Forgot your password?
typodupeerror
Games Entertainment

Believable Stupidity In Game AI 378

Posted by Soulskill
from the much-more-common-in-real-players dept.
Gamasutra is running a feature written by Mick West, co-founder of Neversoft, about creating game AI that is dumb enough to defeat, yet intelligent enough that its "mistakes" are similar to those a real player would make, thus preserving the illusion that the AI is not just throwing the game. "The simplest way to introduce stupidity into AI is to reduce the amount of computation that it's allowed to perform. Chess AI generally performs billions of calculations when deciding what move to make. ... The problem with this approach is that it decreases the realism of the AI player. When you reduce the amount of computation, the AI will begin to make incredibly stupid mistakes — mistakes that are so stupid, no human would ever make them. The artificial nature of the game will then become apparent, which destroys the illusion of playing against a real opponent. ... By reducing the amount of computation, we create an AI opponent that is trying to win, but has been crippled in a way that leads to unrealistic gameplay."
This discussion has been archived. No new comments can be posted.

Believable Stupidity In Game AI

Comments Filter:
  • Kasparov must really be kicking himself if he is reading this article.
    • Re:Deep Blue (Score:5, Interesting)

      by Evanisincontrol (830057) on Wednesday March 18, 2009 @11:40AM (#27242267)
      This has been mentioned before, but I think it's worth bringing up that Kasparov wasn't facing Deep Blue under fair conditions. Even ignoring accusations of cheating and whatnot, there's two very important facts to consider:
      • Normally when a grandmaster plays in a chess tournament, they are givens months of advance warning. The grandmaster will study hundreds of game transcripts, studying their opponent's style and looking for weaknesses. (The opponent will also be given the grandmaster's game transcripts). Deep blue was given Kasparov's transcripts, but Kasparov was given nothing.
      • IBM modified Deep Blue after Kasparov won his first match. This meant that, after finally learning how Deep Blue played (on the fly!), Kasparov basically had to play a brand new opponent.

      If this were a karate match, this would be the equivalent of the master having to fight someone he's never met before, but that person has studied the master's every move. Then, after the master wins the fight, he has to fight someone else who has studied his every move and acts differently. Not a fair fight.

      • Re:Deep Blue (Score:5, Interesting)

        by josh61980 (1025498) on Wednesday March 18, 2009 @01:01PM (#27243625)
        I read about in college. Kasparov did ask for the transcripts. However the Big Blue team told him no. Basically saying it would give Kasparov an unfair advantage because he could study Big Blue's moves and deconstruct the algorithm it used.
  • Cheating AI (Score:5, Interesting)

    by Anonymous Coward on Wednesday March 18, 2009 @11:01AM (#27241637)
    Actually I don't have much issue with the quality of AI's used in games, but I don't like that so many of them cheat. A few games of gotten it right, but many AI's can track my movements through walls. In order to defeat the AI, I have to figure out how it works and so I'm constantly aware it has superhuman abilities and I find that very distracting from the realism.
    • Re:Cheating AI (Score:5, Informative)

      by je ne sais quoi (987177) on Wednesday March 18, 2009 @11:21AM (#27241931)
      I ran into that problem just a few days ago playing Far Cry 2. I was sneaking into the airport to assassinate a character who was in a hanger... As I'm walking around the outside of the hanger towards the entrance, I hear pistol shots at the wall to my left. The AI detected me walked around outside the hanger while he was inside and with perfect accuracy, started trying to shoot through the wall at me. That's the sort of problem this article was about:

      In pool and in shooters, the computer AI is blessed with an omniscient accuracy. The shooter AI knows down to the billionth of an inch exactly where you are, and could shoot your hat off your head from five miles away. Similarly in pool, the AI knows the position of every ball and can calculate where every ball will end up before it takes a shot.

      The solution I found fascinating:

      The programmers of Fritz [a chess program] hit upon a solution that involved the AI deliberately setting up situations that the human player could exploit (with some thought) that would allow the human to gain a positional or piece advantage. Once the human player gained the advantage, the AI would resume trying to win. At no point here is the AI actually dumbed down. If anything, there is actually quite a bit more computation going on, and certainly more complexity.

      So the idea is that the AI needs to calculate precisely where you are, and then rather than hit you if the preferences are set to "hard" or miss you on the "easy" setting, probabilistically make a decision based on what a weaker or stronger human player would do. It's was a great read!

      • Re:Cheating AI (Score:5, Interesting)

        by patro (104336) on Wednesday March 18, 2009 @11:31AM (#27242139) Journal

        The programmers of Fritz [a chess program] hit upon a solution that involved the AI deliberately setting up situations that the human player could exploit (with some thought) that would allow the human to gain a positional or piece advantage. Once the human player gained the advantage, the AI would resume trying to win.

        It's so humiliating, isn't it? We can only win if the machines let us. I for one welcome...

        • Re:Cheating AI (Score:4, Insightful)

          by Hurricane78 (562437) <.gro.todhsals. .ta. .deteled.> on Wednesday March 18, 2009 @11:53AM (#27242525)

          No. What should humiliate you, is the fact, that there is no "machine" "winning". There is only a machine blindly and incredibly stupidly processing a giant set of rules, created by programmers, out of a giant amount of knowledge of many many persons.

          So in fact you play a whole expert comitee that can every minuscule detail down to the stangest exception, in advance.

          Now if you win that, you win against them all, and are truly a genius!

          So how about that fixing your self-confidence issues? ;)

          • by patro (104336) on Wednesday March 18, 2009 @11:58AM (#27242631) Journal

            So how about that fixing your self-confidence issues? ;)

            And how about you getting a sense of humor? ;)

          • Re: (Score:3, Insightful)

            No. What should humiliate you, is the fact, that there is no "machine" "winning". There is only a machine blindly and incredibly stupidly processing a giant set of rules, created by programmers, out of a giant amount of knowledge of many many persons.

            Well, to be fair, there's no "you" losing. There's only a biological machine blindly and incredibly stupidly processing electrical and chemical inputs, based on a set of rules created through years of evolution, and out of the stored memory and neural network training that you have accomplished up to date.

            Just because all of that has a high-order output display that looks like consciousness and thought is no more significant than the fact that the computer's display looks like a chess board. We're way mor

        • Re: (Score:3, Funny)

          by john83 (923470)

          It's so humiliating, isn't it? We can only win if the machines let us. I for one welcome...

          Absolutely. I find it humiliating that a Howitzer can fling a shell further and faster than me, that my car is faster than I am (and can carry more weight) and that my calculator is faster and more accurate at arithmethic than I am.

      • Re:Cheating AI (Score:5, Interesting)

        by Nick Ives (317) on Wednesday March 18, 2009 @12:12PM (#27242855)

        FC2 was notorious for the enemies ability to see you through anything, they clearly didn't even attempt to solve the perfect aim / x-ray vision problem.

        The best shooter in this regard is Crysis. The enemy AI can only see you over long distances if they happen to look in your direction through either binoculars or a scope and if you can't see them they can't see you, even through bushes.

        • by SharpFang (651121) on Thursday March 19, 2009 @04:20AM (#27252685) Homepage Journal

          if you can't see them they can't see you,

          AFAIK they used this approach in Half-Life 2.
          Pick up jar.
          Obstruct the line of sight to the turret.
          Approach turret, carrying the jar in front of you.
          Crowbar the turret.

        • Re: (Score:3, Insightful)

          by nutshell42 (557890)
          The best shooter in this regard is Crysis.

          No, it's not.

          The enemy AI can only see you over long distances if they happen to look in your direction through either binoculars or a scope and if you can't see them they can't see you, even through bushes.

          I only managed to play Crysis for a short time before the lack of immersion killed it for me and the enemy targeting AI was the main problem.

          • Patrol boats can see you through 20m of underbrush and will fire at you with gyro-stabilized sniper machine guns. I
      • Re: (Score:3, Insightful)

        by Cornflake917 (515940)

        I ran into that problem just a few days ago playing Far Cry 2. I was sneaking into the airport to assassinate a character who was in a hanger... As I'm walking around the outside of the hanger towards the entrance, I hear pistol shots at the wall to my left. The AI detected me walked around outside the hanger while he was inside and with perfect accuracy, started trying to shoot through the wall at me. That's the sort of problem this article was about:

        I'm not necessarily saying that this is truly desirable from and FPS AI, but the top Counter-Strike players can do this and do this all the time. I played in a top-tier CS for a while and we learned where all good spots for shooting through walls were. The map "de_nuke" was notorious for having these spots. As CT'S we just listen for the T's, and if they were dumb and didn't walk, a spotter would announce their position, we shoot through the walls and we would generally get a kill or two and then get subs

      • Re: (Score:3, Funny)

        by Guysmiley777 (880063)
        Farcry 2 had a LOT of problems with it. But I'd suggest that *I* know when someone is outside my door without being able to see them. And back in my college years I REALLY knew when the upstairs neighbors were home without ever seeing them.
        • by Walkingshark (711886) on Wednesday March 18, 2009 @06:03PM (#27248459) Homepage

          Farcry 2 had a LOT of problems with it. But I'd suggest that *I* know when someone is outside my door without being able to see them. And back in my college years I REALLY knew when the upstairs neighbors were home without ever seeing them.

          Did you also shoot at them through the walls and ceiling with perfect accuracy?

      • Re: (Score:3, Insightful)

        by crossmr (957846)

        Its not that fascinating. What makes human opponents bad is their inability to see the board and to think ahead more than 1-2 moves. The stronger a player is the more moves he can think ahead. If you want to make stupid AI, then you need to limit its depth, and give it a percent chance of missing things like pins, forks, skewers, etc. You could try to program some kind of tunnel vision. Like the beginner player who doesn't notice the bishop hiding down in the corner when he hangs his queen out to dry. You

    • by grumbel (592662)

      Quite true, its not just that they cheat a bit in there doing, its also that the overall structure of the game cheats, a lot. Most of the times for examples enemies and friendly character will not shoot at each other, they will stand there and shoot, but never actually hit anything, unless you go there and shoot a bit of yourself and trigger a script that will make your friends move forward. In most FPS you can just walk away from the fight, admire the scenery and neither friend nor foe will ever came to ch

    • Re:Cheating AI (Score:5, Interesting)

      by Vectronic (1221470) on Wednesday March 18, 2009 @11:37AM (#27242229)

      I think that's largely because AI is generally controlled as a group entity, so there is one main master pool of data that they get information from.

      When what should be done, is that each AI is IAI or something, individual artificial intelligence, which can be done with object masking, and an analysis of what the AI can see in it's perspective camera, or it's range to a sound, instead of all players and sounds being a dot on a grid, with no regard for obstructions and range.

      Little more on topic, I don't really mind figuring out how the AI is working, what I dislike, is like hard-coded faults, usually with waypointed bots in FPS type games, where they will always get stuck at the same spot on that same path. Because then I abuse it, i'll lead them there, wait for them to get stuck, and kill them... lotsa fun for 15 minutes, but the game gets really boring quickly, however I actually like the superhuman AI as long as they still have to abide by the rules I do (not shooting through walls I can't, etc), makes for great practice.

      I generally don't play games for realism, but rather for the lack of it, I can't go out collecting coins from trees, or shooting my neighbours "really"... excluding racing/flying simulators, but usually they don't have much problems with realistic AI because of how many variables there are to "fuck with", most, if not all of which can happen in reality, sudden gust of wind, punctured tire, blown engine, etc, perhaps thats what humanoid AI games need, is more variables to be more realistic. Different eyesights, hearing, reaction times, strength, etc, etc, then slightly randomized variations on them during the same match, so that even a hard-coded fault in the AI wouldn't come to the exact same result, humans don't play by constants, why should AI.

      Now that i'm rambling, I'll end with the fact that most games are multi-player now, so they spend more time working on the human interaction with the game, and the AI is just tossed in afterwards, probably carried over from v1.0, just so they can say it has that option, expecting people to want to play people. As a side note, maybe thats the logic behind some of them, make shitty AI, to try and force more people to buy+play the game so the game is useful.

      • Re:Cheating AI (Score:4, Interesting)

        by nextekcarl (1402899) on Wednesday March 18, 2009 @01:42PM (#27244231)

        Your mention of racing games makes me recall this racing game I was playing when I was a kid on an Atari ST called Hard Drivin' (IIRC) and I was almost beating the AI when we came up to the draw bridge jump. It was basically a ramp that automatically raised and lowered itself in a cycle, with a large tower in the middle. If you hit it when it was too low you smashed into the tower. If you hit it too high you'd overshoot the track, because right after the other side of the tower was a hard left turn. I could tell the AI was going to hit the jump at the wrong point and overshoot the whole thing, while I was going to hit it perfectly. So when I get to the other side I'm really ecstatic as I watch the shadow of the other car pass over me. I start to get less so when the shadow turns to the left and the AI car lands right in front of me, like nothing special had happened!

    • Re: (Score:3, Insightful)

      by TheRaven64 (641858)

      A lot of these things are hacks to make the AI fast enough to run on the kind of machine that the game targets. For each enemy to have proper vision, you need to do ray casting from each enemy to the player (quite expensive, and very expensive with lots of enemies) and you also need to program them to model human behaviour when the person is occluded so that they guess where the person is. Alternatively, you can just do a distance check, which takes a dozen cycles, and have them able to track the person a

    • Re:Cheating AI (Score:4, Insightful)

      by snowraver1 (1052510) on Wednesday March 18, 2009 @12:15PM (#27242899)
      Civilization Revolution is terrible for this. If you play at the higher difficulties, they will spawn armies and keep sending them your way. The enemy players rarely attack each other. My G/F was playing this yesterday and one of the enemy cities would spawn close to 10 cannon armies in a single turn, then send them at the hevily fortified city to die. Next turn they did the same thing. There is no way that they should be able to build that fast.
    • Re:Cheating AI (Score:4, Interesting)

      by jd (1658) <.imipak. .at. .yahoo.com.> on Wednesday March 18, 2009 @01:38PM (#27244189) Homepage Journal

      I would agree - to a degree. To me, an AI should be as smart as possible (even if superhumanly so - if I wanted a human opponent, I'd go to a gaming club), but should do so on no more information than a human player would have. Thus, you should not have one side play in a "fog of war" and the other be given a full-information scenario. That doesn't cut it.

      But within the constraint of equally limited data, I have no objection to the computer throwing every clock-cycle it has into trying to beat me. I'd prefer it. Game AIs are frequently dumb to the point of being pointless.

      One wargame I used to play was "Crusade in Europe". I found out that if you bombed the enemy supply depots and just sat on the beaches of Normandy, the AI's forces would all starve to death. I successfully won World War 2 from the D-Day landings onwards with under 500 casualties. I wish to argue that this should be impossible, no matter HOW good the human player is.

      Sure, players want to win. That's natural. But they should win because they're good enough to win, not because the AI lets them, even if the AI is sneaky enough to not make it obvious that it's letting them win. Games should be hard. It took me almost a year to reach the top rank in BBC Elite. Had the AI been half-way competent, it should have taken me longer. Games that are completed and disposed of in a fortnight aren't worth the money to buy or the effort to write.

  • by L4t3r4lu5 (1216702) on Wednesday March 18, 2009 @11:03AM (#27241663)
    Have a PRNG have the outcome of 313373 cause the bot to either:
    - Fall on own grenade.
    - Rocket-jump at 25 health.
    - Hump the face of the nearest corpse.
    • Re:Easy solution (Score:5, Insightful)

      by Aladrin (926209) on Wednesday March 18, 2009 @11:35AM (#27242199)

      You're joking, but having realistic actions like teabagging a defeated corpse brings a lot more illusion of reality than a lot of the other stuff they do.

      As for the article, I saw a lot of 'dumbing down' and 'intelligent mistakes' ... But I saw absolutely nothing about 'personality'. -That- is what makes an AI seem real.

      Take the poker example. If you just create 3 levels of players, bad, good, and perfect... There's no personality.

      Instead, you make different players: Cardsharp, timid bets, reckless bets, etc. In other words, you model the AIs after real player types.

      In other words, you're trying to pass the poker Turing test with this AI.

      • Re:Easy solution (Score:5, Interesting)

        by somersault (912633) on Wednesday March 18, 2009 @01:03PM (#27243643) Homepage Journal

        Bah. It depresses me how bad the AI still is in FPS games after I made my own bots for CS years ago (when I didn't have a decent internet connection - when I got broadband I stopped making the bots). My bots had different personalities, can't remember if you specifically had to specify rusher/camper/whatever or if it was just a certain courage level, but you could specify obedience level (for responding to radio commands), weapon preferences, ability to use grenades, aiming skill (higher skill levels would use more controllerd fire and be more likely to HS you on the first shot, while lower ones would start at about chest level then just spray and pray), whether they were able to look sideways to check for enemies down side alleys as they were running along a path etc, all per bot so you could create awesome bots (modelled on myself and my friends :P), and noobs, etc. In the last incarnation they were starting to pick up knowledge of stuff like where they had killed enemies or died themselves which affected their 'courage' and how likely they were to start sneaking around or rushing (made a big difference because you can't hear walking enemies in CS and the bots respected that). Those were the days.. AI is fun, at least for games like Counter-Strike.. it's not quite so much fun for stuff like board games..

        If anyone still has CS 1.5 and wants to try them out they're called TEAMbot and one of the last releases is still up at http://www.planethalflife.com/teambot [planethalflife.com] . I probably still have the latest version of the source on one of my old HDs..

        • Re: (Score:3, Interesting)

          by Cytotoxic (245301)

          One of the best AI examples I've played against was a quakeC bot written to learn just as a player would. The bots had no knowledge of the map nor any information beyond what a human player could garner, but they learned everything they were exposed to. So the first encounter was an easy kill. Later encounters became progressively more difficult as they learned to avoid your fire and learned to anticipate your dodges. In the end, they would memorize all ammo and health spawn points and times such that y

  • by gmuslera (3436)
    Dont confuse it with Artificial Ignorance [ranum.com]
  • If you have too good of an AI. Give it a standard deviation of probability, And adjust it for for the skill level. So for the most part it will shoot near the target but sometimes it will miss and other times it will just be way off.

    • Re: (Score:3, Informative)

      by v1 (525388)

      I think the problem they were discussing is that if you use that probability model, then there is a 2% chance that the computer will make such a totally boneheaded move that goes way beyond what any normal player would commit as a mistake. Like in chess swooping in with the queen to take a pawn and immediately be captured by the adjacent pawn, for no tactical advantage. If you are relying on pure probability to determine what mistake the computer makes, it will occasionally produce grossly unlikely mistak

    • Re: (Score:3, Informative)

      by PhilHibbs (4537)

      Shooting accuracy is easy and has been standard in bot AI since forever.

  • I think the key isn't reducing the number of calculations, but changing the final decision process.

    For example a chess playing AI will make lots of calculations in order to deduce the best possible move. Along the way it has already found the 2nd best, 3rd best, etc. etc.

    Just add an algorithm to the final pre-move analysis and, every once in a while, have it choose the non-optimal move. Tweaking the parameters (e.g. which non-optimal move and how often to not pick the best move) would result in a weaker o

    • by MBCook (132727)

      The article discusses that. The problem is you get in situations where the computer has been playing well and then makes a move so stupid no human would ever make it. It just moves, say, it's queen to be sacrificed with no purpose to it.

      That kind of thing feels insulting.

      I think the idea in the article, that the computer should make a move that leaves a big opening for the human (should they see it) is a good one. If the human doesn't see it, you can do it again. If they do, they feel like they've outmatc

      • Re: (Score:3, Interesting)

        by Compholio (770966)

        The article discusses that. The problem is you get in situations where the computer has been playing well and then makes a move so stupid no human would ever make it. It just moves, say, it's queen to be sacrificed with no purpose to it.

        Not exactly, the GP seems to be discussing a probabilistic system weighted against success. You'd only get dramatically stupid moves on a regular basis if all possible moves were weighted equally, if you weight the best moves the most and the worst moves the least then yo

    • Re:Believable AI (Score:4, Interesting)

      by haystor (102186) on Wednesday March 18, 2009 @11:21AM (#27241939)

      Fritz has a sparring mode which does a little better than that. It will find a route that sets up a position where the player can force a win of a piece or a pawn. Essentially it sets up a tactical middle game puzzle live in the middle of a game.

      The player doesn't know when it will do this or even if it will happen at all. But it is most likely to happen when the player puts the computer under pressure. This is great because it teaches the player to press the computer and coordinate pieces while also constantly keeping an eye out for the wins.

      The whole chessmaster series features near-perfect play alternating with just flat out dropping pieces.

      Even with Fritz though, "easy" mode is still well above beginner.

  • Interesting thought (Score:4, Interesting)

    by JustNilt (984644) on Wednesday March 18, 2009 @11:11AM (#27241811) Homepage

    So, basically, we have to determine how many "calculations per second" equivalent an average human can manage. Then we have to allow a range on either side of that since not everyone has the same capacity. Once we manage that, game AI would start being more realistic, huh?

    Somehow I doubt it's that simplistic but still sort of interesting.

    • by MBCook (132727) <foobarsoft@foobarsoft.com> on Wednesday March 18, 2009 @11:25AM (#27242005) Homepage

      That's not what I got out of the article.

      What I took away was have your opponent play it's strongest, but make exploitable situations for the player. Make a pool shot so they human starts in a good position. Make a chess move that, while beneficial, opening a big possible hole for the player to exploit. Make the FPS bot run for cover at the wrong moment, but not randomly/suicidally.

      (those are all from the article)

      Basically make the AI make human like mistakes (mistakes in strategy) instead of "computer like" mistakes (just lowering their accuracy, not looking far ahead, etc).

    • by MobyDisk (75490) on Wednesday March 18, 2009 @11:30AM (#27242121) Homepage

      Actually, he is saying the opposite. He is saying that by reducing the number of calculations per second, you create an unrealistic opponent. Instead, you must do additional calculations to model the mistakes that a human would make. Our problem is not that we don't do enough calculations, but that we make mistakes in our calculations. We are inaccurate, we jump to conclusions, we get excited, or calculate one branch of the tree very deeply while ignoring another one. Those types of things are tough for computers to do.

    • Find the "clock speed" that the game needs to win against a particular person say, 50% of the time. Call that the gamers "clock speed" or gaming intelligence.
      Once you have that, you could start giving games meaningful measures of difficulty: such as "This game is suited to players with a GI greater than 80"

      It would then be interesting, if not useful, to see how people's G.I. varied, and if their GIs correlated (or negatively correlated) to any other metric, such as SAT scores. Even better, you could deter

  • by ndavis (1499237) on Wednesday March 18, 2009 @11:12AM (#27241823)

    This must be the problem facing the team creating Duke Nukem Forever.

    They needed the AI to be dumb enough so you could hear the comments all the time during the game.

  • by jollyreaper (513215) on Wednesday March 18, 2009 @11:12AM (#27241825)

    What I've always wanted to see is more scripted realism in games. For example, the Medal of Honor games worked much in the same way as a Disney theme ride with certain prescripted actions occuring when you passed by. Run across the field to the house, then the soldiers there will go through a scripted sequence of planning the next move, then they do so. You walk past the far side, a German tank triggers and comes crashing through at you. These are all nice starts. The original Aliens V. Predator game would have the human opponents freak out at random. You tear the head off of someone beside the soldier, he might drop his weapon and run screaming or start spraying the walls at random. And the most unsettling of all were the civilians who would run, cower and cringe away from you, the alien monster.

    All of the above are tricks, not real intelligence but things that provide the illusion of intelligent agents engaging in realistic behavior. Critics will say the heavy scripting ruins the replay value because there's not as much room for variation and surprise but I think that it makes the games more interesting. Unfortunately, not many people go to the effort here.

    I for one would love to see a shooter where I burst in on the room of baddies playing cards and see them fumble for their weapons, someone drops his, etc. It would be very realistic to have an enemy get the drop on you but his gun jams and he's left trying to clear it when you engage. As mentioned before, AVP created a sense of realism when the humans freaked out and started firing randomly.

    When we get right down to it, players aren't looking to get their asses mercilessly beaten every time they play. Neither do they want a pushover opponent. Gamers want to win but they want to feel like they had to earn it. It's rarer to find gamers who want to push the working for it to masochistic levels but they do exist. They would be typified by Rogue fans. For those who don't know, Rogue is a dungeon crawler where you really should save your game except you can't except as a bookmark -- you can save it to come back later but if you die the previous save point is deliberately deleted. You have to beat the game in one go through.

    The only other game I've encountered that masochistic is Escape Velocity Nova, a space exploration and trading game with a realism mode. You die in the game, you die for keeps, you have to start over. To its credit, it does offer a vastly different play style. For example, you want to hit a big pirate ship for max profits, you pick a world near where they spawn and land. Each time you launch local space reloads and a pirate might respawn nearby. You have maybe a one in ten chance of taking him as a lowly player but it's fun. You keep reloading and rolling the dice until you win and you get a nice haul. If you play it in hardcore mode, you have a vastly different approach to this sort of thing. For starters, you lose your ship and it's gone, you have to buy a new one. If you lose your escape pod, you're dead. You will take a vastly different approach tackling a monster like that when you risk losing hours of progress. This seems too much like work to me but some people love it. I think they're the same ones drawn to high-risk PVP games like EVE Online. I think it's a form of gambling addiction, the risk of possibly losing a lot of stuff and the thrill of making it through.

    • Re: (Score:3, Interesting)

      I think a set of possible scripts would actually make things more realistic. In reality a team goes according to script. They might have contingency plans. The more trained and prepared the more contingency plans and the more they will follow those plans. I would expect the SAS to be much more accurate when everything goes wrong than the common soldier. The less trained and prepared the less contingency plans and the more they will panic and deviate from the plan when things go wrong. I think a good s

    • by skorch (906936) on Wednesday March 18, 2009 @01:04PM (#27243655)
      Sorry, but as you say I must almost completely disagree with your sentiment on scripted events in games. Scripted events are not good example of AI because there is no decision making, which makes them predictable and exploitable. So the only way to scale difficulty in a scripted scenario is to just pump up the AI's accuracy, damage, and health, which are not very interesting. Scripted events work fine for fairly linear narratives and setting up big cinematic set-pieces, but they don't make for interesting gameplay (mind you I did not say they don't make for "fun" gameplay).

      The events you describe in AvP are not necessarily examples of scripted scenarios, but sound more like a scripted set of responses to stimuli the player provides (would the AI react differently if you didn't rip off a soldier's head?). The trick for interesting yet realistic decision making is to allow the AI a range of responses that it can make, and then every time you present the same scenario to the computer you may get a different response. So when the AI is actually making decisions, rather than just following a pre-scripted path, this allows the player to make actual decisions in response, rather than just following their own memorized trial-and-error derived path to success.

      The key to a good scaling AI doesn't have to be that tricky, it can just be a matter of what range of choices you allow any given AI to make and what sorts of "mistakes" you throw in that pool of choices.

      When I face "easy" opponents in an FPS, I want them to use simple tactics (not just be unable to hit the broadside of a barn) like charging forwards blindly, or getting scared easily and retreating or even panicking, and being easily suppressed by heavy fire. When I face more advanced opponents, I want the range of their choices to move up the tactical scale to include flanking maneuvers, suppression fire, use of cover, and tactical retreats. A good mistake for an advanced AI would be to assume you're in the wrong position if you duck out of view and to attack that wrong position vigorously (as opposed to the omniscience a lot of AI's seem to have). They don't have to be any more accurate or need any more bullets to kill than an easy bot, but at least they could present more of a real challenge without artificially increasing their stats. Granted this is harder to do and would require actual programming rather than just increasing a few numbers, but that's the price for good AI in your game.
  • by hal2814 (725639) on Wednesday March 18, 2009 @11:15AM (#27241877)

    Oh, the humanity! Football games drive me nuts when the AI does stupid things no real person would ever do. Why the hell did my fullback just brush by the linebacker that's right in my RB's way?! Why can't I get my linebacker to stay in his lane on running plays?!

    I'd love to see the difference in difficulty in Madden being the difference between playing a Jerry Glanville-coached team vs a Tom Landry-coached team. Instead, all increasing the difficulty does is make your opponents more talented but no smarter. Even on the highest difficulty, FBs don't understand their blocking assignments.

    • Re: (Score:2, Insightful)

      by damnbunni (1215350)

      How much of that is due to difficulty in writing a good AI for a fullback and how much is due to EA not needing to write a good AI for a fullback because there aren't any other football games left to compare it to?

      When you have a license monopoly, why try?

      • by hal2814 (725639) on Wednesday March 18, 2009 @11:58AM (#27242645)

        A fullback's running assignment is one of the most conceptually easy AIs to write. Run in front of the RB and knock as many people down as possible before they get to the RB (or until the RB passes you). If they can make a reasonably sane QB AI, they should have no problem with a decent FB.

        As far as monopoly, the Madden fullback AI was a Rhodes Scholar compared to the fullback logic in the 2K games. At least the Madden FB doesn't go running off to the other side of the field based on how the D is stacked. And don't get me started on NCAA 2K2's misuse of the word "flex." Flex is not a damn blitz! Flex LBs are supposed to sit back and plug holes, not free-for-all the QB. And that's coming from someone who preferred the 2k series.

    • Re: (Score:3, Funny)

      by Anonymous Coward
      I never thought that I'd have to make the following proclamation... I don't follow your technical jargon.
    • by rickb928 (945187) on Wednesday March 18, 2009 @12:19PM (#27242969) Homepage Journal

      "Oh, the humanity! Football games drive me nuts when the AI does stupid things no real person would ever do. Why the hell did my fullback just brush by the linebacker that's right in my RB's way?! Why can't I get my linebacker to stay in his lane on running plays?!"

      Gee, you sound like a real life coach. Certainly like my High School coach.

      I'm thinking the AI is working like it should here. You got your disgruntled, not getting paid enough FB who isn't taking the hit, and your linebacker who thinks he's smarter then your Defensive Coordinator and is freelancing with visions of stardom in his head.

      Realistic this is, I think. Patience, padiwan. Trade you must. Draft you will. Beware of anger.

  • AI leaps and bounds? (Score:5, Interesting)

    by Gizzmonic (412910) on Wednesday March 18, 2009 @11:17AM (#27241903) Homepage Journal

    Year after year, I read these kind of articles that report how game AI increases in leaps and bounds...and I still don't see it. Bad guys in GTA still seem to rush towards grenades, Halo/Gears of War enemies are either completely impulsive or avoidant. I'm not knocking the programmers...I think game AI must be very difficult to achieve, and even harder to detect for the layman (such as myself).

    Does anyone have an example of really good AI in action games (or any non-RPG, non-RTS games)?

    • by Sj0 (472011) on Wednesday March 18, 2009 @11:56AM (#27242589) Homepage Journal

      The Half-life series has always been acclaimed for the AI.

      I found Left 4 dead had excellent AI. The zombies rarely did things that didn't make sense, the only thing I can think of is when they climbed up on objects they didn't need to climb over.

      It's not enemy AI, but Alyx from HL2 was pretty impressive. The zombies rarely did something stupid, but Alyx never did anything stupid. I'm sure I'm not the only one who formed a weird bond with the character by the end of Ep. 2

    • by Jim Hall (2985) on Wednesday March 18, 2009 @01:35PM (#27244145) Homepage

      Does anyone have an example of really good AI in action games (or any non-RPG, non-RTS games)?

      The AI in the first Half-Life was pretty good, I thought. Especially for the era. There were AI creatures that, once they saw you, would run to the rest of their group so they could attack in greater numbers. IIRC, other AI would behave a certain way (i.e. aggressive) until their health dropped too low, then would act in another way (i.e. defensive, even retreating.) It was very believable with the non-human creatures (the sonic dog-things) and not too bad with the enemy soldiers. I think the soldiers had certain logic, where if they had a reasonably good shot at you, they took it - otherwise, they'd reposition to get a better angle. Net effect: in certain areas, you'd have two soldiers laying down "covering fire" while two others ran around the corner to flank you. I was surprised by that the first few times it happened; very decent AI.

      I'm re-playing Killzone 2 right now. The first play-through, I thought the AI wasn't too bad. The second time through, I realized that the AI had a different behavior when you were more than a certain distance away vs. closer. So on my second time through the game, I ran up to a lot of Helghast and used the knife on them (there's a trophy for that, anyway.) If you can get close enough without taking too much damage, it's easy because the AI takes about half a second to switch to the other "mode", during which time it has stopped shooting. That's the opportunity to strike. (Yes, this kind of kills re-play value.)

    • by Jim Hall (2985) on Wednesday March 18, 2009 @01:51PM (#27244393) Homepage

      Does anyone have an example of really good AI in action games (or any non-RPG, non-RTS games)?

      I really liked the AI in the Thief 1 & 2 games (never played Thief 3.) Very believable, added a certain dimension to the game.

      Guards would sort of tool around the place, doing their rounds. If you hadn't been discovered, they were not very attentive (you might believe they were just bored with the routine.) If they heard you make a noise, they entered a higher level of alertness, became more suspicious. Their posture would change as they snooped around, looking for what caused the noise. You had to be really well-hidden for them not to find you. If you made any more noise, they went towards that. Make a lot of noise, or show yourself, and they entered full-alert and came charging. You were pretty much screwed if you found yourself trapped in a semi-dark corner on marble tile when guards were around.

      If a suspicious guard didn't find anything, then he would (after a long while) go back to the lower alert level, and just go about his day. But I don't remember that guards, once they actually saw you, ever went back to just doing a normal, unaware patrol.

      (Did suspicious guards "infect" nearby guards, causing them to become suspicious for a certain time? Maybe someone here will remember.)

      Guards alsowent into higher alert automatically if they came across an unconscious body. So you always had to be careful about stashing the body(ies) when you coshed someone.

      It would have been much better if guards responded to torches going out, or moss suddenly appearing in a room, or an arrow sticking out of a post, or a door left open. Even a simple acknowledgment "hmm, I thought that torch was lit before... must have gone out" would have been more realistic.

      But generally, I thought the AI in Thief was pretty well done.

  • by Genrou (600910) on Wednesday March 18, 2009 @11:23AM (#27241979)
    If it is so difficult to raise the computers to the level of human intelligence, it is probably impossible to reach the level of human stupidity.
  • by rillopy (650792) on Wednesday March 18, 2009 @11:23AM (#27241985)
    Unfortunately, the AI generally only gets a tiny slice of the CPU time. If it were to use as much as the graphics, etc, then sure: the extra processing required to make the AI believably stupid would be easy. The innovations are there, it's just they are too slow or processor intensive to be implemented in most games.
  • No Human? (Score:5, Funny)

    by chrispycreeme (550607) on Wednesday March 18, 2009 @11:24AM (#27241997)

    The problem with this approach is that it decreases the realism of the AI player. When you reduce the amount of computation, the AI will begin to make incredibly stupid mistakes -- mistakes that are so stupid, no human would ever make them.

    The author has obviously never played chess with me.

    • Impatience (Score:3, Interesting)

      by Xocet_00 (635069)
      It's interesting that they say this actually. I'm a terrible chess player not because I don't 'get' the game, but because I'm not very patient. So I tend to do fairly well playing speed chess, but doing very, very poorly in a normal game. I tend to just get tired of evaluating the possible moves after a while and just make whatever one was the most promising out of the few that I did think about.

      Isn't that sort of the same thing as limiting the number of calculations? In this case limiting the calculation
    • Re: (Score:3, Funny)

      by theaceoffire (1053556)

      The author has obviously never played chess with me.

      You sunk my battleship! Now how am I supposed to connect four?!?

  • This is the stupidest (because it's most obvious) summary I have read on Slashdot in weeks. There's no other way to say it. It reads like some interesting discovery ... but it's not.
  • by AlpineR (32307) <wagnerr@umich.edu> on Wednesday March 18, 2009 @11:28AM (#27242103) Homepage

    My first rule of game AI is that the computer should have access to the same information and controls as a human player. I hate games where the computer knows about your units and buildings that it hasn't scouted.

    The big advantage that computers have is that they can micromanage every unit with 100% efficiency. One way to reduce skill could be to limit the amount of attention the computer can spend, maybe in the form of "actions per minute". For a game like poker that could be a limit on how precisely the computer player calculates odds. A more experienced human player has a better feel for the game, so a more skillful computer player could dig deeper into the nooks and crannies of probability.

    A way that computers often act too stupid is not accounting for how their interactions with one player will influence other players who aren't directly involved. For example, in a three-way game the computer player might throw everything against the strongest player, weakening them both and letting the third player win. Humans have millions of years of instincts for dealing with such situations. So the game AI might need to precompute some game theory and adapt to opponent reactions over a series of many games. Then it could be dumbed down by reducing its use of that experience and acting more like a newbie human player.

  • Competing goals (Score:5, Interesting)

    by olclops (591840) on Wednesday March 18, 2009 @11:30AM (#27242125)

    If you want an AI to make human like mistakes, you have to have at least a roughly human cognitive model. The simplest way to do this, it seems to me, is to give the AI competing goals. Rather than just have the AI "try to win", and then cripple its ability to do that effectively, you could give it multiple goals to strive toward, and then give it some degree of randomness in which goal it chooses to pursue. Victory vs. pain-avoidance, attack vs. finding time to recover, etc.

    • Re: (Score:3, Interesting)

      by rm999 (775449)

      "you could give it multiple goals to strive toward, and then give it some degree of randomness in which goal it chooses to pursue. Victory vs. pain-avoidance, attack vs. finding time to recover, etc."

      That strategy would still create bot-like behavior; programmed correctly, a bot will find an "ideal" solution to a constrained problem. This isn't how humans work. Humans aren't just random number generators attached to optimizers. In fact, the score function of the typical game engine (like chess) works almost

    • Re:Competing goals (Score:5, Insightful)

      by tnk1 (899206) on Wednesday March 18, 2009 @03:07PM (#27245637)

      I agree with this totally. One of the bigger reasons some players fail at a game is that they aren't actually playing the same game as everyone else.

      What I mean is illustrated by some post I read once where some jerk, who was also a rather good player, laid it out bare:

      Many people don't play the game. They invent their own little rules for what is "fair" or "better" or "morally right". This handicaps them. You win by playing the game and using all of your abilities and all of your assets to do so, no matter how "cheap" or "skill-less" they seem to you.

      If the game makes it so that some skill does more damage for less effort, but you prefer to use another skill because it seems "cool" to you, or you liked the animation or whatever, you deserve to lose.

      The one thing that this illustrates is that a computer also tends to have clarity of purpose. They are programmed to kill you. That is what they do. They aren't there to smirk or taunt you (unless that's in the script). They will not dance around or try and add finesse to their moves to look cool. They use the most efficient moves or actions to kill you. Or, sometimes, they only get a certain set of moves, but they are scripted to execute them in a certain manner.

      So, basically, by giving your NPCs a "personality" where their goals aren't to strictly kill you with Terminator-like focus, but perhaps to simply make you look bad, or use some moves that *they* think are cool, which really aren't all that useful, you can make them a bit more "human".

      The problem with most mobs is that you already know their motivation, so knowing what they will do next is actually rather easy to figure out. So, if you "cheat" with their AI, it becomes apparent to players that you either buffed or nerfed them artificially.

      If your mobs act in a manner where they are believably foolish, its a lot easier to handicap them and have a player believe that the handicapping is their lack of "skill", rather than you simply giving them less hit points or some absurd lack of resistance to one damage-type.

  • by hey! (33014) on Wednesday March 18, 2009 @11:32AM (#27242155) Homepage Journal

    And vice versa.

    One thing that is stupid: trying the same things that failed in the past.

    This is a component of smart behaviors as well. If you don't know what to do, try something and watch very carefully how it fails. If you are in a desperate situation and you are going to definitely fail through inaction, then try an action which failed in the past and hope you get lucky. Or vice versa, when the action that usually works looks like its going to fail, try doing nothing.

    Animals freezing in the face of danger is an example of this. It's not much of a defense, but you might get lucky. Maybe the prey a couple animals down the line will get itchy and draw the predator's attention.

    On the other hand, smart behavior can be a component of stupidity. If the red button gets you a treat 80% of the time and the green one gets you a treat 20% of the time, the intelligently stupid thing is to push the red button 100% of the time. The stupidly intelligent thing is to try to work out the pattern of red/green rewards.

    If you want realistic model of stupidity, provide the NPCs with a range of decision making strategies, all of which work to some degree, but the better of which take more effort (computation). The NPC can choose between the strategies with a random function weighted towards the better strategies, but as time and "stress" come into play the function can shift towards the easy but less effective strategies.

    That's a pretty good model of human performance "choking".

    Evolution did not produce human stupidity because it was useless, after all.

  • F.E.A.R. (Score:5, Insightful)

    by A. B3ttik (1344591) on Wednesday March 18, 2009 @11:41AM (#27242287)
    F.E.A.R. is the only game to date that I've played and honestly felt like I was playing against human opponents. Honestly, they were as smart as or even smarter than playing against people online.

    They did this through heavy use of waypoints and scripted events. If that's what you have to do to make it realistic, then by all means, do it.
    • Re: (Score:3, Informative)

      by CAPSLOCK2000 (27149)

      FEAR gained it's AI from using a planner to string actions together to reach some kind of goal.

      It's not the waypoints or scripted events that make it special, every shooter has those.
      In short a character in FEAR consists of a set of actions (shoot, dodge, open door, jump through window, etc..., etc...) and a set of goals (kill player, survive, stay in cover).

      Each action has a number of pre- and post-conditions, just like functions have in (formal) programming. Actions also have a cost. A searching algorithm

  • NP-tard? (Score:5, Funny)

    by illegalcortex (1007791) on Wednesday March 18, 2009 @11:41AM (#27242289)

    Do we have programmers that are smart enough to program stupidity algorithms to be smart enough to be as stupid as humans?

  • by vadim_t (324782) on Wednesday March 18, 2009 @11:49AM (#27242431) Homepage

    A computer that plays on equal terms.

    AIs often win in some games not by the virtue of being smarter, but by having an unfair advantage. Examples:

    • In RTSes, constant money injections. This pretty much nullifies attempts to attack resource collection -- they don't need it anyway.
    • Knowledge of the position of everything. In RTSes, they don't need to discover your position. It's useless to try to build an outpost and hide the real base somewhere behind it. In FPSes they know where you are, and can tell when you're sneaking from behind
    • Instant reaction time and all-encompassing awareness. In RTSes, the AI is capable of controlling every unit at once, and knows what's going on in the whole map at once. Meanwhile, the players are limited in the speed they can give orders, and only has a view of part of the world. Due to this, the AI can't be fooled by multiple attacks from different places, it will see all of them perfectly.

    My suggestion: An AI should be coded as a bot, within the constraints given to the player. If the player can only see a part of the battlefield (like in Starcraft) then the AI should have the same limit and need adjust its own viewport to gain awareness of an area. It should also be limited by the fog of war, and lack the ability to see out of the back of its head. To put in another way, a fair Starcraft AI would be one implemented with a camera pointed at the screen, controlling only the keyboard and mouse inputs.

    The idea is that I want to be beaten because the AI is indeed smarter, not because it's got a superior access to the battlefield I can never gain.

    Chess probably comes closest to the sort of thing I want -- the AI and human are fighting on very equal terms. I don't see the calculating millions of positions a second as a problem, that's simply an implementation detail.

    • Re: (Score:3, Interesting)

      by v1 (525388)

      My suggestion: An AI should be coded as a bot, within the constraints given to the player. If the player can only see a part of the battlefield (like in Starcraft) then the AI should have the same limit and need adjust its own viewport to gain awareness of an area. It should also be limited by the fog of war, and lack the ability to see out of the back of its head. To put in another way, a fair Starcraft AI would be one implemented with a camera pointed at the screen, controlling only the keyboard and mouse

      • Re: (Score:3, Interesting)

        by vadim_t (324782)

        While this is a very good idea, it's very difficult to implement well, and it's been tried plenty of times. I've played games that attempted that, but as a result were very easy
        to beat. For example, you could start an attack on three fronts, and the AI would ignore all but the top two threats, and the third front would just walk all over them. Every single time.

        That's just a bad implementation. There's no reason why an AI couldn't ocassionally spend a while to look at its territory. Also, the human player u

  • by rapiddescent (572442) on Wednesday March 18, 2009 @12:19PM (#27242977)
    back in the day - Gran Turismo (the popular playstation driving game) used to have AI cars that would make driving errors such as braking too late into corners or oversteering and spinning out onto the grass.

    It used to have hilarious consequences as AI cars behind the spinning-out-of-control AI car would crash into it, deflecting and causing a complete pile up.

    This gameplay felt realistic because this is what happens when cars are travelling at high speed in close formation.

    Newer versions of Gran Turismo on the Playstation 3 - have way more computation cycles and so the AI cars now drive a whole lot better and never seem to crash. Sure they take different lines into corners and so on - but they don't completely bollox it up like the human drivers often do. It has made the game pretty infuriating because it has taken a randomness factor out of the game.

  • by Animats (122034) on Wednesday March 18, 2009 @12:51PM (#27243471) Homepage

    That particular game programmer happens to have worked on games where perfect execution is possible. In chess, "execution" is moving the pieces; in poker, it's moving the cards. The game engine is expected to perform those operations perfectly. There's no "friction" (in the sense that Clausewitz used the term) in such games.

    That's not true of a combat game. Weapons have finite accuracy, as do humans; sometimes there will be a miss even if the shooter, human or AI, did everything right. Weapons can jam (America's Army simulates this.) Running characters don't necessarily follow their planned path; bumps on the ground and slippery spots can interfere. The AI has to face those limitations, too.

    Of course, if you make it too real, some kinds of games are unplayable. You can't really drive a car very well with a game pad or joystick. (Watch people driving R/C cars that way. They crash every few minutes.) In most console driving games, the CG of the vehicle is below the ground, to make the thing unreasonable stable.

    In my ragdoll-physics days, we'd made enough progress that a two-person martial-arts fighting game with real physics looked feasible. Then we realized it would be unplayable. "Your throw failed because your left foot was out of position. Further to the left. Again!" "Yes, sensi." Real physics in a fighting game would make gaming feel like a bad day at the dojo, although without the bruises. Most of your moves wouldn't work. A game with a learning curve like real martial arts, where you train a few times a week for a few years before you're any good, would never sell.

  • Truly realistic (Score:4, Interesting)

    by gurps_npc (621217) on Wednesday March 18, 2009 @01:55PM (#27244439) Homepage
    The author's unspoken assumption is that it is impossible to have them make mistakes the way humans do.

    Take poker for example. We have a standard bias of "unknown = 50%". This actually works pretty well for cases where information is not known. To make the winning software programs, they basically program in the rules that a human expert knows to be true. It is NOT that hard to instead program in a bunch of rules that a human FOOL 'knows' to be true. Just find some bad poker players and ask them what they do in certain circumstances.

    -------------- Similarly, the pool game could be made more realistic. I noticed the first thing he did was have the computer select the highest possible point scorign shot, ignoring banking a shot unless it is set to super-expert. That is NOT what humans do. Bad pool players pick the EASIEST shot - i.e. the one that is most straight on and least distance. (I know, I am a bad pool player). As you get better, you raise your standards about what you think you can hit. So a moderate player looks among all the shots he thinks he can hit and takes the highest point one of that.

  • by w0mprat (1317953) on Wednesday March 18, 2009 @03:47PM (#27246325)
    Human behavior is naturally variable, for example, a pro basketballer can still and will miss a hoop. Likewise this variability allows amateurs to have some luck. Indeed an elite gamer will occasionally have their ass handed to them by a complete noobcakes. We don't see this in game AI, which is ruthlessly consistent.

    It's interesting that in order to create better AI, we need to create Artificial Stupidity. Some would argue that is already all around us.
  • by 7-Vodka (195504) on Wednesday March 18, 2009 @08:26PM (#27250053) Journal

    mistakes that are so stupid, no human would ever make them.

    Really? That's a bet I would like to be on the other side of.
    Someone needs to get out and mix in the general population.

FORTUNE'S FUN FACTS TO KNOW AND TELL: #44 Zebras are colored with dark stripes on a light background.

Working...