'Neurotic' is Best RTS strategy 186
An anonymous reader writes "Austrian researchers experimenting with adding emotion to game AI say that 'neurotic' software is best at RTS. They developed aggressive, defensive, neutral and neurotic bots to play Age of Mythology, based on psychological models of emotion. Neurotic bots beat the standard game AI every time and faster than the other personalities."
Result is specific to AoM? (Score:5, Insightful)
This tells us more about the game-play balance in AoM than how to approach games in general. I'd be more interested in seeing these bots play CiV 4 where I doubt that neurotic behaviour would triumph.
Re:Result is specific to AoM? (Score:5, Insightful)
My guess is that the advantage is limited to games with "learning" AIs, where the AI attempts to extrapolate your behaviour based on your past events. The neuroticity adds an element of unpredictability which will confuse the hell out of an AI that works using extrapolation or neural net training. If the game has a rigid rule based AI there should be no advantage, just the opposite.
Re:Result is specific to AoM? (Score:5, Interesting)
Reading the article, (which is freaky low on detail) it seems more like "Neurotic" in this case is meant to signify a lack of caution. Aggressive won every match, and neurotic won every match, but neurotic did it faster. This suggests that irrational risk taking (the article mentions that the AI skews its internal numbers about how many resources it thinks it has) can beat a more cautious opponent.
In both cases it seems clear that aggression carried the day, and that the only real difference was that the AI that lacked caution won faster. To me, that suggests a big problem with the regular AI, because that lack of caution is usually pretty easy to exploit...A counterattack on a resource gathering operation would leave the crazy AI crippled, due to low reserves. The regular AI's counterattack algorithms must be pretty weak, or it's build order is too cautious or something.
I'd love to see a better description of the AI programming.
Re:Result is specific to AoM? (Score:4, Interesting)
I'd think that in a 3 person battle a neurotic AI would be at a great disadvantage because the style of "to hell with the consequenses, charge!" game play might win against 1 but not with a 3rd party. They'd jump in take advantage of the neurotic side when they had no reserves left and had spent themselves fighting the 2nd opponent.
Re: (Score:3, Funny)
Reminds me of the 40k Orc Codex: "We never lose... If we wins we win, if we dies we're dead so it don't count as beat and if we runz away we can come back to fight anuvva day" (Paraphrased of course - this is
Re: (Score:2)
Every so called "learning" AI I use that againist struggles with it
Re: (Score:2)
If the AI had the intelligence to create one or two construction bots to "disassemble" the wall, th
Re: (Score:2)
Re: (Score:3, Interesting)
Re: (Score:2)
Re: (Score:2)
Re: (Score:3, Informative)
Maybe it is a mistranslation. Though in that case, as an Austrian invented neurosis, it pretty much messes up psychiatry in the English speaking world.
Re: (Score:3, Insightful)
To me, that sounds about right for a game-winning AI. Most AIs seem nice and placid and just wait around for the players to attack, and then under-react to the attack.
-Jeff
Re: (Score:2)
Re: (Score:2)
I've played 4 hour AoK games...not so with AoM. Also AoM introduced rigidity into game play with TC positions. AoE III makes it even worse, being able to only build one castle... while the game play has de-evolved greately from an economic management stand point (which is was AoE/AoK always has been about). You could Ensemble has tried to make the game more approachable for people who can't devote time to master a more complex system, or to play 4 hour games... but it's
Re: (Score:2)
I would like to see someone write a better AI for AOE. It doesn't have as many artificial restrictions as AOM etc, so the AI needs to be a bit more flexible.
Re: (Score:2)
It doesn't necessarily mean there's anything wrong with defensive or regular AIs in general, as much as it shows that in these particu
Re: (Score:2)
"Learning" like a human? My first thought on reading the headline was how / if this could be used to make a decent poker AI. Unpredictable behavior, within certain parameters, is an advantage in many games where
Re: (Score:2)
Re: (Score:3, Interesting)
Having watched some amazing starcraft players, neurotic sounds about right.
Re: (Score:3, Insightful)
Re: (Score:3, Interesting)
Years ago I remember reading about a study which "proved" depressives were more cognitively accurate, by setting up a task which was fixed so that the subjects always failed. The depressives of course recognized this much more quickly than the normals.
However, that said I think there is still an interesting point here. The neurotic profile may exaggerate the situation, but at least it reacts to it, as opposed to inbuilt tendencies toward being aggressive or defensive all the time.
Re: (Score:2)
To the degree that the depressive tends to deny the potential for happiness, it is quite possible that his estimation of positive results is more accurate. On the other hand, I expect that his estimation of negative results is even more exaggerated than normal.
Re: (Score:2)
Welcome to Lords of the Realm 2! (Score:4, Interesting)
I discovered that a hardcore neurotic kind of strategy worked well in Lords of the Realm 2 when playing with my brother. He didn't care, and would rather have the game over quicker than not, so when we started the game he immediately spent all his resources on getting weapons and a huge army, and within four turns or so had come over and whooped my ass. Every single other aspect of his kingdom was in shambles, but he had the element of surprise, and that's all that ended up mattering.
I'm thinking the AI would think something similar to me... "Surely he won't try that. If he fails in his attack, he'll just fall over on his own accord in a few turns." Unless he doesn't.
Re:Welcome to Lords of the Realm 2! (Score:5, Funny)
Re: (Score:2)
Re: (Score:3, Funny)
Re: (Score:3, Informative)
I hate to tell you, but "Lords of the Realm 2" came out two years before "Starcraft," so i doubt there were very many Zerg rushing around at that point :)
Re: (Score:2)
When I was your age, we only had one RTS called Dune 2. It didn't even have a frickin' colon in it's name! We had to lay the frickin' concrete before we could build the goram tank plant and even THINK about havin' a rush of anythin'! And then, when you built yer unit cap of 10 whole tanks, a sandworm'd come along and eat 'em all before you got within shooting range. You youngsters've got it too easy, what with yer fancy-shmancy zerglings and no sandworms. Bah!
Re: (Score:2)
Perhaps you're so old that your memory is starting to go (47 by your math i guess) but you couldn't actually rush _anything_ in Dune 2. There was no way to select multiple units at one time, neither drag-select nor ctrl-select had been implemented yet. You had to click on a un
Re: (Score:3, Funny)
In my day, single clicking every unit and inching them forward one at a time WAS a tank rush. And another thing... super bats were the first "mobs," why I can remember one Wumpus hunt...
It was Dune 2, and not Wing Commander, that convinced me to by a Sound Blaster. Granted, Wing Commander made more use of it.
You're right of course, there was no rushing in Dune 2. But remember setting up a semi-circle of vehicles and baiting the bad guys in? Or laying out concrete all the way to the doorstep of your op
Re: (Score:2)
BTW, I found that one of the best strategies in the old Civilization games was to build horsemen/charioteers as fast as possible and raid other civs before they had a chance to start even at the expense of your own city growth. Only oceans got in the way of a quick win this way.
Re: (Score:2)
If you're willing to expend your entire kingdom (or empire, or corporation, or whatever) so that you can crush everyone else, have you really served as a good leader? What games force you to justify that expense?
Re: (Score:3, Interesting)
The difference is that games have an end, whilst short of global catastrophe, real life does not. If a group is successful to the point of eliminating all other groups, it will soon turn on itself because the values that brought it to that stage demand it. If, for example any particular human group you choose such as Christians, blacks, whites, whatever, successfully elimated all other groups on the planet, you'd soon see it split into new, struggling factions. Because objectively, there aren't any differe
Nothing new (Score:2)
Realworld examples (Score:2)
This may finally explain (Score:5, Funny)
addiction (Score:4, Interesting)
Well, sort of seriously, anyway.
The cultural tradition of women getting their way stems, in my opinion, from the cultural reinforcement of addictive tendencies in men. More specifically, addiction to sexuality. While the male sex drive is strong, cultural influences encourage even more slavery to this impulse, and further incline one to view a low sex drive (or even just a stoic level of self-control) as a lack of masculinity, or simply put, as weakness.
The end result is that men adopt a strongly sex-driven persona which in turn gives their women great control over thier behavior.
In other words, our notion of horny=manly sets us all up to become p-whiped.
The door swings both ways. Biology + cultural reinforcement inclines women (at least American women) to want romance (especially to be seen in public with a man who is showering affection on her). Learn to grant and withold that, and you can start getting your way too.
Re:addiction (Score:4, Insightful)
Makes sense (Score:3, Interesting)
Re:Makes sense (Score:5, Insightful)
If current RTS bots resemble their cousins from five or ten years ago (I haven't played in a while,) an emotionally-balanced bot would take a bold, successful strategy and "balance" all of the effectiveness out of it, leaving a milquetoast strategy that does no harm to his own civilization and usually no harm to the other guy's civilization, either.
Re:Makes sense (Score:4, Interesting)
Believe it or not, the old AI's in Age of Empires, with no sense of retreat, were harder to fight as they'd send their forces at you non-stop. The game was almost completely about whether you can build an army faster than the AI because the AI would not hesitate to send his entire army after you as soon as he developed it.
Re: (Score:2)
I just give up on it and watched computers play.
Re: (Score:3, Informative)
Hence why Koreans are so good at Starcraft.
Re: (Score:2)
Re: (Score:2)
*ponders* (Score:2, Funny)
faster is better? (Score:3, Interesting)
Faster is better now? Then why did they bother to code the defensive personality?
Re: (Score:2)
Re: (Score:2)
AoM AI (Score:4, Insightful)
Since Software is a reflection of its makers... (Score:3, Insightful)
i.e. would have Hitler been considered neurotic?
Re: (Score:2, Offtopic)
But who cares about some real-time strategy game? (Score:5, Interesting)
To get a meaningful result they'd need to test the different programs against experienced, intelligent human opposition. Or better, stop messing around with real-time strategy games and design AI for a game whose rules are already well-known. If a 'neurotic' or 'emotional' player program starts beating the 'purely logical' computer engines in chess, then I'll take notice. We know that the existing AI for chess is quite good (and there is a choice of several strong engines to test against) so any advance over that is likely to be genuine and not just exploiting obvious flaws in some existing program.
Re:But who cares about some real-time strategy gam (Score:2)
Re: (Score:2)
I'd imagine pitting the bots against one another in a game of Texas Hold 'Em would yield some good data about the bots' performance with respect to each other (ie. the neurotic one might take the first couple hands because of vigorous betting, but does his risky behavior over time bankrupt him? etc.)
But who cares about some real-time strategy game (Score:2)
Re:But who cares about some real-time strategy gam (Score:4, Interesting)
But thats just it. Chess allows only for the "Next Best Move". Playing an illogical move only results in the player playing it to loose because it puts them at a disadvantage and the logical computer simply knows the counter moves anyways for your worst move.
As in...
A logical AI assumes you'll play the next best possible move, but if you play the next possible worst move you are in a worse position and the AI simply knows the next best move and plays for that, but if you still keep playing the worst possible move you will only end up loosing faster.
In that regards, a logical chess program would be an AI or human who plays non-logically.
However, the reason why an RTS is important is because Chess is a limited game to a certain subset of rules that a computer can brute force all possible best moves.
However, in real world combat situations, there are no set definitions of strategies because you are simply allowed almost infinite possibilities of winning.
Lets say we take a human pilot or an AI pilot in actual Fighter combat in the skies (we'll see this scenario in the next 20 years) and pit them against each other in a real world situation. A logical AI would understand what the next best move is and the pilot will have an idea of what a logical AI would do.
However, the human pilot might do something crazy it knows it can throw off the AIs strategy like flowing into a nearby storm cloud or perhaps into a dangerous maneuver through a canyon or city landscape (under bridges and between buildings) which might throw the logical AI off.
After a while, a human pilot would have a general strategy with dealing with an AI that didn't adapt. He would know how an AI would react and be able to defeat it without too much effort.
Now a completely crazy AI would basically confuse the human and also other AIs who assuming the other AI was going to do in its next best move. Since in the real world (and in RTS) there are almost infinite combinations of what you can do in real combat, being unpredictable really helps win battles.
But like I said... Chess only has a limited set of moves. I would be an illogical AI would do far better at a game of Go than his logical counterpart.
Re:But who cares about some real-time strategy gam (Score:2)
While on the surface there fewer choices any minor thing has disproportionate influence on outcome(e.g.attacking 1 second after some tower upgrade).
Chess is completely deterministic:Thats why chess books exist.Computer that play chess,just calculate move with best score.They do not have any AI,just bunch of sorting algorithms for game tree.
Re: (Score:2)
And to think, at one time we thought that WAS AI.
crazy leaders? (Score:3, Interesting)
Re:crazy leaders? (Score:5, Insightful)
As opposed to todays political leaders who are all striking examples of stable minds?
Re: (Score:3, Funny)
I read this and the phrase "stable minds" led me in a straight line to "horse's ass."
I leave you, the reader, to see the pun-ic significance.
Re: (Score:2)
Re: (Score:2)
Like Alexander the Great, Julius Caesar, or Woody Allen...
Re: (Score:2)
Whenever a new bloodline gained power (Julius and Augustus Caesar, Galba), they were always competent or even brilliant people. Hardly neurotic. Then things go downhill from there.
Didn't I Just Blow Your Mind? (Score:5, Funny)
Ah... That explains a huge amount. (Score:2)
neurosis:
1. Also called psychoneurosis. a functional disorder in which feelings of anxiety, obsessional thoughts, compulsive acts, and physical complaints without objective evidence of disease, in various degrees and patterns, dominate the personality.
2. a relatively mild personality disorder typified by excessive anxiety or indecision and a degree of social or interpersonal maladjustment.
It pretty much explains virtually every rts game player I've ever met.
Out of the blue Obligatory (Score:4, Funny)
In other news... (Score:3, Funny)
Bad measures of AI (Score:4, Interesting)
The default AI in most games is terrible - even just writing a "do-random-stuff" AI would probably beat the in-game AI 20-50% of the time (provided you put in simple anti-suicide routines, like not using up all it's available funds etc.). Most AI in games relies on the fact that it knows everything that's going on (including exactly how long until their next unit is built, how many pixels you are away before it can fire on you, how much gold it will have by then etc.) and will generalise EVERYTHING (i.e. it'll be in "attack" or "defense", "hard" or "soft", "co-operative" or "go-it-alone"). Most games have a variety of "sliders" on the AI and the games-makers tweak them either randomly, in steps for each more difficult level or according to a pre-built AI "profile" (e.g. cautious but fast etc.).
In some games, that's more than enough to give anyone a challenge, at least until they are nearing the end of the game's useful lifetime. Snooker/pool games spring to mind. You won't beat a "top-level" AI on a snooker/pool game. It knows exactly where everything will go, even several "moves" in advance if necessary and can play a perfect game if required.
RTS's though, are much harder to simulate. Yes, there are a lot of factors involved in the creation, strength, durability, mobility etc. of units but at the end of the day it's a military tactics game. Pixel-perfect positioning of a nice ambush will keep the computer in an endless loop of "attack, run away, heal, attack, run away, heal".
I've not played AoM much, I'm an AoE2 fan personally, but the AI was amazingly easy to overwhelm with just a simple early-game rush, confuse with an impenetrable fortress hiding some long-range weapons and particularly predictable when it comes to individual AI tactics.
All AI's are predictable to a point in mass-market games - you can always "learn" to beat the AI in any particular game. Granted, it may be hard to do, it may be different to other similar games, but there's always some point at which you "know" what it's going to do.
It seems to me that, given that, an AI that is very "jittery" and over-compensates might beat the in-game AI in some games. However, on others, even in the same genre, it would get trounced. The "researchers" are assuming that the in-game AI is somehow a good approximation of a "neutral" player. They are also assuming that they have programmed each type of AI without any glaring logic holes in their tactics and that they are all equally matched in terms of capabilities. A cautious AI would win over a boisterous AI in only 50% of games.
More importantly, it's only a test of AI programming skill, not what "personalities" are trying to be reflected by the coders.
Re:Bad measures of AI (Score:4, Interesting)
However, I can say with great certainty it is not only possible to enact emotion in a cognitive system, but is being done right now. I'm doing it and developing real software systems employing it. The standard computer model of emotion in computing, called the OCC Model, is partly wrong. It misses what's really happening in humans. I've developed a more correct model that works very very well and probably matches the mechanism people use. I haven't published it. Why? Because some of my key competitors are Google and Microsoft. (Yes, Google's working on AI, shades of Skynet, eh?) Anyway, it is far easier to build systems that accurately have and express emotion that ones that can read human emotions. In other words, having and expressing (output) are easy enough, reading deep emotion in others (input) is much more difficult.
A few ending remarks. A lot of people are working on not much more than toy AI, and I've read some DoD-sponsored papers that are so far off base they are sad. I believe the correct approach combines both symbolic and analog AI (NNs) in a new way, and that we can create reasonable emulations, if not parallels, of human cognition. But they must come from a decent merging of psychology, sociology, and computing science. I've been working on the right path, a very productive one, charting a new course, and am writing what is currently a 5 volume book set I'd like to become the 'Knuth' of Synthetic Intelligence development. It should change the face of gaming and a few other things. Finally, I'm currently trying to emulate neuron-based systems in Erlang, by the way. Boy, is it parallel. I think that holds a lot of promise.
Genuine People Personalities! (Score:2)
Scientific basis for Sirius Cybernetics in Hitchhikers' Guide to the Galaxy?
is "psychology" what matters here? (Score:2, Interesting)
When it is clear I have no hope of winning... (Score:2)
Sadly, this made me smile and feel happy since 40 minutes before it was his move that made it certain I would not win.
hmm ... (Score:2)
Obligatory Hitchhikers refrence.... (Score:2)
Re: (Score:2, Troll)
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
I agree that some jargon just exists to make people feel special.
A lot of jargon exists to save time.
With regard to software, Patterns would be a good counter-example.
I've seen senior resources have very brief but concise conversations using patterns jargon.
"So I'll use a singleton for this and a factory object for that"
"sounds good."
The same conversation without the jargon would have taken much longer and been prone to miscommunication.
Re: (Score:2)
No, we don't cater to the lowest forms if life her (Score:5, Insightful)
Everytime you tell a story you have to set a certain limit where you just have to assume the person you are talking too understands your words. For instance, you just seem to assume that I know what an acronym is. That I get your use of the word "drift" what does your racing style have to do with slashdot editors?
This is slashdot, we do NOT explain words like RAM or CPU. If you don't understand those acronyms, you do not belong here. This is furthermore the game section of slashdot and Real Time Strategy is a well known genre of games. Do we have to explain FPS as well? (First Person Shooter) How about 3D?
At a certain point you just have to decide, allright my audience just knows this, and if they don't they are not my audience. If you don't, you end up like mainstream publications that have to dumb down everything to such an extent that EVERYONE feels insulted.
One of the more intresting approaches I have seen is/was (not sure if it still exists) is the dutch childerens news. It leaves out some stories but uses the extra time to more deeply explain the rest so that a person with limited world knowledge (like a kid or an american) can still follow what is happening in the world. You can also clearly see the problem there, they need a lot more time to cover the same event.
So unless you want slashdot stories to run several pages and be linked to hell to wikipedia, you are just going to have to use your own brain. This is the internet, the answer is only a few clicks away.
Re: (Score:2)
I had to think for second what RTS was, OTOH the GP obviously knows the meaning of "bot".
Re: (Score:2)
I agree though that if you need RAM defined for you then you probably won't get much out of the discussion.
Re: (Score:2)
Re:No, we don't cater to the lowest forms if life (Score:2)
LOL
"I have no idea what the hell RTS stands for" (Score:2)
Re: (Score:2)
Chicken chicken? (Score:2)
Chicken, chicken chicken chicken chicken. Chicken chicken Chicken, chicken chicken chicken CKN chickens Chicken Chicken Chicken. Chicken chicken, chicken chicken chicken, chicken chicken chickens chicken chicken chicken chicken. (Chicken chicken chickens [youtube.com], chicken.)
Chicken?
Re: (Score:2)
Re: (Score:2)
The Wikipedia article on Real Time Strategy games is the second result [google.com] when searching Google for "RTS."
There's nothing wrong with asking questions when you see a term you're unfamiliar with, but there's no need to complain that the summary didn't spell it out for you.
Re:Tautologous (Score:5, Funny)
Re: (Score:2)
http://en.wikipedia.org/wiki/Red_Dwarf_characters#Talkie_Toaster [wikipedia.org]
Re: (Score:2)
Re: (Score:2)
To make a long story short, I spent too much time debugging it and too lit
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)