Forgot your password?
typodupeerror
Games Entertainment

Keep Playing With AI 175

Posted by Hemos
from the learning-from-you dept.
An anonymous reader writes "The BBC reports how a newly developed AI system 'learns' your playing behavior and can even play for you when its time to take out the garbage or do other non-essential things around the house. My only question is if it could even learn to bs for me on those laggy starcraft 3v3 games."
This discussion has been archived. No new comments can be posted.

Keep Playing With AI

Comments Filter:
  • Thank you but. . (Score:1, Flamebait)

    by alnapp (321260)
    I've already got friends to play with

    Al
  • Great... I think I'd rather have an AI that plays better than me than one that can find previously unheard of ways to meet its demise like I can.
  • Something like this? [penny-arcade.com]
  • by Ratface (21117) on Wednesday September 04, 2002 @10:51AM (#4195074) Homepage Journal
    I would prefer that the AI took out the garbage so that *I* can continue playing my game ;-)

    Besides which, who wants to give up their game for "someone" else to play. I mean it would be bad enough coming back from running an errand and finding that your sibling/gf/friend has died and put you back to the start let alone your friend. Or even that they've managed to get you past the point you've been banging your head against for ages so that now you feel cheated at not having achieved the goal yourself.

    Nope, I think the "pause" button is not going to be replaced by an AI any time soon.

    • I think the application is for online games where pausing is either rude, impossible, or the other team can simply unpause for you (the case in the craft games).

      I think this is a great idea. It's not made to play the entire game, just to hold out long enough for the chore/phonecall/whatever to be finished such that you haven't falled AS far behind.

      Sure it wont be as good as us. And if the opponent finds out your on the phone, a feign to your ally followed by a strong attack to you will probably work every time (not that that ever fails against humans). But if they don't know, and don't try to exploit it, it'll be fine. In any case you'll be better off then nothing.
    • I hear you, but I think it might be better the other way around.

      I've noticed that some games, which require *constant* attention...like TFC or DoD...where there is really no rest time at all...end up giving me a bad case of neck-strain, eye-strain, and back-strain.

      But, when I play games like counter-strike...or even EQ...there are usually regular opportunities to get up for 30secs or so and stretch...get a drink if water, take a bio break, put the pop-tart in the toaster...whatever it is. I find that when I play games this way, I can play them for 10 hours at a stretch...but the "other" kinds of games that require constant attention really bust my body up bad. Probably why I don't play them as much anymore.
    • I would want it to do the taunts for me.

      nothing like have somebody (the computer, in this case) talk smack to your opponents when your hands can still be occupied kicking his / her ass.

      speaking of which... AI to find "my style of pr0n" while hands are occupied with other stuff might be useful too. hmmmmm...
    • If you have a game spanning more then a few players, a pause button isnt really an option.

      The point here is, its an online real time game.

      If everyone else is still playing, then having an AI run for you while your busy is much better then just leaving your side sitting around waiting.

      And in theory it wont be able to figure out things you haven't done yourself. Since it learns from you. To keep a game balanced the AI shouldn't be better then you are or you end up with Munchkins sitting back and watching the AI play.
  • by jsonmez (544764) on Wednesday September 04, 2002 @10:51AM (#4195075)
    Then I want it to play the best strategy, not do the same stupid stuff I do wrong...
    • That's the whole point. It's simulating your presence with the assumption that if you were there that you would make the same mistakes (stupid or otherwise) that you would normally make.

      If you just want to face off the AIs, that's a whole 'nuther story.
  • What is this world coming to if we have a COMPUTER to play our COMPUTER GAMES. I thought these things were for fun, and that people enjoyed playing games THEMSELVES! What was I thinking?
    • by Anonymous Coward
      Yes... yes it does... because if we add AI to the mix we can remove the driving control from vehicles and keep the braindead morons that populate and clog and smear themselves all over the highways from trying to use the feeble mind of theirs to control that vehicle in a safe manner... something that is 100% impossible for 90% of the world population.

      the end result is cars that YOU CANNOT EVER STEER OR CONTROL YOURSELF! and that would be a wonderful thing.

      until the collective IQ of the planet rises above 80.... we desperately need everything automated.
      • "if we add AI to the mix we can remove the driving control from vehicles and keep the braindead morons that populate and clog and smear themselves all over the highways from trying to use the feeble mind of theirs to control that vehicle in a safe manner"

        Except that this system is supposed to imitate the behavior of the people whose efforts it's supposed to take over. Meaning that we'd have even MORE crashes, because the computers would "learn" that crashes are the right way to drive and then auger into a cement wall on EVERY TRIP.

        Of course, careful marketing would downplay this type of problem.
    • What is this world coming to if we have a COMPUTER to play our COMPUTER GAMES. I thought these things were for fun, and that people enjoyed playing games THEMSELVES! What was I thinking?

      Ever play UO? It's THRILLING to sit for hours and practice magic, or hiding.

      I had a little metal ball that sat on my Macro Key - so I didn't have to sit for hours before I could go out in the woods and be PK'd.

  • AI taking over my game? I prefer a pause command (in desktop games) or 'logout' command (in multiplayer games).
  • I've heard/seen of macroing in MMORPG's for years now. People macroed when MUD's were the "first" MMORPG's, then in Ultima Online, and then EQ, etc.
    • I've heard/seen of macroing in MMORPG's for years now.

      In this system, the AI learns your playing style and writes the macros itself.

      • I'm always suspicious of how "AI"'s (actually not AI, computer player) "learn"ing your play is actually implemented in computer games. In my experience, the computer opponents just run around in circles, launching attacks that consist of merely pushing units toward the player, and only succeeding if the CP's resources outnumber the human's. If they are doing some kind of learning, it's non-obvious to the observer.
  • Oh no... (Score:3, Insightful)

    by FortKnox (169099) on Wednesday September 04, 2002 @10:52AM (#4195086) Homepage Journal
    Imagine all the lonely AI cyber-sex sessions that will happen in this world...

    Seriously, though, there has to be a line drawn here. Sure, it'll be good for parents to get the kids off the machine for dinner, but won't it eventually lead to being an all-AI game? Isn't the point of big games, like MMORPGs to be that the people with no life and play 800 hours a week to have better characters than the casual gamer? With this system, you teach the AI to practice blacksmithing, let it run day and night for a few days, and come back with a master blacksmith. Just seems like you are taking out the challenge of the game...

    For the record, I don't play MMORPGs.
    • Re:Oh no... (Score:3, Insightful)

      by Bingo Foo (179380)
      but won't it eventually lead to being an all-AI game? Isn't the point of big games, like MMORPGs to be that the people with no life and play 800 hours a week to have better characters than the casual gamer? With this system, you teach the AI to practice blacksmithing, let it run day and night for a few days, and come back with a master blacksmith. Just seems like you are taking out the challenge of the game...

      And Bully for them, I say. The more potentially dehumanizing technology there is around, the more we are forced to consider what is quintessentially human. AI that plays your game for you might be a liberating experience, in that it puts you face to face with the conclusion that having no life and playing 800 hours a week is not worth anything after all.

      • So what exactly is worth doing for 800 hours a week if not playing video games?
      • Playing 800 hours a week would be worth something. At the very minimum you could sell the time machine.
        • No, no, there's no time machine. You remember the whole Atari ad campaign about "gaming at the speed of light"? See, when you do that, time slows down, so you can game longer. Get it?

          Virg
          • Actually going faster would mean you could fit less hours into the week. To fit more hours of game time into the rest of the worlds week acelerate the rest of the world, and stay still.
    • Re:Oh no... (Score:2, Funny)

      by DonkeyJimmy (599788)
      After watching someone I know practice fishing for 8 hrs a day, every day, for over 2 months on ultima online, I welcome whatever allows people to seperate themselves from that portion of gaming monotomy. Players will still have to decide weather to fish, cook, blacksmith, or whatever with their characters spare time. At least this way they can go do something productive, like watch TV or do drugs.
    • won't it eventually lead to being an all-AI game?

      That could be kind of cool to watch, see where the AIs take their virtual civilization on a massive scale like that. Much better than watching the computer play chess against itself. Not that I've ever done that.

      SablKnight
    • With this system, you teach the AI to practice blacksmithing, let it run day and night for a few days, and come back with a master blacksmith. Just seems like you are taking out the challenge of the game...

      That's not challenge, that's drudgery. If you don't want AIs like this to invade your games, play games that require more skill and less repeated action.

  • ...when I need to get off my lazy game-playing ass and hit the gym?
  • Dave, (Score:4, Funny)

    by kvn299 (472563) on Wednesday September 04, 2002 @10:54AM (#4195095)
    I don't think you want spend all that gold on that that Palladin shield. Maybe you should relax a bit and think it over.
  • by WetCat (558132)
    Can this system develop programs for me? Or at least
    assist me in small tasks?
  • by Spit_Fire1 (247104) on Wednesday September 04, 2002 @10:55AM (#4195102)
    The company has developed an artificial intelligence system that learns a gamer's style of play and can take over and play for them if they have to spend time away from the game.

    So If i'm not very good at a game the ai wont be either? Even so this could be exploitable and used to be better at a game than a friend, we all remeber zbot from quake2.

    He said many players of online games become frustrated because their lifestyle limited their interaction with a game world.

    but in a stragagy game you can run when nature calls and be mostly ok

    Typically they involve creating lots of slightly different solutions to a problem, testing to see which perform best and then taking and randomly mutating these to produce a new batch that are again tested, mutated and so on.

    They should focus this advanced AI on the computer players of the game not into an autopilot mode.
  • What's the point? (Score:3, Interesting)

    by Mr_Silver (213637) on Wednesday September 04, 2002 @10:57AM (#4195108)
    The company has developed an artificial intelligence system that learns a gamer's style of play and can take over and play for them if they have to spend time away from the game.

    Ok, I'm no hard-core gamer but personally, I can't think of anything worse than AI making guesses about what my strategy is and what I'm planning and thinking of doing.

    So the question is, what's the point? If "real life" intruides on my gaming, I simply hit pause and come back to it later.

    It just seems to me like one of those things that'll make people go "wow!" for the first couple of minutes and then never use again.

    In other words, a bit pointless, especially if you could have been spending that development time doing something more worthwhile (like adding depth to a game, improving other AI, adding extra levels, better documentation etc. etc.)

    • If "real life" intruides on my gaming, I simply hit pause and come back to it later.

      It is a multi-player game. In a turn based game (like the [card] games on yahoo), people going for pees, answering the phone, fetching a drink etc. can be a nuisance, but if they say brb, it at least gives the others a chance to pop away for a sec too. Of course, it could just be lag....

      Now, if everyone is out for themselves in a last-man-standing battle, you need to leave, you accept the chance you might die/lose/whatever.

      But lets imagine a real time strategy in which you are one of three allies (USA, Britain, Russia), fighting a 6 hour battle simulating WWII. Now lets imagine you are the US, and I am Winston Churchill. I've been managing my armies for the last three hours when my partner tells me dinner is ready.

      Am I supposed to:

      1. Tell her to fuck off?
      2. Use my keyboard as a plate?
      3. 'Press pause' and tell the 5 (or 50) other players to wait for me to come back?
      4. Let the computer do what its good at?
      I'm not a hardcore player either; my mouse clogs up etc, and I hate micromanagement. This kind of stuff would work just fine - perhaps 24 hours a day (with me checking in daily for an hour to set budgets, initiate or even approve attack plans, etc.

      That's the point.

      • > But lets imagine a real time strategy in which you are one of three allies (USA, Britain, Russia), fighting a 6 hour battle simulating WWII. Now lets imagine you are the US, and I am Winston Churchill. I've been managing my armies for the last three hours when my partner tells me dinner is ready.
        >
        >Am I supposed to:
        >1.Tell her to fuck off?
        >2.Use my keyboard as a plate?
        >3.'Press pause' and tell the 5 (or 50) other players to wait for me to come back?
        > 4.Let the computer do what its good at?

        1) Instead of "Fuck off", how about "Bring the food in here, serving-wench!"
        2) If you're lucky, you'll get to use your keyboard as a plate. If you're unlucky, your lap will be the plate. And it'll be French Onion Soup.
        3) You'll have to press pause anyway while you yank the keyboard out and run screaming around the room.
        4) So yeah, you'll still need an AI.

        > I'm not a hardcore player either; my mouse clogs up etc, and I hate micromanagement. This kind of stuff would work just fine - perhaps 24 hours a day (with me checking in daily for an hour to set budgets, initiate or even approve attack plans, etc.

        Y'know, I'd like that in a slow-moving RTS like your imaginary WW2 sim. Imagine a [single-player] game that took over your PC and ran a world in the background, 24/7, for a period of weeks/months.

        Churchill was a hero - but even he had to sleep.

    • Oh well, perhaps you won't like the IA on this game, but they can continually improve it until maybe, can replace the player. Even if it doesn't, it's innovation for now, and that we must applaud.

      Now imagine if an AI learns how to play the style of the champions, for example, if the CounterStrike champion of your local LAN center is a camper with a sniper or a machine gun, what crate he likes to hide on that map, etc, etc.. Even playing 50% of this, you could effectivily play against "half" of what the world's best player has to offer.

      For example, bots could also be created for RTS games. Imagine that you suck against fast players with some race on a particular game. You could download enemies with this playing style, and practice against.

      Of course, it won't be the same as the real thing, but for training or for fun, it's a great step.
    • So the question is, what's the point? If "real life" intruides on my gaming, I simply hit pause and come back to it later.

      In the article it specifically states that this is an online real-time strategy game in which the world decays at a rate completely independant of how long you've been playing (in other words, the world decays on the server, not the client). There's no hitting pause, though you could log out of the game, but then the game goes on anyway.

      It just seems to me like one of those things that'll make people go "wow!" for the first couple of minutes and then never use again.


      I'm wondering whether or not this AI is running on the server or the client myself. It would seem ideal that you could just set the thing to go and log off, but that would take some pretty good servers to manage if there will ever be a lot of players. If it's on the client I have to wonder how much players could take advantage of it to 'enhance' the playing style used by the AI.
  • One big problem that is immediatly obvious. If the games fancy genetic algorithm is actually good, you could probably hack the game with a state file made by someone who was really GOOD at the game.

    However, as anyone who's played this type of game before would attest : sometimes you just HAVE to go afk RIGHT NOW or you lose your connection to the server due to technical reasons.

    It would be very nice if the game would take at least basic action to prevent death (such as casting teleportation spells, healing, running away...SOMETHING other than standing there) if you get attacked and you are afk or linkdead.
  • I wonder if you could get the computer to absolutely demolish your opponents with rushes if you simply have it watch you build a few buildings, set up a super-fast rush attack, repeat, and then just turned it on and watched it go. If you did it fast enough, and the AI's sample size of your behavior small enough, you in theory just watch it pump out Zergling-equivalents after just 3, 4 minutes of "teaching it." Let the AI 0wNz0r your opponent... unless he's doing the same thing. I can sort of see this becoming something of a fad, who can "train" their AI's to be more vicious/effective.
    • If I remember correctly that's a mode that Sega put into Virtua Fighter 4 for the PS2... you could "train" an AI and then fight that AI against your friends AI....

      I think it has possibilites...
  • by MongooseCN (139203) on Wednesday September 04, 2002 @10:58AM (#4195115) Homepage
    My only question is if it could even learn to bs for me on those laggy starcraft 3v3 games.

    I don't know about bsing but maybe if you hooked up a mechanical system to your serial port and ethernet cable, it would learn how to pull the cable out of the wall just before the end of your starcraft games.
  • Maybe this can be applied to a plug-in for IE. Then it can constantly refresh the frontpage of /. and try and get first post whilst I'm off hunting down pictures of Natalie Portman.
  • What?!?! (Score:1, Insightful)

    by Anonymous Coward
    Why can't it take out the damn garbage and let me play?
  • Virtual Fighter 4 (Score:2, Interesting)

    by robbway (200983)
    Virtual Fighter 4 for Sony Playstation 2 (PS2) allows you to train fighters to fight in your style. It takes quite a bit of repetition to get it to learn, and then it can fight for you and like you do. It is very reminiscent of the portable Gigapets and their ilk.

    Imagine, I can now eat hot buttered popcorn with both hands as the game plays for me! Is their no limit to my weight gain?
  • Rather, there won't be much of a need to teach it to play FPSes while using aimbots or RTSes while using de-fog of war'rs; once these bots are released it'll only be a matter of time before the proxy bots themselves are hacked and that will present another, potentially impossible obstacle to overcome. If it can out-micromanage and out-aim a human and it can't be detected as it's sitting as an external process, but some may use it as its intended for (why? can you not turn the game off for 15 minutes?) then there's going to be a lot of hand-wringing and a lot of irate people on either side of the fence.
  • Netstorm (Score:3, Interesting)

    by Godeke (32895) on Wednesday September 04, 2002 @11:12AM (#4195181)
    Actually, at one point there was a game based in part on the ability to be disconnected and return called NetStorm. I actually liked it quite a bit (was a beta tester and bought it when it came out) but it ended up selling a very small number of copies and all the players on the server were using hacked clients by day two of the actual release.

    Anyway, the game would fight on while you were gone, which was possible because the pieces were stationary cannons and the like, so when you came back you probably were a bit behind, but not wiped out. I won a few times after a reconnect, so the idea worked.
  • Just about the only game I play is Asylum MUD [asylum-mud.org]. I wonder if this AI would be able to determine what quests I want to do, and remember to snaffle a potion at appropriate times.

    If so, it's a better MUDder than I ;-)
  • To Game Developers (Score:5, Insightful)

    by Speare (84249) on Wednesday September 04, 2002 @11:13AM (#4195187) Homepage Journal

    I agree the server should be watching the player. How better to take notes on how to improve the gaming experience? But don't use it to play the game FOR the player when the player's bored with the game. FIX THE GAME.

    If you've designed your game with lots of boring repetitious stuff which is well-suited for a machine, then you've gone the wrong direction.

    If your idea of making certain events rare is a spawn-rate measured in hours or days, then you've gone the wrong direction.

    If you think of your paying customers as gerbils who will do anything, especially hitting the spacebar or attack key every ten seconds, for eight hours at a stretch, then you've gone the wrong direction.

    Instead, if you want to keep your player's interests, offer more entertainment that works within their available time. Make the player's time in the game more valuable. Make it possible to play a little over lunch, a little on Thursday evening, and still feel accomplishment.

    For starters, employ adaptive spawning instead of location-based spawning. If the server notices a party of adventurers who haven't fought anything in a while, decide approximately how tough an encounter should be, then let it descend upon them. Vary the toughness, vary the approaches, vary the circumstances which trigger a spawn. Don't count server time to the next spawn, count character time to their next adventure opportunity. If the game isn't focused on hunting and leveling to the exclusion of all else (hah, yeah, like THAT will ever happen in THIS industry), then watch the players' behavior to decide what kinds of quests the player likes. Ration those out at a rate that keeps them interested, in character-time, not server-time. If the player plays twice a week, give them the stuff they like each time they log in. If the player really does enjoy slashing for hours on end, then give them a little surprise every now and then.

    Massive multiplayer games should take advantage of the massive multiplayer-ness. Like, duh. The statistical analysis which could be done on player behavior in MMORPGs is staggering. The fact that game designers just don't bother doing it or using it, is mind boggling beyond the extreme. The fact that today's MMORPGs are essentially single-player games with thousands of human-powered NPCs just makes me wonder whether anyone really gets it.

    • If you've designed your game with lots of boring repetitious stuff which is well-suited for a machine, then you've gone the wrong direction.

      I think it should be said that if your game CAN have macros to accomplish a lot, you've done something wrong.
    • by beleg777 (551987)
      If you've designed your game with lots of boring repetitious stuff which is well-suited for a machine, then you've gone the wrong direction.

      Diablo II, check.

      If your idea of making certain events rare is a spawn-rate measured in hours or days, then you've gone the wrong direction.

      Diablo II, check.

      If you think of your paying customers as gerbils who will do anything, especially hitting the spacebar or attack key every ten seconds, for eight hours at a stretch, then you've gone the wrong direction.

      Diablo II, check.

      Yup, I agree. I know you're talking about MMORPGs, but it applies here too. And I think the problem is the same as the ones we complain about in the business world as well. Making a quality product and making a successful product are often different. (see Blizzard vs Blizzard North)
      • Blizzard vs Blizzard North

        But which is which? As I've always found resource gathering painfully BORING. As such I am not much of a fan of the warcraft/starcraft games. I do enjoy squad based RTS, myth the fallen lords and mech commanded for example. Diablo 2, though not perfect is a great game IMHO. I suppect I would reverse the "successful" and the "quality" to what you would chose.

        • Well, it all does come down to preference. I personally really like resource driven RTS games, and get sick of hack n slash RPGs much more easily.

          To me though, the thing is SC had extrememly well thought out details. The details of D2 were rather sloppy, and the coding was abysmal. If you want to disagree, take a look at the patch changes list, and remember that many ballance changes that happened were not included. And then consider how efficiently the program runs after all that. And the origional D2 runs in the same resolution as SC, too.

          Regardless, I can't argue that you should or shouldn't like one more than the other. I'm just saying one was a good idea further developed and excecuted well, and the other was a good idea that was done not nearly so well.
    • Having certain events only happen once in a few days is probably good, actually; it's just that the player shouldn't be waiting for just this one thing. There are games where certain things turn up only once in years of play, and people get really excited when they turn up. The rest of the time, they look for other things.

      For that matter, if you have a ~once/week occurrence where the player had better be paying attention and has to do something situation-appropriate that isn't the usual thing (like run away as fast as possible), you'll develop a nice paranoia in your players even though it doesn't happen that often. Plus you'll make people not leave the game on autopilot because they'll not want to be gone when something important happens.
  • Now is this really an AI or simply just a kind of statistical probability and analysis "tool" (for lack of a better word)? Is all it doing just simply watching what you do, saying "oh when he comes across a zombie he's more likely to cast x spell" and storing that somewhere? Sounds more like a self-adjusting script to me, and if that's all AI is considered these days then oh well. :)
  • I'm waiting for the day I can deploy my MMORPG character using an AI, head off to work, and once and a while repond to his thoughtful emails when he encounters trouble in the game.

    I'll send him back a response telling him what to do, and if he screws it up, and doesn't get iced by some goblins or whatever, you can be sure it will come up at his next performance review.
  • by nick255 (139962) on Wednesday September 04, 2002 @11:32AM (#4195279)
    "The Electric Monk was a labor-saving device, like a dishwasher or a video recorder. Dishwashers washed tedious dishes for you, thus saving you the bother of washing them yourself, video recorders watched tedious television for you, thus saving you the bother of looking at it yourself; Electric Monks believed things for you, thus saving you what was becoming an increasingly onerous task, that of believing all the things the world expected you to believe. "

    An now we have AI's to play tedious computer games for us!
    • I've wondered if Tivo qualifies for the electric
      monk from the Dirk Gently Holistic Detective book

      I can't count the number of shows that the tivo
      decided I should record which I've never really
      watched before the space was reused for another
      show.

      granted, the Tivo doesn't ride a horse
  • It would be interesting to be able to take your AI snapshot from a month ago and play against it, and see if you've improved.
  • ...would be an AI that could teach ME how to play, so i dont get humiliated every time i try an online game.
  • seriously, then i'd be more happier, might ascend for the second time too..

    oh wait..

    it learns how i play.. so it'll usually die before medusa to trolls, or wizard will wipe it's silly ass.
  • Strange game, the only way to win is not to play... how about a nice game of chess?

    Lame I know, but with the WarDriving reference just 2 stories away on the main page I just had to.
  • Taking out the trash is definitely a non-essential task. It's much easier to just pile it in up to the very brim of the garbage can, stomp on it a few times (remembering to carefully avoid the streams of grease and rotten tomato juice that jettison from the containers under your foot) and repeat the process. Since there is a very large amount of unused space between an atom's election and the nucleus, you can continue to fill and compress the same canister for some length of time. You will eventually end up with..you guessed it..Neutronium - a substance so dense that nothing can possibly compress it further. At that point, you simply sell the neutronium on e-Bay to various scientist hobbiests on the internet and start over.

  • How odd, though I am reminded of people making bots for Ultima Online in order to have their characters make money.. Saying most of these games are simply character building anyway.. I played lineage (lineagethebloodpledge.com) for a while until I got bored with character building and wanted to explore, explore before character building and you get killed. fun.. I have set up a large scale ALICE bot that people can put on their webpages at qboard.org (not 'just' a bot, it functions as a news tool, etc..) and am testing that out.. It has had 15,000 conversations so far! So, Hemo's if you want a bot that chats for you too.. ? ;) check botspot ..
  • by dmorin (25609) <dmorin@@@gmail...com> on Wednesday September 04, 2002 @12:01PM (#4195403) Homepage Journal
    What I want is AI that will suck at the game when I suck, and get better as I get better. That way it's not always a case of either I win all the time or lose all the time. Throughout the years I've noticed that chess programs tend to have that problem -- you can beat it all the time at level 1, but almost never win at level 2.

    I thought this would be a great way for children to practice the game. Seemed very "Diamond Agey" to me.

  • Wouldn't it be great if this could learn how I *work*, so leaving me free to concentrate on games ;)
  • by grytpype (53367) on Wednesday September 04, 2002 @12:17PM (#4195477) Homepage
    I have developed an AI that will make your Slashdot posts for you. It just pastes big quotes from the article and throws in a few off-topic references to the DMCA.
    • Hey,

      I have developed an AI that will make your Slashdot posts for you.

      Imagine a Beowulf Cluster of those!

      It just pastes big quotes from the article and throws in a few off-topic references to the DMCA.

      Quotes from the article, eh? You must be new here. Welcome!

      The writeups here are always 100% correct, fair and impartial (except on days ending with a 'y'), so it's never worth reading the article anyway (as if you could expect it to display).

      -Michael
  • from darkages [darkages.com] for speedhacking and using my zippolighter to level skills...argh...

    cu,
    Lispy
  • its all nice to copy your play
    style.. but could they also get
    it to mimick eleet smart ass coments?
  • My only question is if it could even learn to bs for me on those laggy starcraft 3v3 games.

    That's not funny at all... I always longed to meet one of those assholes in real life so I could slap them silly. Or at least scream at them for a little while. People like that are one of the many many reasons it takes twice as much time to find a decent starcraft game as it takes to play the damn game.
  • would be if you could mod this "AI" into learning not only from the player, but also from the opposite players, and then have a bunch of "AI"'s fight against each other...

    Also, it could be used as a nifty screensaver... or to shock non-techie friends... "Yeah, I'm a bit stressed, so my machine is deathmatching itself."

    Let's just hope there are no Harvesters in this upcoming game...

    • would be if you could mod this "AI" into learning not only from the player, but also from the opposite players, and then have a bunch of "AI"'s fight against each other...

      There was a Quake2 bot (for single player DM) that did have a setting which allowed it to adjust skill level according to how well you did against it. If you spawned multiple bots with this setting, though, they scaled extremely quickly.

      Unfortunately (or fortunately depending on how you look at it), playing against that bot for a couple of weeks lead to a lot of accusations once I started playing against real players online again.
  • There are recently a couple of articles on slashdot regarding learning in robots, games etc.. I have read some comments who said what is so new about this... people are doing it from years. I think what people should look for is how "generic" the system can be. One type of learning is just store all the moves of previos games in database and just get the move based on the current position on the board. Obviously, this is not really "generic".
  • In online chess, there is now a distinction made between whether a person or a program is playing. Perhaps RTS games could mimic this, building some kind of interface to let people develop AI.

    Granted, this would take most of the RT out of RTS, but a lot of people are more interested in build orders and tactics than point and click.

    One would hope that the RTS games would be designed so that evolutionary strategies tend to domninate static ones.
  • Back in the day, when I was hacking netrek [netrek.org], I had a damn good go at writing a learning robot client, using a genetic algorithm.

    I failed, along with every other developer that tried it. I failed because while the game is composed of simple concepts - speed, turn, weapons, tractors, transporters - the emergent strategic complexity is way beyond an artificial player.

    The robot could win dogfights, but while it won the battle, the opposing humans were winning the war. It could never figure out or negotiate strategies. Even if I had got it to play a good strategy, the human opponents would have just found a better one, as they have done again and again when playing each other.

    That emergent complexity and strategic depth is what makes netrek such a great game, even today. As a simple rule, if you can write an AI that can beat a human, then you've got a game that's strategically limited, like chess, rather than one where strategy must be a flexible concept, like go.

  • Play the normal games and the quality of opponent goes down (iq and maturity level).

    UMS games involve strategy, not just build_as_fast_as_I_can_and_rush.

    Try any Sunken D or Special Forces maps (personal favorites).
  • lately, the way ive been playing on battle.net, the AI would watch my strategy closely, evaluating diligently, predicting the style and outcome of my strategy,...

    and at that crucial moment i get a phone call and need its help for a few minutes, i click it on and...

    every character would slit its own throat, saving the gold and lumber.

  • The article appears to have been slashdotted, but even so, given the state of AI research right now as I understand it (and I'm probably behind), there are some significant limitations on how good a system like this could be.

    1. If this system truly learns from players, it will require a significant set of training examples in order to 'learn' what the best decision is at any point in the game. In this case, I would think 'best' does not mean 'most likely to win the game' but 'most like the player'. With the number of variables involved in playing a game, it would either take a lot of saved data or a long time to learn any sort of useful evaluation function.

    2. How would a learning system like this decide on which variables to examine when making its decision? Games vary widely. Usually, the less specific the variables--specific meaning the more evenly the value of a variable seperates information into groups--the less accurate the result of the decision will be. This is called 'Information Gain'.

    Even if the system takes the easier route of applying its own evaluation function instead of trying the learn from the player, there are still a lot of difficulties to overcome. For some games--like starcraft--evaluating the state of the player's game is somewhat easy. Using starcraft as an example, one could attatch values to all of the units and then try to move to the state with the highest unit value. However, for other games--like, say, MMORPGs--this would be a nightmare.

    As an example, one of the research projects I've worked on involved training a decision tree algorithm to evaluate link texts to web pages based on user evaluation of those labels. The object was to create a system that would take a page, create an anchor text, and then use a user-data trained evaluation function to choose the best label to pass to the page generator. Even with good data (albiet not enough) and good differentiation between page evaluations, our system was right about half the time.

    I don't know if I buy a realtime learning gameplaying system that's good enough on current hardware. Especially one that works out of the box on all games. There are tricks one can that help, but the real thing isn't quite here yet.
    • I don't know if I buy a realtime learning gameplaying system that's good enough on current hardware. Especially one that works out of the box on all games

      I don't know if the article's just up and down or what, but the second time I tried to get to it, the thing came up just fine. In any case, it answers your question, because it's being developed for a specific game by the developers of said game, and it's an online RTS game.
  • Bah, go one better. Play ProgressQuest [progressquest.com]! No time spent training the computer, it already knows!! Save hours each day!!! (Re)learn the basics, like personal hygiene!!!! Master the appropriate use of punctuation!!!!!

    OK, I'm done now.

    SablKnight
  • I'm wondering if anyone has attempted to link the knowledge stores of an AI chatbot like Alicebot [sunlitsurf.com].

    I enjoy the fact that she can learn, but it seems she would learn at a much faster pace if she could link with other Alicebots via Jabber to syncronize her data stores.
  • The whole point of online gaming is to play against human players who can react to new situations with original ideas.

    Why on Earth would I pay to go online to play against hundreds of machines who are playing on behalf of their owners?
  • I am far too busy with my daily routine and work -I want to play games, but my schedule just does not allow it.

    This is so great, now I can have this thing play games for me all the time.

    I feel like I am having more fun already.
  • Yikes, shades of Mr. Katz... Anyway, if this approach is successful at approximating player behavior, I think it could be a wonderful thing and introduce an exciting new trend into the online game industry. Consider:
    • Right now, even good games have their boring periods where the user must do many repetitive actions dictated by some simple rules. These actions would easily be learned by a good AI engine. Players could relegate such tasks to AIs and focus on the fun stuff instead. The trick would be to make sure the AI knows in what situation to begin the repetitive task -- maybe a little tougher, but should be manageable. It's similar to what medical diagnosis AIs have been doing for years.
    • The ability of players to automate repetitive tasks will encourage game developers to focus more on the aspects of play that are really fun. It will make boring games more obviously boring -- if I can spend an hour playing and then turn it over to the AI and have it play just as well, then it's not really a very fun game is it? So, we raise the bar for innovative gameplay.
    • Whole new types of games could take advantage of this, along with the always-on connectivity of broadband connections. I'd love to see persistent strategy games, where you can check in on your kingdom for a few minutes or hours each day, and the rest of the time your trusty AI "advisor" runs things for you. Sort of remniscent of the old BBS door games, in a way. With MMOGs expanding into things like The Sims Online, it's clear that the medium is ready for more than just RPGs. A learning AI of this sort could be a massively effective enabling factor for innovation (chokes on buzzwords, hehe).
    I want to see it in action. I've got to wonder about their choice to use genetic algorithms -- they're notoriously "the third best solution to any problem" (neural nets are the second). Seems like a more traditional decision-tree-based approach would be more suitable. But it just depends on whether they've been able to tune the selection criteria and crossover function in a suitable way to address the problem at hand. Hopefully it works out well, because I'd like to see this approach become quite common.

You know, the difference between this company and the Titanic is that the Titanic had paying customers.

Working...