self-righteousness, you fucking hedonists.

Hey... I like doing things for other people with no benefit to me, and it doesn't make me feel self-righteous. :sad:
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on February 05, 2010, 07:54:43 PM
Quote from: Mistress Freeky on February 05, 2010, 06:19:49 PM
Quote from: Iason Ouabache on February 05, 2010, 08:47:29 AM
IMHO, altruism is over-rated anyways. More often then not it is pure illusion. What appears to be selfless behavior is really meant to protect a gene or meme. Plus no one would be altruistic if it didn't give us an over-inflated sense of self-righteousness, you fucking hedonists.

Hey... I like doing things for other people with no benefit to me, and it doesn't make me feel self-righteous. :sad:

It means that your neighbours will survive at your expense, come the revolution (or something).
Title: Re: Altruistic robots produced through evolution
Post by: Freeky on February 05, 2010, 08:01:35 PM
No, I don't think so. When push comes to shove, it's a different matter entirely.
Title: Re: Altruistic robots produced through evolution
Post by: Iason Ouabache on February 05, 2010, 08:04:15 PM
Quote from: Mistress Freeky on February 05, 2010, 06:19:49 PM
Quote from: Iason Ouabache on February 05, 2010, 08:47:29 AM
IMHO, altruism is over-rated anyways. More often then not it is pure illusion. What appears to be selfless behavior is really meant to protect a gene or meme. Plus no one would be altruistic if it didn't give us an over-inflated sense of self-righteousness, you fucking hedonists.

Hey... I like doing things for other people with no benefit to me, and it doesn't make me feel self-righteous. :sad:
You got enjoyment from helping others. You got your reward, hedonist. ;)
Title: Re: Altruistic robots produced through evolution
Post by: Iason Ouabache on February 05, 2010, 08:06:59 PM
Quote from: FP on February 05, 2010, 03:05:31 PM
Quote from: Iason Ouabache on February 05, 2010, 08:47:29 AM
IMHO, altruism is over-rated anyways. More often then not it is pure illusion. What appears to be selfless behavior is really meant to protect a gene or meme. Plus no one would be altruistic if it didn't give us an over-inflated sense of self-righteousness, you fucking hedonists.
From a zoological perspective, altruism is a useful pattern in studying genetically-influenced behaviour in individuals.  So to say that a potentially altruistic individual hastens their own death only to protect genetics present in a group, or because they exist in a society where this is mutually beneficial, is both restating the obvious and missing the point.

I assumed, given the subject matter, we were talking about zoological altruism?
I don't see a difference between zoological and non-zoological altruism. Actions are actions whether they come from an organic machine or a metal/silicon machine.
Title: Re: Altruistic robots produced through evolution
Post by: Freeky on February 05, 2010, 09:05:47 PM
Quote from: Iason Ouabache on February 05, 2010, 08:04:15 PM
Quote from: Mistress Freeky on February 05, 2010, 06:19:49 PM
Quote from: Iason Ouabache on February 05, 2010, 08:47:29 AM
IMHO, altruism is over-rated anyways. More often then not it is pure illusion. What appears to be selfless behavior is really meant to protect a gene or meme. Plus no one would be altruistic if it didn't give us an over-inflated sense of self-righteousness, you fucking hedonists.

Hey... I like doing things for other people with no benefit to me, and it doesn't make me feel self-righteous. :sad:
You got enjoyment from helping others. You got your reward, hedonist. ;)
:lulz:
Title: Re: Altruistic robots produced through evolution
Post by: BabylonHoruv on February 07, 2010, 05:43:39 AM
Quote from: FP on February 04, 2010, 02:11:34 PM
Quote from: BabylonHoruv on February 04, 2010, 09:18:14 AM
Quote from: FP on February 04, 2010, 09:11:37 AM
Moreover, I disagree with the premise that altruism requires "intentionality (and sentimentality)".  Or either, even.  Certainly, in this context, having a sentient AI which could answer questions like those posed above would be a far greater achievement than altruism.

Not really.  iGod can answer questions like that.  On the other hand it can't do any of the things the "altruistic" robots can do.
I assume you're joking - iGod is just A.L.I.C.E. (http://en.wikipedia.org/wiki/Artificial_Linguistic_Internet_Computer_Entity) -  it matches against patterns in sentence structure but has no comprehension of the conversation, other than a few pre-programmed responses on predictable subjects.  It's a clever trick, but it's not sentience.

I didn't say it was Sentient, it clearly isn't.  But if you were to ask it those questions it would answer you.
Title: Re: Altruistic robots produced through evolution
Post by: Reginald Ret on February 07, 2010, 06:44:41 PM
i like this thread.
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on February 07, 2010, 06:54:17 PM
Quote from: Iason Ouabache on February 05, 2010, 08:04:15 PM
Quote from: Mistress Freeky on February 05, 2010, 06:19:49 PM
Quote from: Iason Ouabache on February 05, 2010, 08:47:29 AM
IMHO, altruism is over-rated anyways. More often then not it is pure illusion. What appears to be selfless behavior is really meant to protect a gene or meme. Plus no one would be altruistic if it didn't give us an over-inflated sense of self-righteousness, you fucking hedonists.

Hey... I like doing things for other people with no benefit to me, and it doesn't make me feel self-righteous. :sad:
You got enjoyment from helping others. You got your reward, hedonist. ;)

By your standard of altruism there can be no such thing.

Your definition of altruism is therefore dysfunctional.

Altruism is only definable in terms of humanistic feeling.
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on February 07, 2010, 07:02:14 PM
Quote from: Sigmatic on February 07, 2010, 06:54:17 PM
Quote from: Iason Ouabache on February 05, 2010, 08:04:15 PM
Quote from: Mistress Freeky on February 05, 2010, 06:19:49 PM
Quote from: Iason Ouabache on February 05, 2010, 08:47:29 AM
IMHO, altruism is over-rated anyways. More often then not it is pure illusion. What appears to be selfless behavior is really meant to protect a gene or meme. Plus no one would be altruistic if it didn't give us an over-inflated sense of self-righteousness, you fucking hedonists.

Hey... I like doing things for other people with no benefit to me, and it doesn't make me feel self-righteous. :sad:
You got enjoyment from helping others. You got your reward, hedonist. ;)

By your standard of altruism there can be no such thing.

Your definition of altruism is therefore dysfunctional.

Altruism is only definable in terms of humanistic feeling.

Obviously, my definition of unicorn is dysfunctional.
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on February 07, 2010, 07:06:25 PM
QuoteObviously, my definition of unicorn is dysfunctional.


It's more likely than you think.
Title: Re: Altruistic robots produced through evolution
Post by: Captain Utopia on February 07, 2010, 09:18:39 PM
Quote from: Sigmatic on February 07, 2010, 06:54:17 PM
Altruism is only definable in terms of humanistic feeling.
Human altruism is only definable in terms of humanistic feeling, zoological altruism is a observable behaviour pattern in some other creatures.
Title: Re: Altruistic robots produced through evolution
Post by: Reginald Ret on February 07, 2010, 10:15:51 PM
Quote from: FP on February 07, 2010, 09:18:39 PM
Quote from: Sigmatic on February 07, 2010, 06:54:17 PM
Altruism is only definable in terms of humanistic feeling.
Human altruism is only definable in terms of humanistic feeling, zoological altruism is a observable behaviour pattern in some other creatures.
real altruism can't occur in a evolving system.
'humanistic altruism' cant occur outside of humans.
these robots are selfish bastards either way.
Title: Re: Altruistic robots produced through evolution
Post by: Captain Utopia on February 07, 2010, 10:26:15 PM
What the heck is "real altruism"  :?
Title: Re: Altruistic robots produced through evolution
Post by: Reginald Ret on February 07, 2010, 10:41:22 PM
i think i mean what you call zoological altruism.
i just call it altruism.
Title: Re: Altruistic robots produced through evolution
Post by: Captain Utopia on February 07, 2010, 10:52:51 PM
So you're saying that zoological altruism can't occur in an evolving system?
Title: Re: Altruistic robots produced through evolution
Post by: Reginald Ret on February 07, 2010, 11:13:32 PM
i'm saying it can't evolve.
but it is not my specialty, and if someone can expertly explain it to me i'd be happy.

i kinda feel like im about to get my arse kicked with science and/or fact here, so go ahead and have fun.
Title: Re: Altruistic robots produced through evolution
Post by: Golden Applesauce on February 08, 2010, 12:12:29 AM
Quote from: Regret on February 07, 2010, 11:13:32 PM
i'm saying it can't evolve.
but it is not my specialty, and if someone can expertly explain it to me i'd be happy.

i kinda feel like im about to get my arse kicked with science and/or fact here, so go ahead and have fun.

I'd be happy too, if you explain which meaning of "altruism" you're talking about.
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on February 08, 2010, 01:29:48 AM
The altruism that can be explained is not the true altruism. (Likewise, the magic that can be explained is not the true magic, and unicorns are only definable in terms of pixie dust and giant planet-eating love muffins from out of space.)
Title: Re: Altruistic robots produced through evolution
Post by: Reginald Ret on February 08, 2010, 02:46:09 PM
Altruism is helping others without direct or indirect profit to yourself.
It costs energy/time/something and gives you nothing back.
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on February 08, 2010, 06:12:53 PM
Quote from: Regret on February 08, 2010, 02:46:09 PM
Altruism is helping others without direct or indirect profit to yourself.
It costs energy/time/something and gives you nothing back.

If it gives nothing back (not even a modicum of pleasure), then what you're describing is tantamount to  martyrdom.
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on February 08, 2010, 06:37:36 PM
Martyrdom isn't altruistic either. After all, every martyr knows that all martyrs are honored posthumously.
Title: Re: Altruistic robots produced through evolution
Post by: Captain Utopia on February 08, 2010, 06:56:31 PM
I give up.  Wake me when this thread has any relevance to cool robots and/or altruistic behaviour in non-sentient creatures.
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on February 08, 2010, 06:59:39 PM
Who knew altruism would be so controversial on PDcom? 

You're right though FP, the point of this thread is cool robots.
Title: Re: Altruistic robots produced through evolution
Post by: Captain Utopia on February 08, 2010, 07:16:02 PM
It's not a subject without controversy (http://en.wikipedia.org/wiki/Altruism_in_animals), and neither am I an expert in any field related to this, though I can't help but think it bears more relevance to the analysis of robotic behaviour patterns than talk of unicorns or martyrs or how sentient minds consider or imagine past and future events in order to perform an action which may or may not subsequently be endlessly philosophized as whether it leans more towards selfishness or altruism.
Title: Re: Altruistic robots produced through evolution
Post by: Jasper on February 08, 2010, 07:29:04 PM
Yes.

So, are these robots zoologically altruistic?
Title: Re: Altruistic robots produced through evolution
Post by: Captain Utopia on February 08, 2010, 09:11:54 PM
The actual paper (http://www.plosbiology.org/article/fetchObjectAttachment.action?uri=info%3Adoi%2F10.1371%2Fjournal.pbio.1000292&representation=PDF) clarifies a few things - the large tokens (all individuals in group get 1 point) which require two bots to push have a higher cost than pushing a small token (only that individual gets 1 point).  This does move the cost/benefit ratio closer towards altruism.

The key to all of these simulations is that they make certain abstractions, and it's crucial to identify those and at least make some estimation as to how these abstractions effect the fidelity of the simulation.  For example - the simulation used 100 groups, which contained 10 individuals each, and the individuals were able to identify group-members with regards how similar their genomes were and use that input to drive behaviours based upon kin.  Given that the genomes were themselves software abstractions, the question is whether fudging that recognition to something like a simple value of "how closely related to me is this bot over there", fundamentally affects the outcome?  In this case I don't think it does - animals appear to be able to recognise and differentiate between members of their families and community, and strangers - so it isn't a magic or unrealistic faculty to turn into an abstraction.  Recognition is also an interesting area to simulate, but it doesn't look to be directly relevant to the experiment.

The criticism Kai raised is more interesting - the robots are being selected not on some real-world robot-wars style fitness criteria, but on an abstracted "how many points can it score".  Is it legitimate to use points to abstract a more complex activity which has a direct impact on fitness?  E.g. a sentry meerkat who barks out a warning to the group -- individual fitness would be better served in the short term by using the time to escape, rather than warn others.
Title: Re: Altruistic robots produced through evolution
Post by: Triple Zero on February 08, 2010, 10:09:54 PM
in my daydream ideas about evolutionary programming, if I want individuals to be able to distinguish genetically related others from those that are further genetically removed, I always feel that giving them a special sensory input for "genetic similarity of target organism" is kind of like cheating.

My idea would be to give them a set of LFO's in a bunch of genetically determined frequencies. The sensory input would not determine genetic similarity, but the correlation of an organism's set of LFO's with the target organism. This also gives non-related strains the option of "faking" the similarity, kind of like mimicry, and it gives organisms the option of genetically controlling their similarity [as they don't have to change their LFO frequencies if they evolve a couple of generations away from the main species, but they might find it beneficial do to so, or maybe the main species finds this]

It doesn't have to be LFO's either, it can just be a sequence of numbers, but in my idea the oscillators can also be used to control certain bodily functions, so they are not just flags.
Title: Re: Altruistic robots produced through evolution
Post by: Rococo Modem Basilisk on February 08, 2010, 10:16:02 PM
Noisy robot mating rituals FTW
Title: Re: Altruistic robots produced through evolution
Post by: Sir Bearington on July 27, 2012, 04:31:15 PM
This was a news article from 2010...

Why the heck haven't we heard from anything similar since?