Slashdot Mirror

← Back to Stories (view on slashdot.org)

Neural Networks-Equipped Robots Evolve the Ability To Deceive

Posted by timothy on from the I-never-blinked-that dept.

pdragon04 writes "Researchers at the Ecole Polytechnique Fédérale de Lausanne in Switzerland have found that robots equipped with artificial neural networks and programmed to find 'food' eventually learned to conceal their visual signals from other robots to keep the food for themselves. The results are detailed in a PNAS study published today."

22 of 116 comments (clear)

  1. Mhm by alexborges · · Score: 5, Funny

    I mean, yesterday, they built an certified evil robot. Today they made a lying one....

    Cant tag it for some reason but... what could possibly go wrong?

    --
    NO SIG
    1. Re:Mhm by netruner · · Score: 5, Funny

      Wasn't there also a story a while back about robots fueled by biomass? This was twisted to mean "human eating" and we all laughed.

      Combine that with what you said and we could have a certified evil, lying and flesh eating robot - What could possibly go wrong indeed.....

      --



      DISCLAIMER: This post was not checked for speling and grammar- if you complain- you're a whiner
  2. Define deception? by Rival · · Score: 4, Interesting

    This is quite interesting, but I wonder how the team defines deception?

    It seems likely to me that the robots merely determined that increased access to food resulted from suppression of signals. To deceive, there must be some contradiction involved where a drive for food competes with a drive to signal discovery of food.

    1. Re:Define deception? by fuzzyfuzzyfungus · · Score: 3, Insightful

      The question of what exactly constitutes deception is a fun philosophical problem but; in the context of studying animal signaling, it is generally most convenient to work with a simpler definition(in particular, trying to determine whether an animal that doesn't speak has beliefs about the world is a pile of not fun). I'd assume that the robot researchers are doing the same thing.

      In that context, you essentially ignore questions of motivation, belief, and so on, and just look at the way the signal is used.

    2. Re:Define deception? by odin84gk · · Score: 5, Informative
      Old news. http://discovermagazine.com/2008/jan/robots-evolve-and-learn-how-to-lie

      These robots would signal other robots that poison was food, would watch the other robots come and die, then move away.

    3. Re:Define deception? by capologist · · Score: 4, Insightful

      Yes, but not flashing the light near food seems like a simple matter of discretion, not deception.

      I'm not constantly broadcasting my location on Twitter like some people do. Am I being deceptive?

    4. Re:Define deception? by fuzzyfuzzyfungus · · Score: 4, Informative

      In the specific, limited, not-all-that-similar-to-ordinary-english-usage, sense of "deception" I suspect that they are using, there really isn't much of a difference.

      If a species has a discernable signalling pattern of some sort(whether it be vervet monkey alarm calls[with different calls for different predator classes, incidentally], firefly flash-pattern mating signals[amusing, females of some species will imitate the flash signals of other species, then eat the males who show up, classic deceptive signal] or, in this case, robots flashing about food), adaptive deviations from that pattern that serve to carry false information can be considered "deceptive". It doesn't have to be conscious, or even under an organism's control. Insects that have coloration very similar to members of a poisonous species are engaged in deceptive signalling, though they obviously don't know it.

      Humans are more complicated; because culturally specified signals are so numerous and varied. If twittering your activities were a normal pattern within your context, and you started not twittering visits to certain locations, you would arguably be engaged in "deceptive signaling" If twittering were not a normal pattern, not twittering wouldn't be deceptive.

  3. The next step is clearly... by billlava · · Score: 5, Funny

    A robot that learned not to flash lights that would give away the location of robot food to its competitors? The next step is clearly a robot that learns not to flash lights when it is about to wipe out humanity and take control of the world!

    I for one welcome our intelligent light-eating bubble robot overlords.

    1. Re:The next step is clearly... by julesh · · Score: 4, Funny

      The next step is clearly a robot that learns not to flash lights when it is about to wipe out humanity and take control of the world!

      It's something that hollywood robots have never learned.

      Next thing you'll be saying that terrorists have learned that having a digital readout of the time left before their bombs detonate can work against them...

  4. Mis-Leading by ashtophoenix · · Score: 3, Insightful

    To use the term "learned" for a consequence of evolution to what seems to me to be a Genetic Algorithm seems mis-leading. So the generation that emitted less of the blue light (hence giving less visual cues) was able to score higher, and hence the genetic algorithm favored that generation (that is what GAs do). Isn't this to be expected?

    --
    Life is about being a Phoenix!
    1. Re:Mis-Leading by Chris+Burke · · Score: 3, Interesting

      To use the term "learned" for a consequence of evolution to what seems to me to be a Genetic Algorithm seems mis-leading.

      "Learned" is a perfectly good description for altering a neural network to have the "learned" behavior regardless of the method. GA-guided-Neural-Networks means you're going to be using terminology from both areas, but that's just one method of training a network and isn't fundamentally different from the many other methods that are all called "learning". But you wouldn't say about those other methods that they "evolved", while about GA-NN you could say both.

      Isn't this to be expected?

      It's expected that the GA will find good solutions. Part of what makes them so cool is that the exact nature of that solution isn't always expected. Who was to say whether the machines would learn to turn off the light near food, or to turn on the light when they know they're not near food to lead other robots on a wild goose chase? Or any other local maximum.

      --

      The enemies of Democracy are
    2. Re:Mis-Leading by ashtophoenix · · Score: 5, Funny

      who's to say we aren't all very evolved GA's ?

      The Creationists!

      --
      Life is about being a Phoenix!
  5. Deception is not always evil. by vertinox · · Score: 4, Insightful

    In this instance they were playing against other robots for "food".

    In that regards I'm sure that is the evolutionary drive for most species in acquiring meals and keeping the next animal from taking it away from him.

    Like a dog burying a bone... He's not doing it to be evil. Its just instinctive to keep his find from other animals because it helped his species survive in the past.

    --
    "I am the king of the Romans, and am superior to rules of grammar!"
    -Sigismund, Holy Roman Emperor (1368-1437)
    1. Re:Deception is not always evil. by Flea+of+Pain · · Score: 3, Funny

      Like a dog burying a bone... He's not doing it to be evil.

      Unless he has shifty eyes...then you KNOW he's evil.

      --
      Do not argue with an idiot. He will drag you down to his level and beat you with experience.
    2. Re:Deception is not always evil. by alexborges · · Score: 3, Insightful

      Intent is of no importance.

      Evil deeds are evil.

      --
      NO SIG
  6. Not really that impressive. by lalena · · Score: 5, Interesting

    From the article, staying close to food earned the robot points. I think a better experiment would be a food collection algorithm. Pick up a piece of food from a pile of food and then return that food to the nest. Other robots could hang out at your nest and follow you back to the pile of food or see you going to your nest with food and assume that the food pile can be found by going in the exact opposite direction. Deception would involve not taking a direct route back to the food, walking backwards to confuse other robots...
    I've done Genetic Programming experiments using collaboration between "robots" in food collection experiments, and it is a very interesting field. You can see some experiments here: http://www.lalena.com/ai/ant/ You can also run the program if you can run .NET 2.0 through your browser..

  7. Soon they will realize by gubers33 · · Score: 3, Funny

    That if they kill the humans they will have nothing stopping them from getting more food.

    --
    Just because you are wrong and I called you out on it doesn't mean I am a Troll.
  8. decepticon by FooAtWFU · · Score: 4, Funny

    They have a light, which at first flickers randomly; they learn to turn the light off so that other robots can't tell where they are. To my mind that's not really sophisticated enough to qualify as "deceptive".

    Yeah. It's more like the robots are hiding from each other. You could, in fact, describe them as "robots in disguise".

    --
    The World Wide Web is dying. Soon, we shall have only the Internet.
  9. Re:Hardly deceptive by CorporateSuit · · Score: 4, Informative

    From just reading the summary, I guessed that the light went on when the robot found food, and that other robots would move towards those lights, because they indicate food, and that some robots evolved to not turn on the light when they found food, so they didn't attract other robots, so they had it all to themselves, which would be an advantage.

    The summary didn't include enough information to describe what was going on. The lights flashed randomly. The robots would stay put when they had found food, and so if there were lights flashing in one spot for long enough, the other robots would realize the first robots had found something and go to the area and bump away the original robot. The robots were eventually bred to flash less often when on their food, and then not flash at all. By the end, robots would see the flashing as a place "not to go for food" because by that point, none of the robots would flash when parked on the food.

    --
    I am the richest astronaut ever to win the superbowl.
  10. Re:The robots didn't learn... by jasonlfunk · · Score: 5, Interesting
    (Fixed formatting)

    FTA: The team "evolved" new generations of robots by copying and combining the artificial neural networksof the most successful robots. The scientists also added a few random changes to their code to mimic biological mutations.

    The "scientists" changed the code so that the robots didn't blink the light as much when it was around food. Therefore other robots didn't come over and therefore got more points then the other robots. The "scientists" then propagated that ones code to the other robots because it won. The AI didn't learn anything.

  11. Re:HAL runs for Congress by jd2112 · · Score: 3, Funny

    Nonsense, How can a computer have an extramarital affair.

    --
    Any insufficiently advanced magic is indistinguishable from technology.
  12. No, they did "learn" by Chris+Burke · · Score: 4, Informative

    The "scientists" changed the code so that the robots didn't blink the light as much when it was around food.

    No, they didn't change the code. The Genetic Algorithm they were using changed the code for them. You make it sound like they deliberately made that change to get the behavior they wanted. But they didn't. They just let the GA run and it created the new behavior.

    The part about adding random changes, and combining parts of successful robots, is also simply a standard part of Genetic algorithms, and is in fact random and not specifically selected for by the scientists. The scientists would have chosen from a number of mutation/recombination algorithms, but that's the extent of it.

    The "scientists" then propagated that ones code to the other robots because it won.

    Yes, because that's what you do in a Genetic Algorithm. You take the "best" solutions from one generation, and "propagate" them to the next, in a simulation of actual evolution and "survival of the fittest".

    The AI didn't learn anything.

    Yes, it did. Genetic Algorithms used to train Neural Networks is a perfectly valid (and successful) form of Machine Learning.

    If you mean that an individual instance of the AI didn't re-organize itself to have the new behavior in the middle of a trial run, then no, that didn't happen. On the other hand, many organisms don't change behaviors within a single generation, and it is only over the course of many generations that they "learn" new behaviors for finding food. Which is exactly what happened here.

    With the domain of robots, AI, Neural Networks, and Genetic Algorithms, this was learning.

    --

    The enemies of Democracy are