Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 



Forgot your password?
typodupeerror
×
Real Time Strategy (Games) Games

Emergent AI In an Indie RTS Game 146

x4000 writes "My recent RTS game uses a new style of AI that hybridizes rules-based AI with emergent AI logic. As a disclaimer, I'm really not an AI programmer at all — my background is in databases, financial modeling, etc. But it just so happens that database experience, which often involved distilling data points from multiple sources and then combining them into suggested decisions for executives, also makes a great foundation for certain styles of AI. The approach I came up with leans heavily on my database background, and what concepts I am familiar with from reading a bit about AI theory (emergent behavior, fuzzy logic, etc). The results are startlingly good. Total development time on the AI was less than 3 months, and its use of tactics is some of the best in the RTS genre. I'm very open to talking about anything and everything to do with the design I used, as I think it's a viable new approach to AI to explore in games, and I'd like to see other developers potentially carry it even further."
This discussion has been archived. No new comments can be posted.

Emergent AI In an Indie RTS Game

Comments Filter:
  • Article summary: (Score:5, Insightful)

    by ActionJesus ( 803475 ) on Wednesday June 03, 2009 @02:20AM (#28192691)

    "I just wrote a game. Heres some techy stuff to get it posted on slashdot. Yay advertising!"

    • Thanks for the Culture of Cynicism comment -- we definitely need more people like you around that needlessly shit on others doing new stuff.

  • player mimicry (Score:5, Interesting)

    by drDugan ( 219551 ) on Wednesday June 03, 2009 @02:29AM (#28192753) Homepage

    could you catalog user actions and use them as possible inputs for your AI?
    like this: http://slashdot.org/comments.pl?sid=1165583&cid=27243769 [slashdot.org]

    it would seem this might make for the most challenging AI - one that
    learns and mimics good human players. I have yet to see any games
    that can do this well

    • by x4000 ( 1568105 )
      Hi there -- I'm actually the dev from the article. This is a very interesting suggestion, and I'm sure that people will try this at some point. My main issue with that approach is that it requires a huge amount of ongoing data, which I'm not sure quite how to deal with at this stage. But like I've said, I'm fundamentally a database programmer and not an AI programmer. With my approach, what I wanted to do was have basically a "stateless" set of AI logic, which could look at any given situation and make
      • by mcvos ( 645701 )

        I think the Mimiry suggestion is more comparable to a chess player who has played a lot of games, studied other people's games and studied books on opening theory and that sort of thing. That gives a good player a big knowledge base of good moves and a feel for how the results of those moves might turn out. A self-learning system would expand its base of good moves with each new game it plays.

        • by Gulthek ( 12570 )

          Unfortunately, you are giving chess a little too much credit here. An unbeatable chess strategy really is to have an internal catalog of board states and optimal moves from those states.

          For a less rigid game a strategy of recording player moves becomes intriguing, but also extraordinarily more complex in that you must catalog sequences of related actions. AI by macro?

          • by mcvos ( 645701 )

            Unfortunately, you are giving chess a little too much credit here. An unbeatable chess strategy really is to have an internal catalog of board states and optimal moves from those states.

            No, an unbeatable chess strategy is calculating the entire game to the end (or at least to an obviously won osition). I'm just explaining how chess strategy works in practice. How am I giving chess too much credit?

          • by erko ( 806441 )
            Are you saying professional chess players don't prepare for big matches by studying their opponent? (and their opponent's previous games)

            I realize that players at that level probably mostly play from a memory of board states, but there are so many possibilities that knowing which ones to focus on let's you analyze the possibilities that are most likely. The unbeatable chess strategy you describe is for a computer with a ton of memory and a fast search capability, not for humans or human-like AI.

            Back to
  • Summary useless (Score:5, Informative)

    by toxicbubble ( 1568519 ) on Wednesday June 03, 2009 @02:31AM (#28192761)
    Summary reads like a marketing blurb but the actual article is slightly more interesting. The basic idea is that in an RTS game, the AI is at a unit level rather than an 'almighty all-seeing controller'. It is a fairly interesting idea and does sound sort of different way of thinking about computer RTS opponents. Weather or not this actually makes for a fun game or a good idea remains to be seen, but at least there is something (dare I say) slightly innovative about this.
    • Re: (Score:2, Insightful)

      The notion of intelligent agents has been around for quite a few years.

      Even I, 12 years ago at the University, had to implement a miserable little game where the A.I. was at a lower level than an all seeing, all knowing AI that makes decisions, each agent with it's set of "intelligent", adaptive rules.

      So... how is this concept new (or NEWSworthy, for that matter)?
      • by mcvos ( 645701 )

        So... how is this concept new (or NEWSworthy, for that matter)?

        This is games.slashdot, and good AI still hasn't been done in games. If this results in some decent AI, it's worthy of slashdot. But a bit more data on either the quality of the AI or the technical side of it would have been nice.

      • how is this concept new (or NEWSworthy)

        By linking sufficient AI together in a functional framework which could become a commercially and financially viable product. This is a far more difficult task than a single project at University which does not have to appeal to a wide audience with often conflicting requirements.

      • Re:Summary useless (Score:5, Informative)

        by x4000 ( 1568105 ) on Wednesday June 03, 2009 @07:13AM (#28194027) Homepage
        Quite valid -- intelligent agents are not a new idea (I'm the dev from the article). However, the vast majority of RTS games are still using decision trees, I guess because the prevailing wisdom is that such is needed because of the complexity of RTS play. Is it so surprising that industry lags behind academia? But, even my approach is not purely an intelligent agent approach, but rather combines in a bit of global logic as well (for reinforcements, choosing global attack targets, etc). I think that a hybridized sort of approach is really needed for RTS games, since they do have so many levels at once.
    • Re:Summary useless (Score:5, Interesting)

      by BikeHelmet ( 1437881 ) on Wednesday June 03, 2009 @04:31AM (#28193315) Journal

      In short, it segregates the controller AI from the unit AI.

      I can remember when playing SupCom against easy opponents, if I didn't build any defenses, the opponent would stop sending units into my base for a while, instead moving them around in circles somewhere outside it. Even an easy/stupid AI has to make decisions that a stupid person would make. Mainly - CHARGE!

      But at the same time, the best AIs were omniscient. They'd target your first fusion reactor with bombers as soon as you build it... It became so predictable that I'd build a shield, turn it off, build a fusion, then turn the shield back on.

      But in SupCom there were all the modded AIs which chose more interesting tactics, and you could enable cheating for any AI to give them a resource and difficulty boost.

      I think to be realistic, AI has to be segregated even more. You need an Advisor, which decides the direction things should be going. Do we need more resources? Do we have an urgent matter to deal with, like artillery pelting the base? The Advisor should just decide what to tackle, and then pass that on to the other AI subsystems. Like a player, the AI subsystems should take time to do stuff. An AI can't instantly decide what's an entrance to his base. He has to study where the units usually come from, and locate possible landing zones for air transports, etc.

      To ramp up the intelligence, you let it assign more issues to its subordinates more rapidly, and you let it learn across missions. Pretty soon the AI can tackle any frequently played map.

      • Re: (Score:3, Interesting)

        Thinking about it a bit more, I wonder how this compares to the AI used in hack n slash games where you get swarms of enemy's all over the place. I'm thinking of the Diablo I & II (and future III) series from Blizzard. I suspect these games use a similar idea in their monster AI.

        These games use fairly simple monster AI that usually follows simple rules, so it may be much simpler than what this guy claims. However I think it must be applied per creature. Some types of monster will run and cower when y
        • Re: (Score:3, Informative)

          by malkavian ( 9512 )

          Diablo series uses heuristics, pure and simple. Each unit has a set behaviour rule, with no adaptive whatsoever.

      • It was worse in Total Annihilation.

        I watched the AI once to see how it adjusted difficulty: speed.

        The fast AI could build units faster, move faster and collect more resources per second. It simply cheated.

        • by Nick Ives ( 317 )

          All strategy game AI does this. At least the Civilisation games have always been honest about it, they even tell you how much the AI cheats at various difficulty levels.

          At the higher difficulties the productions bonuses awarded to the AIs made military victory impossible. The only reason you'd want to play at such a high difficulty is to play the diplomatic game.

    • The problem is that in an RTS, you play as the "almighty all-seeing controller". If the computer AI can make decisions at a lower level, it's:
      1) Not emulating playing another human (not ideal)
      2) Keeping track of so much more than a human player can

      Like when you're playing Starcraft on the hardest difficulty, and the AI could use every unit's special power in the same instant-- I always yelled "cheater!" since a human couldn't possibly activate a half dozen different special powers on twenty different units

      • The problem is that in an RTS, you play as the "almighty all-seeing controller". If the computer AI can make decisions at a lower level, it's:
        1) Not emulating playing another human (not ideal)
        2) Keeping track of so much more than a human player can

        Like when you're playing Starcraft on the hardest difficulty, and the AI could use every unit's special power in the same instant-- I always yelled "cheater!" since a human couldn't possibly activate a half dozen different special powers on twenty different units in a single frame of animation.

        Why shouldn't the player's units be able to do the same thing? Most people don't WANT to micromanage RTS units.
        I'm sick and tired of telling infantry to move out the way of incoming tanks, and use special powers manually on individual units before they blow up seconds into a firefight.

  • Like to see.... (Score:5, Insightful)

    by Daemonax ( 1204296 ) on Wednesday June 03, 2009 @02:41AM (#28192809)
    I'm very open to talking about anything and everything to do with the design I used, as I think it's a viable new approach to AI to explore in games, and I'd like to see other developers potentially carry it even further."

    If you're serious about this, then release it under a Free software license.
    • by coaxial ( 28297 )

      If you're serious about this, then release it under a Free software license.

      Yeah, because the techniques are completely unreproducible. Ideas translate implementations. You just want a free game.

      • No I don't actually, I play computer games maybe once every 2 months at the most. You do also realize that when I say Free software, I mean Free as in freedom (what is commonly called Open Source)? As a nerd, and also a comp sci major, I would be more interested in the implementation details.
        He could also simply release the code as Free software, and have the artwork as something to purchase.
      • I'd prefer Free source to a "free" game, but either would be good. A vague description of an algorithm in a commercial game... urgh. Slow news day.
      • by PhilHibbs ( 4537 )

        You just want a free game.

        Given that it's an online game, with all the AI code implemented on the server side, even if he did release the source you would have to run the server side yourself, including providing your own data sets (maps, unit stats, graphics, etc.).

        • Re: (Score:2, Informative)

          by x4000 ( 1568105 )
          The game isn't online, it's client-server between players. The "host" is just another player.
    • by daeglin ( 570136 )

      If you're serious about this, then release it under a Free software license.

      I do not necessarily need the source code, but a technical description of the algorithms would be nice. I read most of TFA and it is quite shallow.

    • Re:Like to see.... (Score:5, Informative)

      by x4000 ( 1568105 ) on Wednesday June 03, 2009 @09:37AM (#28195657) Homepage
      I'm not going to release the game for free, given that if I'm to be able to continue to pursue game development it can't continue to be in my hobby time forever. For similar reasons, I'm not going to release the entire code as open source. However, I've already open-sourced a lot of smaller things from my code (force feedback code from my other game, fixed-int math from this game, etc). Also, I've now added a second part to the article which has some partial AI code from the game, and people are free to use the ideas there and build off of them as much as they want. I don't want people to make AI War clones, but rather to think about the ideas that I am presenting and implement them in their own way. The AI War code is not the only way to approach this general design philosophy, not by a long shot. Here's part 2 of the article, with the added code and such: Designing Emergent AI, Part 2: Queries and Code [blogspot.com]
      • Re: (Score:3, Insightful)

        by Daemonax ( 1204296 )
        I never suggested that you release it for free as in no cost, simply as Free software, which is often called by its more business friendly name of open source.
        If you don't want to do that though, that's your choice of course, you wrote the code. But if you wanted to see it implemented in other games, the easiest way would be to give access to the code under a Free license. Either way I don't care too much as I'm not much into computer games.
  • Not all that new (Score:5, Insightful)

    by The Optimizer ( 14168 ) on Wednesday June 03, 2009 @02:46AM (#28192829)

    I seem to remember most all of these things were in (or experimented with) the RTS games I worked on a decade ago - Age of Empires/Kings/Mythology (Decentralized Intelligence, Strategic Tiers, Sub-Commanders, etc). Not all of those were exposed to the end-user via the AI script / expert system / etc, and things improved with each iteration.

    I also remember that while some Ai things may have seemed like great ideas, and were neat to implement, they didn't always make for a better game experience.

    And I personally say you should make an economic AI that is bound by exactly the same rules as human players, and doesn't cheat at all. And as I remember, the definition of 'doesn't cheat at all' was an occasional ongoing discussion and subtle things that could be considered as cheating, like 'Can I Path from here to there?' or the reactions times of the computer vs a human sometimes had massive implementation ramifications.

    A good test in my book was 'can the AI handle a wide range of truly random maps / game worlds.

    Humans will always be finding the limits of Computer player AIs, and saying you'll just put in counter code whenever someone tells you of your AI's limits... Hmmm... I think that's weak.

    All this has been done before, and all this will be done again.

    All the above is solely my opinion and recollections, and in no way speaks for anyone but myself.

    • by Yvanhoe ( 564877 )
      I agree that the "do not cheat" is a good rule. However, having ten times mire resources for the AI is only cheating if it is hidden. If you have a starwars-esque setting where you are taking on the huge Empire with only a tenth of their resources, it can make for an interesting challenge.

      This gentleman says that his AI is often the goliath in a david vs goliath scenario. I suspect that this makes AI far easier : it doesn't care to waste some resources, its strategy is to be overwhelming...
      • Re: (Score:3, Insightful)

        by mcvos ( 645701 )

        I agree that the "do not cheat" is a good rule. However, having ten times mire resources for the AI is only cheating if it is hidden. If you have a starwars-esque setting where you are taking on the huge Empire with only a tenth of their resources, it can make for an interesting challenge.

        Rebels against the Empire is never going to be a flat playing field. The die-hard do-not-cheat/flat-playing-field position means you start out from the same position, with the same resources, the same information and the same options.

        Whether that makes for a fun game is a different matter. It does when the AI is really, really good. So usually it doesn't.

        This gentleman says that his AI is often the goliath in a david vs goliath scenario. I suspect that this makes AI far easier : it doesn't care to waste some resources, its strategy is to be overwhelming...

        Exactly. It's a different style of play compared to the flat playing-field duel. It's not a fair game anymore, so what counts as cheating and what's simply

    • AIs tend to sprawl, and are able to manage far too much at once.

      They need to organize better. Taking Supreme Commander as an example - player bases are usually orderly, but once the shields go down the whole thing goes down. AI bases are usually twice as big, and are packed with lvl 1 power gens. They're awful to move about in; units getting stuck everywhere... but the AI still manages to issue repair commands to everything, and keep 60 factories producing different units.

      An AI should be forced to act like

      • by The_Noid ( 28819 )

        That's part of why AI's are often no fun to play against, their strategy sucks, but their reaction time, and "clicks per second" are perfect. An AI in a FPS with hitscan weapons is impossible to beat, because it'll never, ever miss. An AI in a RTS can issue commands to hundreds of units at the same time.

        Until now this was not really a problem for RTS games, because the AI had no real strategy and could thus be outsmarted.

        A possible solution would be to limit the number of "clicks per second" that the AI can

    • by brkello ( 642429 )
      Uhh, why do you put higher expectations on AI then you do on yourself? If you learned all the basics of a game and reached a limit, someone better than you could let you know how to improve your game. You expect an AI to be perfect and be able to anticipate every strategy? That's great, show me a human that can do that first though.
  • Add some flaws. (Score:5, Informative)

    by apodyopsis ( 1048476 ) on Wednesday June 03, 2009 @03:11AM (#28192951)

    I'll ignore the shameless plug.

    Ever since I wrote my first connect 4 game in the 80s - and was totally thrashed by it, I never beat it - its been clear to me that the trick is to degrade a computer player in most circumstances to the level that it appears to have human flaws and play in a more human fashion.

    Of course this logic only goes so far and some games require a search space so vast or a completely different programming model that even now a computer cannot beat a competent real human (Go is an excellent example of this).

    The point is that it is easy to program a computer to win, the hard part is to program is lose convincingly.

    • Re: (Score:3, Insightful)

      by BenoitRen ( 998927 )

      You never beat your Connect 4 game? I used to play such a game on my dinosaur PC in the early 90s. The AI even had a name: Olivetti. It was perfect; it would always win.

      Unless you tricked it.

      You see, you have to counter his every move, and anticipate the last column that will be left. Eventually it'll be forced to put his chip in the last column, which allows you to win.

      • Re: (Score:3, Interesting)

        by apodyopsis ( 1048476 )

        Sadly not!

        I was ~12 and I had just understood looking ahead - so in my naivety I made something that was capable of looking ahead for pretty much the entire game.

        it annihilated me.

        Still it amused my family who mocked my pain as much as they could. Still, I was heartened to see that none of them could defeat Frankenconnect4 either.

      • Re:Add some flaws. (Score:4, Informative)

        by Anonymous Coward on Wednesday June 03, 2009 @03:44AM (#28193123)

        http://en.wikipedia.org/wiki/Solved_game

        Connect Four

                Solved first by James D. Allen (Oct 1, 1988), and independently by Victor Allis (Oct 16, 1988)[3]. First player can force a win. Strongly solved by John Tromp's 8-ply database[4][5] (Feb 22, 1995). Weakly solved for all boardsizes where width+height is at most 15[3] (Feb 18, 2006).

        Emphasis mine.

      • I found a way to beat the AI I wrote by forcing the AI to block then placing a piece on top of it for a double win. But my AI just weighted positions and didn't look ahead at all.
      • Wasn't there an episode of star trek where this happened, Data was playing a game against some guy who hated Riker. Data couldn't beat him but he could drag the game out indefinably. Connect 4 has a limited board but the game in ST was open ended
    • The point is that it is easy to program a computer to win, the hard part is to program is lose convincingly.

      Winning convincingly is pretty difficult too.

      Taking Left4Dead as an example; we were doing good against the bots. We got them all separated, and I'm about to pounce the last guy. Just before I land on Louis's head, he teleports over to an incap'd Zoey that's far away, and picks her up.

      Rest assured, the bots died - but stuff like that really takes away from either winning or losing. Imagine if Louis's teleporting act had saved his three friends, and they made their escape?

      (Note: This was an all-bot team. Som

    • by mcvos ( 645701 )

      Ever since I wrote my first connect 4 game in the 80s - and was totally thrashed by it, I never beat it - its been clear to me that the trick is to degrade a computer player in most circumstances to the level that it appears to have human flaws and play in a more human fashion.

      Only in simple, full information games. In complex strategy games, particularly turn-based ones, nobody has been able to design AI that can stand up to a good human player in a fair fight.

      Computers are really good at calculation and at doing lots of simple things fast, but they're absolutely awful when it comes to strategic thinking, which is why they're good at full-information games with a limited number of options per move (connect four, chess), and RTS games that are more about fast mouse control than a

  • by Anonymous Coward on Wednesday June 03, 2009 @03:37AM (#28193085)

    my background is in databases, financial modeling, etc. But it just so happens that database experience, which often involved distilling data points from multiple sources and then combining them into suggested decisions for executives which blew up the stock market.

  • The human brain is simply a pattern matching engine designed to find the most appropriate response in order to maximize survival.

    The average adult brain contains a huge database of experiences stored in a format that it is easily retrievable when signals arrive from the external triggers. When such a signal or signals appear on the brain, the brain does a pattern matching on the database, and produces an output. The output is a response or responses that are transmitted to the body so as that the entity rea

    • Re: (Score:1, Interesting)

      by Anonymous Coward

      So in your opinion the sum of all past, present and future innovation existed in the mind of the first human (or indeed ape, or even single-celled organism) who ever lived, and who apssed that knowledge down to his children?

      Your understanding of intelligence and reasoning is trivial, and trivially disproved. Humans do rely on a database of past experiecnes to avoid solving each problem from scratch, but the crucial difference between the human mind and a bot is the ability to solve new problems and create n

      • by master_p ( 608214 ) on Wednesday June 03, 2009 @08:03AM (#28194411)

        The human mind solves new problems and creates new solutions by applying pattern matching to the old problems and solutions. With pattern matching, the brain creates an analogy, which is expanded and turned into a new idea.

        For example:

        1) animals fear fire.
        2) animals bother me.
        3) I can use fire to keep animals away from me.

        From then one, the brain has the pattern of 'using one thing to achieve another thing'. This pattern can be used in a wide variety of situations, including formulating the idea of relativity. If you read the history of Physics, you will see many things discovered before Einstein published his works concerning the nature of the universe, light, electricity, gravity etc.

        And of course, you have to have in mind that Einstein had a problem to solve which motivated him. It's problem solving (i.e. experiences must maximize our survival) that leads to constructs like the brain.

    • Don't underestimate the difficulty of pattern matching
    • Re: (Score:3, Insightful)

      by psnyder ( 1326089 )

      The human brain is simply a pattern matching engine designed to find the most appropriate response in order to maximize survival.

      "simply"?! How can you not be in awe of such a machine? I counter your implied apathetic bias with my own bias of amazement. (^_^)

  • Master of Orion (Score:3, Informative)

    by Johnno74 ( 252399 ) on Wednesday June 03, 2009 @05:04AM (#28193469)

    I have yet to see anything that beats Master of Orion's AI

    But to be fair I've played very few strategy games in the last 10 years, so shoot me down if I'm talking out my arse :)

    In MOO the AI would recognise your tactics, and make moves specifically to counter them. You couldn't keep using a winning strategy.

    A good tactic early in the game was to build a large number (thousands) of tiny cheap ships loaded to the brim with MIRV missiles which would overwhelm the defences of the far larger, well equipped and expensive enemy ships.

    The AI would then counter by building a large number of small defensive ships, and equipping ships with ECM units, displacement devices etc which made missiles ineffective.

    Man that game was good. Perfect blend of simple gameplay and deep strategy. I've never played anything else as good, modern 4x space games all seem to be about micromanagement.

    • Re: (Score:2, Interesting)

      by Dopefish_1 ( 217994 )

      You're giving the game far too much credit. Master of Orion was a fantastic game (MOO2 even more so), but the AI was not its strong point.

      The main difficulty in the game came from the AI's massive advantage (read: cheating) in production. Or from map position (if you got unlucky and started somewhere without many good planets nearby, you're in trouble).

      MOO2 also suffered from poor AI, as well as several crash bugs. It also included deeper gameplay in many areas, and IMHO most significantly, multiplayer c

    • Comment removed based on user account deletion
    • by mcvos ( 645701 )

      I have yet to see anything that beats Master of Orion's AI

      But to be fair I've played very few strategy games in the last 10 years, so shoot me down if I'm talking out my arse :)

      In MOO the AI would recognise your tactics, and make moves specifically to counter them. You couldn't keep using a winning strategy.

      Are you talking about the original MoO? You could just steamroller right over them. Not much strategy required (though the battle system was very exploitable).

      Fun game, but I'm not impressed by the AI.

  • by petrus4 ( 213815 ) on Wednesday June 03, 2009 @05:10AM (#28193483) Homepage Journal

    ...then it is worthwhile remembering that centralisation was its' most fatal
    weakness.

    In the original story, (the end of the T2 novel, or thereabouts) Connor won by
    blowing up the central core under Cheyenne Mountain. SkyNET's primary
    exploitable weakness was that it was never willing to truly reproduce, for
    fear of losing control; that is, to create another AI with fully the same
    level of functional intelligence that it had. (I believe personally that a
    compelling case could be made for the assertion that SkyNET, as depicted, was
    not truly strong AI, but I digress)

    The point is that as far as creating genuinely effective weak artificial
    intelligence is concerned, the decentralised/segregationist approach is the
    correct one.

    Given my own experience with FPS mapping, I also concur with the author of TFA
    when he says that making AI choose the "best" choice 100% of the time, is
    not the best tactical approach, over time. My own experience gradually
    suggested that around 75% appears to be the magic number, as far as creating a
    truly emergent, unpredictable opponent that humans will be unable to overcome.

    Granted, said 75% is also only effective where there are a large number of
    divergent solutions to a given problem, each with close to an identical level
    of effectiveness, but with a few subtle points plus or minus, each way.

    Even with a fuzzy, emergent system, the best trees still have a maximum number of
    branches. The real trick however is not to hand code said trees at all,
    because then you simply end up with static, rote heuristics. Rather, as the
    author possibly implied, it is far better to attempt to code
    observation/deduction capabilities, guided by the above percentage, and let
    the system do the rest on its' own.

    I still remain extremely skeptical, however, that humanity will ever see the
    emergence of truly strong (human level or greater) AI. It is worth remembering that
    strong AI is a fundamentally and profoundly atheistic concept; the possibility of it more or less presumes a definitely atheistic universe as a prerequisite. For those of us who believe in the existence of God, (or at least the soul) the idea (at least
    in terms of non-biologically generated, acorporeal AI, a la SkyNET; AI derived
    biomechanically is a seperate concept) therefore has some fairly
    serious problems.

    • Re: (Score:3, Interesting)

      by mcvos ( 645701 )

      It is worth remembering that strong AI is a fundamentally and profoundly atheistic concept; the possibility of it more or less presumes a definitely atheistic universe as a prerequisite.

      Very interesting point, but I disagree. I disagree despite the fact that I'm a Christian and I don't see Strong AI as viable is the foreseeable future. I don't think there's a connection between those two beliefs. I think it is in theory possible to model absolutely everything on a computer, but I also think full human-level intelligence is too complex for us to grok completely for a long time to come.

      For those of us who believe in the existence of God, (or at least the soul)

      Well, what do you mean by a soul here? To me, our soul is not some magical spirit wholly seperate from our

    • Re: (Score:3, Interesting)

      by sznupi ( 719324 )

      ...
      I still remain extremely skeptical, however, that humanity will ever see the
      emergence of truly strong (human level or greater) AI. It is worth remembering that
      strong AI is a fundamentally and profoundly atheistic concept; the possibility of it more or less presumes a definitely atheistic universe as a prerequisite. For those of us who believe in the existence of God, (or at least the soul) the idea (at least
      in terms of non-biologically generated, acorporeal AI, a la SkyNET; AI derived
      biomechanically is a seperate concept) therefore has some fairly
      serious problems.

      The answer to this dilemma is a very simple one, IMHO.

      Namely, we have NO confirmed processes that would absolutelly require "supernatural" influence (no, there are no solid miracles - nobody ever survived decapitation, no human has grown back an amputated leg; things which people call miracles often originate, in medical examples, from misunderstanding of statistical probablities: natural mechanisms of your body can triumph over seemingly very bad ods, just like they can succumb to very minor dangers (why

    • For those of us who believe in the existence of God, (or at least the soul)

      Well, there's your problem! Take that away, and suddenly the universe starts to make a whole lot more sense.

      Not to mention your second problem, of course, being the manual insertion of carriage returns.

  • by Krneki ( 1192201 ) on Wednesday June 03, 2009 @05:49AM (#28193629)
    From my experience I'd award the best AI to Civilization.
    • by mcvos ( 645701 )

      From my experience I'd award the best AI to Civilization.

      Fortunately we have actually progressed quite a bit from there. Not nearly enough, though.

    • I hope not! There isn't a single Civ game which can challenge a human being without cheating. And it's for Civ-type games that I think the sort of AI regimentation described in the article could potentially do the most good. I'm really glad that we're reaching times where significant resources are being devoted to fundamentally improving game AI. Maybe in Civ 5, I can have an interesting struggle with an AI opponent who doesn't cheat. Right now we are miles from this, though.
      • by Krneki ( 1192201 )
        Good AI started with CIV 3 and the later patches applied to it.

        AI in CIV is always at it's best, difficulty levels only gives bonus to AI or human players. This is why AI cheats at higher levels and gets destroyed at lowers.

        Anyway, no one proposed any better AI then CIV. Still waiting.
        • Re: (Score:3, Interesting)

          Civilization is a turned-based strategy game, of course the AI is going to be "better" than any real-time games. It's got at least a few seconds to minutes to make it's decisions, while other games AI has to make decisions in the timeframe of one update command. And comparing AI from one game to another is really quite pointless and silly if you think about it, since each game has it's own set of rules. I mean I could argue that Deep Blue (the AI that defeated Kasparov, the world chess champion) hands d

  • by thepotoo ( 829391 ) <thepotoospam AT yahoo DOT com> on Wednesday June 03, 2009 @07:01AM (#28193973)

    This looks like a similar approach to one I have been thinking about for a while now.

    This type of layered control is very likely to be the future of all AI, not just that in games (I say this because there is some evidence that the human brain works in exactly this manner). I have a suggestion: let the thing fight itself. Begin with the same basic game, and rather than the randomness and fuzzy logic that you use (what does that mean? Can we see your algorithms?), use an artificial neural network for each unit, another for each "squad" (all nearby units, allows for flanking and such). Something with a few input nodes, a single hidden layer, and a similar number of output nodes should probably be all that's needed for the units, and the squad AI would only need a few more than that. This would likely be more computationally expensive, but it has one big advantage: it will learn.

    Begin with two full armies, each with their NNs randomly generated. Use an evolutionary algorithm, and have the winner fight the winner. Not only does this allow you to create a solid AI with minimal effort (see here [ieee.org]), but when you have your final AI, it will be able to adapt to a specific player's gameplay style (over the course of several games). Replay value is off the charts, development takes a bit more initial effort than what you have, but in the long run you'll get an AI that genuinely uses tactics just like a real human player. I'm not sure how this could be adapted to a commander AI that would dictate broader strategy (due to the complexity of the NN required, you'd probably need a monster computer to run it), but it would be the sort of thing to try.

    Also, this same approach would also work for strong AI, if we had any idea what sorts of NNs to create. RTS is a much simpler problem, and has a lot of applications (pathfinding, planning, coordination) to other types of AI.

    If I've entirely misunderstood what you're doing here, I'm apologize, but TFA had more pop culture references than technical details. Reply if you want me to clarify any points.

    • by nedlohs ( 1335013 ) on Wednesday June 03, 2009 @09:03AM (#28195173)

      NNs have the huge draw back that when you find a situation in which the AI does something completely ridiculous that ruins the game it's really hard to fix especially if you need to ship soon. Your small tweak will likely mess with some other situation. This is more likely in a video game than in a game like checkers since there's more factors at play (interaction with the path finding, etc).

      Backgammon is a better example than checkers. TD-Gammon not only plays the game very well, but changed the way people play the game. There were a number of situation where it played differently than the traditional expert recommendation of the best play, and it's play is now the one the experts use.

      Some games won't be so great at the "learning by playing against itself" NN approach. Anything in which getting stuck in a loop is reasonable will be problematic since the if the game doesn't end there's no result to learn from. In an RTS, this might be the case where you can build a defensive structure that is effectively impenetrable, neither one is going to win even though it could be the optimal strategy (if not losing is the goal, as opposed to winning).

      • Re: (Score:3, Interesting)

        by thepotoo ( 829391 )

        Evolutionary algorithms tied to your NNs (they're competing, remember?) seem like a good way to eliminate that problem. You can also use a separate NN for each function, such as path-finding, targeting, and cover, and use recombination to pull out the best NN for each from the population.

        The case you mention - you're stuck at a local maxima and can't reach the global one - can be overcome via the introduction of NNs which have evolved in a different environment: take an AI from one population and have it

      • In an RTS, this might be the case where you can build a defensive structure that is effectively impenetrable, neither one is going to win even though it could be the optimal strategy (if not losing is the goal, as opposed to winning).

        I would argue that, if this is possible, it is a game-rules problem, not an AI problem, and that an AI approach which would tend to reveal such problems where they exist would be useful for identifying such problems whether or not it was the best AI approach for a shipping prod

    • That linked article was amazing, not least because it was already ten years old. With the computation gains we have made since 1999, it's a crime that this sort of AI has not made it into commercial games.
    • Re: (Score:3, Informative)

      by x4000 ( 1568105 )
      This is a really interesting post, and some of it goes a little bit over my head. Like I've said, I'm a database programmer, not an AI programmer. I might experiment with things like neural networks and such in the future, but right now the AI is doing as well as I could possibly hope for. That was a big part of the point of my article: using the fancier techniques is not even always needed for something like an RTS game, because you can get surprisingly good results with comparably little code.

      I'm su
      • Re: (Score:3, Interesting)

        by thepotoo ( 829391 )

        The second article is much better, thank you.

        You're solution is indeed very fine for what you're doing, and uses a fraction of the computational resources that a NN solution would. If you're looking for a solution that is more adaptable (the NNs I proposed would learn what strategy you use, and find better and better ways of countering it, forcing you to constantly shift your strategy) and has broader applications in the AI world, NNs are clearly superior.

        I should probably have been a bit less technical in

        • Re: (Score:2, Informative)

          by x4000 ( 1568105 )
          Thanks for the added explanation -- and I'm glad you found the second article more interesting. It has only one audience (programmers), which makes it easier to write. The other perhaps has too many target audiences. Switching up the relative weights of the preferences, and having the AI retain information and learn over time, is quite interesting. Beyond the scope of what I can probably accomplish in this game simply because of data size issues and such in a networked game (unless the AI had a permanen
  • Not to nitpick but due to the failures of AI, not even AI programmers are AI programmers. At best they are expert systems programmers. Programming something that falls under the heading should make you part of the crowd. At least you have something to show for your work. There's plenty of folks with gray hair and a life dedicated to AI who have significantly less to show for it.

  • by Anonymous Coward

    ... the RTS-like game of Neuro Evolving Robotic Operatives [nerogame.org]. Instead of controlling your units directly, you had bots that you'd develop with a genetic alogrithm in a training mode. (And you'd train them by killing off "family-lines" of the bots that sucked, and using bots with interesting behavior as seeds for sucessive generations.) Then once trained, you'd give them a fairly general waypoint and they'd do the rest on their own. Which was a very cool concept, but in practice it would hang up the CPU/RAM on

  • I havent played it yet. But early reviews say the autonomous characters are pretty good.
  • Just a recap. Emergence is a different term for an metaphysical organization. The whole is more than the sum of its parts type train-of-thought. Brains create minds. When examining metaphysical systems these qualities cannot be proven to be either absent or present from and in our physical Universe. In the Ancient Greek definition of atoms (indivisible) quanta are the only real things. Everything else is abstract in a Zen manner. There is only dust. But we have experience that flows into our conciou

Don't tell me how hard you work. Tell me how much you get done. -- James J. Ling

Working...