Please create an account to participate in the Slashdot moderation system

 



Forgot your password?
typodupeerror
×
AI IBM Games Technology

IBM Researchers Teach Pac-Man To Do No Harm (fastcompany.com) 135

harrymcc writes: The better AI gets at teaching itself to perform tasks in ways beyond the skills of mere humans, the more likely it is that it may unwittingly behave in ways a human would consider unethical. To explore ways to prevent this from happening, IBM researchers taught AI to play Pac-Man without ever gobbling up the ghosts. And it did so without ever explicitly telling the software that this was the goal. Over at Fast Company, I wrote about this project and what IBM learned from conducting it.

The researchers built a piece of software that could balance the AI's ratio of self-devised, aggressive game play to human-influenced ghost avoidance, and tried different settings to see how they affected its overall approach to the game. By doing so, they found a tipping point -- the setting at which Pac-Man went from seriously chowing down on ghosts to largely avoiding them.

This discussion has been archived. No new comments can be posted.

IBM Researchers Teach Pac-Man To Do No Harm

Comments Filter:
  • Or is this supposed to impress us in some way?
  • by ruddk ( 5153113 ) on Thursday October 25, 2018 @11:16AM (#57535621)

    I don't think so. :*)

    • by Anonymous Coward

      Our digital ghosts are just too yummy.

  • I read the article, a lot of words for so little information.

    It's also pretty easy to avoid the ghosts when then are trying to avoid the player.

  • IBM researchers taught AI to play Pac-Man without ever gobbling up the ghosts.

    ... ghosts are yummy!

    Wocka, wocka, wocka ... nom, nom, nom.

  • by alvinrod ( 889928 ) on Thursday October 25, 2018 @11:21AM (#57535641)
    This is interesting, but I'm not sure how useful it is. You might be able to create an AI that has some desirable characteristics based on human morality, but as soon as you make it compete against other AIs that don't possess those characteristics, it will either adapt to possess them itself in order to remain competitive or it will perish if it's been crippled in a way to prevent it from adjusting. A pacifistic Pac-Man AI might be novel, but if it was made to compete, it wouldn't do as well.
    • but as soon as you make it compete against other AIs that don't possess those characteristics, it will either adapt to possess them itself in order to remain competitive or it will perish

      Only if you program competition as a desirable goal. It might not be. You might program them to prefer cooperation to competition. Why would you make "dog-eat-dog" a trait, when AIs don't need to eat? Why take a nature-based paradigm and impose it on a system that has no need for it?

      Why should AIs compete at all, is the

      • by mi ( 197448 )

        Why would you make "dog-eat-dog" a trait, when AIs don't need to eat?

        ICBMs don't need to eat either... Putin needs to eat. Guess, how he'll program his AI?

        Why should AIs compete at all, is the question.

        Because some of the tasks we may wish to entrust them will have adversarial aspects. If AI is charged with picking out wanted criminals from the crowd, it will need to weight severely harming the criminal — by having him arrested — vs. harming the rest of us a little bit — by letting him sli

        • Gosh, I hope the end state for AI isn't something as mundane as law enforcement or military applications. That would show a real lack of imagination on the part of human beings.

          • by mi ( 197448 )

            I hope the end state for AI isn't something as mundane as law enforcement or military applications

            End state? Certainly not — if there is an "end" at all. But they'll certainly be used for that — indeed, already are used for that [slashdot.org].

            And adversity is not going anywhere, unfortunately — with competing entities (corporations, nations, criminal enterprises, terrorist groups) using AI to their own ends. Just as you can not raise a child unprepared for adversity, you can not develop an AI unprepare

            • you can not develop an AI unprepared to compete

              Sure you can. Use your imagination. Don't be so bloody-minded to think that competition is a necessary state for all systems.

              • by mi ( 197448 )

                Don't be so bloody-minded to think that competition is a necessary state for all systems

                Unlike a teddy bear or a saucer, AI is as multipurpose as a mind... Indeed, it is — or ought to be — a mind. To be useful in a real world, it has to know about all aspects of it, even if the degree of knowledge can differ between domains.

                Now, maybe, you can train a limited one — aimed at solving a particular task. But that really is no different from rearing a child teaching him only one thing (dancing,

                • Indeed, it is — or ought to be — a mind. To be useful in a real world, it has to know about all aspects of it, even if the degree of knowledge can differ between domains.

                  You're still thinking like an engineer, anthropomorphizing the AI. Do you think for a robot to be useful it has to be bipedal and have the approximate shape and function of a human? The point of an AI is to exceed humanity, not imitate it.

                  Don't make the mistake of thinking an AI has to operate like a human mind. Stretch your

        • severely harming the criminal -- by having him arrested

          What? Just being arrested is being severely harmed? No. At best they GOTCHA or at worst it's a waste of everyone's time. But we want to make absolutely sure the bad guys never get away, right?

          More like:
          if Is_This_A_Person() then Report(Yes);
          else Report(No);

          Of course bringing asset forfeiture into the picture:
          if Is_This_A_Person() then Report(Yes);
          if Is_This_An_Object() then Report(Yes);
          else Report(No);

          Or for the latter, a much simpler:
          Report(Yes);

          BF would NOT be happy with this. That it [bartleby.com]

          • What? Just being arrested is being severely harmed?

            You're not from the US, are you? Here just being arrested can quite literally ruin your life.

            Arrests get airtime and newspaper articles, refusals to prosecute or being found innocent does not. So that means any future employer who does a cursory search on you finds out that you got arrested for something. They won't find out that it was a misunderstand, mistaken identity, or due to a corrupt cop. Have you seen any of the mugshot websites where they post all of them? Do you think they follow up on what happe

          • by mi ( 197448 )

            Just being arrested is being severely harmed?

            Anyone deliberately evading arrest does not want to be arrested. An arrest would be viewed as very harmful by the individual — even if it gives him a chance of redemption, paying debts to society, etc. An AI seeking to avoid harming anyone would be useless — like humans, it has to balance the different harms.

            I fear for the day we're 100% efficient, since NO ONE'S innocent of everything.

            I, actually, long for that efficiency — because then we'll b

      • but as soon as you make it compete against other AIs that don't possess those characteristics, it will either adapt to possess them itself in order to remain competitive or it will perish

        Only if you program competition as a desirable goal. It might not be. You might program them to prefer cooperation to competition. Why would you make "dog-eat-dog" a trait, when AIs don't need to eat? Why take a nature-based paradigm and impose it on a system that has no need for it?

        Why should AIs compete at all, is the question.

        Particularly when AI, if it ever becomes a true AI instead of a basic machine learning algorithm, will evolve in a time where it seems like we have plenty of resources to go around if we can figure out how to actually share them (at least for human needs). Whereas humans evolved in a time when sharing often meant you starve during the winter. Might give them a bit different perspective, if global warming or some other catastrophe doesn't mess everything up along the way.

        • Early humans couldn't share because they would starve during the winter? That sounds highly illogical. Sure, there are limits, but why would we need a society if we didn't benefit from other members?

          I don't think this has ever been different for humans. We are stronger together. United we stand, divided we fall. We pool our resources to produce even more than we can alone. A being who spends his/her time hunting and gathering to survive has little time to spend researching advanced machinery to increase p
          • Some dogs are quite spoiled by their owners.

            When my most recent dog died, I realized just how spoiled we are by our dogs.

      • If you can get everyone to make AIs that don't value competition you might have a point, but now there's a whole lot of incentive for one person to make a hyper-competitive AI, because it's going to stomp the crap out of the ones that don't know any better. You're either missing the prisoner's dilemma aspect of this, or just wishing that it didn't exist.

        The simple fact is that an AI which will utilize strategies which are more successful in the real world is going to do better than anything that refuses
        • Competition just happens to be a really good strategy.

          So is cooperation. You are anthropomorphizing all systems, and that is a losing strategy.

  • by kiehlster ( 844523 ) on Thursday October 25, 2018 @11:22AM (#57535643) Homepage
    When the AI begins watching humans play Pac-Man, doing harm to the ghosts, it will consider humans a threat to ghosts and thus eliminate the humans to satisfy its directives. Is IBM's median employee age too young to have seen Robocop?
    • Is it doing harm to the ghosts? They don't suffer any ill effects from being eaten. A bit like being turned into a newt, they get better. Plus, they get better a lot quicker than if they are left alone. I've been killed plenty of times by a regenerated just eaten ghost while in pursuit of still edible ones.

      True "do no harm'" wouldn't allow the ghosts to become edible in the first place, making eating power pills verboten. That reduces the score further but as they aren't training for success that doesn't ma

  • GHOSTBUSTERS!

  • ..all day long for weeks and weeks.
    That's what the title should be.
  • by Daetrin ( 576516 ) on Thursday October 25, 2018 @11:38AM (#57535715)
    Title: "IBM Researchers Teach Pac-Man To Do No Harm"

    Blurb: "they found a tipping point -- the setting at which Pac-Man went from seriously chowing down on ghosts to largely avoiding them."

    So companies will presumably use a similar method to design AIs that will maximize corporate profit with only a _small_ amount of acceptable human murdering in the process?
  • Did they also have Pac-Man stop to ask why the ghosts hated him?
  • Wouldn't avoiding eating ghosts mean it just never got smart enough to know that you could eat power pills and then pass through them? That new optimal paths would arise when the power pill was active? If their algorithm added score for lower time or for points, I think this behavior would change.

    "IBM Researchers Teach Pac-Man to Avoid Ghosts Even When It Is Advantageous To Eat Them" might not have the same ring to it.

  • by hey! ( 33014 ) on Thursday October 25, 2018 @12:01PM (#57535857) Homepage Journal

    It's having an algorithm grind out a solution to playing the game which meets an additional constraints, which they tweak.

    If they'd actually taught the AI ethics, the AI would construct the play constraints for itself starting from ethical principles. At full human levels of ethical self awareness, the AI would be chasing ghosts down the hall and then -- unprompted -- stop and ask itself, "What am I doing?"

  • The definition of AI is getting seriously skewed by the media. This has nothing to do with AI. I could've programmed this and I have no AI programming training whatsoever.
  • I don't think so. They taught it by eliminating runs from the "success" pool when it ate a ghost.
  • It would be interesting to know the difference in scores and completion times between the two game strategies. What is the advantage of being 'ethical'?
  • tic tac toe number of players zero

  • can it play global thermonuclear war?

  • It's right there in the article, “There’s lots of rules that you might not think of until you see it happen the way you don’t want it,”

    Well, if you told a computer to do EXACTLY the thing, and it's possible, they'll do EXACTLY the thing. If you said one thing, but meant another, they're not going to do what you mean, they'll do what you told them. So if your success metric is high score, and eating ghosts increases that, they'll eat ghosts.

    In fact, this is how it works with people

  • What about Ms. Pac-Man?

  • to Do No Evil.

    Ba-dum-tish.

Ocean: A body of water occupying about two-thirds of a world made for man -- who has no gills. -- Ambrose Bierce

Working...