Slashdot Mirror
Artificial Life Forms Evolve Basic Memory, Strategy
Calopteryx notes a New Scientist piece on how digital organisms in a computer world called Avida replicate, mutate, and have evolved a rudimentary form of memory. Another example of evolution in a simulation lab is provided by reader Csiko: "An evolutionary algorithm was used to derive a control strategy for simulated robot soccer players. The results are interesting — after a few hundred generations, the robots learn to defend, pass, and score — amazing considering that there was no trainer in the system; the self-organizing differentiated behavior of the players emerged solely out of the evolutionary process."
I, for one, welcome our new artificial, man made overlords
Needs a Skynet tag!
We all know, God did this, and evolution is fake. This proves it!
Wow look at that teamwork.. maybe those guys could represent England?
If God were real and just, all of the people who deny evolutionary theory would die of polio. Without evolution we wouldn't have the vaccine.
"amazing considering that there was no trainer in the system;"
Not really, it's merely selecting patterns it is not aware of if it's patterns are "successful" or not. If you run a pattern generator long enough you can get all possible patterns within a finite possibility space.
The study also found that the artificial fans of the losing team started to riot on their own.
Finally some news out of my school that isn't sports-, riot-, or rioting-about-sports related.
When you program some evolutionary theory in your digital world and your digital world is developing some evolutionary lifeform that is news?
A bit more than 15 years ago I saw a documentary on Discovery Channel featuring identical work being made by a brittish scientist / computer programmer. His software spawned simple "lifeforms" made up by basic 2D and 3D geometrical objects - cubes, cylinders, flat triangles etc., - that were then trying to evolve methods of how to most efficiently move and travel in the simulated environment they were put in - sometimes an airy environment with ground underneath them, and gravity, and sometimes an "ocean" in which the "lifeforms" swam. Minute after minute the "lifeforms" jiggered and bounced around like broken machinery, but slowly developing a method for moving and navigating that was the most efficient for their particular shape. He spawned caterpillar-like animals made up from chains of cubes, that slowly learned how to wriggle and crawl just like catterpillars and snakes do. He spawned randomized "freaks" that learned that sometimes managed to learn how to walk with their disfiguring, and sometimes learning that the only way was to throw some bodypart around to pull themselves forward. He spawned biped animals that slowly learned how to jump to move forward, an triped animals that learned how to skip from one leg to the other, to the third. He spawned lifeforms in a watery environment that learned how to rhythmically oscillate their bodyparts to create propulsion in order to swim forward and turn around. To me, this was just as impressive, if not more, than the featured story. As a curious detail to it all, the programmer developed his software in BlitzBasic, running on a heavily accelerated Amiga 1200.
We've been applying genetic algorithms with ANNs for quite a while now, quite often also making groups of them cooperate. yawn?
Experiments and other stuff
In the late 1980s, ecologist Thomas Ray, who is now at the University of Oklahoma in Norman, got wind of Core Wars and saw its potential for studying evolution. He built Tierra, a computerised world populated by self-replicating programs that could make errors as they reproduced.
When the cloned programs filled the memory space available to them, they began overwriting existing copies. Then things changed. The original program was 80 lines long, but after some time Ray saw a 79-line program appear, then a 78-line one. Gradually, to fit more copies in, the programs trimmed their own code, one line at a time. Then one emerged that was 45 lines long. It had eliminated its copy instruction, and replaced it with a shorter piece of code that allowed it to hijack the copying code of a longer program. Digital evolvers had arrived, and a virus was born.
Avida is Tierra's rightful successor. Its environment can be made far more complex, it allows for more flexibility and more analysis, and - crucially - its organisms can't use each other's code. That makes them more life-like than the inhabitants of Tierra.
Actually, organisms using each others code sounds way more like our world than ones that can't leech off each other. They already pointed out viruses, and plenty of species exist today that need other species to continue to survive.. in fact pretty much all animals need to eat other lifeforms because we can't draw energy from the sun directly.
which is totally what she said
The robots need to become spoiled, overpaid millionaires, who refuse to train (France). Brag a lot (England) that their opponent is a bunch of "boys" (Germany), who are afraid of them. Then take a 4-1 shellacking from the "boys." And despite being the defending champions, and having a world class league in their country, bow out early. Because all of the players in their first class league are from South America (Italy), and the they have no good domestic players.
Robots with vuvuzelas? No, thanks. My next nightmare.
Schroedinger's Brexit: The UK is both in and out of the EU at the same time!
Eh, they can play soccer, not too impressive. Check back when they evolve their own religion, that would be impressive.
"Science flies us to the moon. Religion flies us into buildings." - Victor Stenger
the self-organizing differentiated behavior of the players emerged solely out of the evolutionary process.
This is the problem with AI research. The notion that we can bootstrap life by mimicking evolution is crazy. Computers are getting faster, but billions of years multiplied by billions of neurons per organism they can't do" Nobody gives a shit what their sex robot "emerged solely out of," they just want to fuck it.
I'm always confused if these discoveries are supposed to show that we'll someday have sentient robots that will rule the world a la every sci-fi for the past decade or if they are trying to model biological evolution in a meaningful way. Personally, I hope the sentient robot thing is NP-complete. :P
For modeling biological evolution, any in silico organism model needs to incorporate the fact that most mutations are "nearly neutral" (some might say slightly deleterious) with respect to the scoring algorithm (selection) while the next largest group is deleterious, and only a small fraction are beneficial. Not every "bit" (base) in a genome has the same value, and certainly that value is related to its context. In the genome mutation can strike anywhere although some places may be lethal so it will never be expressed in a breeding organism. In AI there may be restrictions on the parameters that can change, but in the genome mutations can produce some pretty nasty defects. It's actually the relative badness of those defects which gives selection the power to weed out unfit individuals before the defect can become fixed. However, in biological evolution, defects can and do become fixed, either being linked with good traits or because there isn't sufficient selection power to get rid of them. Thus, after many many generations of "optimizing" the robots should also manifest situations where they do "stupid" things routinely because the "good" things they do are "linked" to the bad things they do on the coding level.
I would tag this as "Intelligent Design".
This is a very simple demonstration that something can evolve from simple beginnings, if the creator was intelligent enough.
A not-so-intelligent designer, OTOH, would probably prefer to create its beings in their final state because it takes more effort to create a system capable of evolution.
I was so amazed by the results claimed for Tierra that I went and reimplemented it myself. And damned if I didn't get similar results. At the time, it blew me away that such a system could come up with novel solutions I hadn't expected or 'programmed in'. Indeed, a couple times it took me a while to even figure out how the things worked.
PHEM - party like it's 1997-2003!
will there be video replay then?
I just read this article and found it quite interesting.
I do have a few ideas about how I would face the design of a system like that. However, I am not used to design such systems, and I would like to go deeper in the subject.
Can anyone recommend some good books/papers about it ?
Thanks a lot.
Speaking of evolutionary behavior in a simulation/game environment...
I liked NERO a lot. The original idea was to have the bots run a capture the flag type game. However I found training mode more fun and interesting by making mazes in the map editor and seeing how AI behavior developed. "Training" my bots to run a maze was a simple yet timely processes of adjusting the reward value sliders for certain behaviors and manually smiting the bots that would get stuck or cling to the walls too much. Usually what would happen once they started getting good at running mazes quickly while showing more interesting behavior than running in circles was that the computer would crash and the last saved "DNA" neural algorithm file would swell from under a megabyte to well over a gig.
Unfortunately nobody has done jack shit in regards to further development since 2007. (At least anything apparent on the public side.) Seems a shame, since it was good up to a point. There should be potential to do more with it. I guess either computers aren't powerful enough to handle the simulation past a certain level or that things just get too complicated on their own which would make debugging nearly impossible.
I figure the NERO bots could also be made to play soccer too, provided there was the right LUA script written. (It used the Torque game engine.) But being that the simulation brickwalls at some point by simply doing maze runs, that seems unlikely at this point.
.... uh, hmmm..... what was I on about?
old news
http://www.robocup.org/
- has been going for a very long time, and often involves more sophisticated physical robots.
Also, as many people have pointed out, this is not really all that original. One of the oldest Genetic Programming's PhDs (in 1980) evolved card players. Tierra pre-dates this stuff. Nothing surprising has emerged here, but I guess it is a nice popular science article for those not familiar with the field.
As others have pointed out, Roger Alsing's Mona Lisa is very cool, as is the work that went into evolving an aerial design for NASA:
http://ti.arc.nasa.gov/projects/esg/research/antenna.htm ... there are over 6000 papers published on Genetic Programming and a huge chunk of them are applications like this. EC techniques like this are just heuristic search algorithms for program spaces.
RS.
give this enough time and the world willl be ending in awhile prepare to nuclear war launched by our computers Judgment day will arrive if they keep this up stock up for war its coming
Not a troll asshole
www.Migrainesoft.com - Computer giving you a headache? We can fix that!
Just think 100 more generations or so they'll be smart enough to code for Microsoft!!!
I think that was mangu's entire point.
As I read it, mangu is saying that any rational, logical take on an intelligent design theory of the universe would likely conclude that any design involved the stipulation and balancing of the underlying rules by which this universe functions, as a very elegantly balanced system that is then allowed to operate independently from the point of the Big Bang (or perhaps earlier if we posit a yo-yo universe), rather than as a hamfisted make-everything-manually, brute-force approach that is not allowed (or perhaps able) to operate independently for even 6,000-odd years.
Anyone who's spent much time coding will no doubt appreciate the idea of a perfectly designed, bug-free system arising from a few lines of simple code that runs forever without the slightest glitch, much more than the image of a bloated behemoth that explicitly instantiates every type of object and codes for every conceivable corner case, and still needs lots of manual bug-fixing while running.
I'm not much of one for religion myself, but if God is supposed to be omniscient and omnipotent, an elegant, ultimately simple, and perfectly balanced universe is much more beautiful and compelling to me. A lot of fundamentalist insistence on things like "God made fossils to test our faith" just sounds far too clumsy for a deity that is supposed to be perfect. Anyway, that's my 2p.
Cheers,
"What in the name of Fats Waller is that?"
"A four-foot prune."