What Would You Like to See from Game AI? 272
jtogel asks: "As someone working in new (bio-inspired) AI research with an eye to applications in games, but within an academic setting, I often hear that game developers are not incorporating cutting-edge academic AI into their projects because it's too "risky" (they can't really predict how gamers would react), and because they don't see the point in it. As a gamer, and as someone who cares what gamers think, I am often surprised by the sorry state of current commercial game AI - it has hardly moved since the 1980s. However, maybe the problem is that no-one really knows what we want from game AI. Academics keep coming up with innovative AI technologies, but what we should we use it for? What do you think? What sort of intelligent behavior would you like to see in games, but don't at present? Which are the most obvious intelligence deficiencies of current NPCs that need to be fixed?"
I'd like to see... (Score:2, Insightful)
... A CHALLENGE!
The only times I can recall game AI really impressing me was when I played Thief, Thief 2, System Shock 2 and Far Cry. Not all the games' AI have high 'wow factor' now but at the time they rocked.
Maybe games have to advance for AI to advance (Score:5, Insightful)
The developers of Red Steel for the new nintendo wii said that they upped the AI players combat skills, because the new controller allowed faster and more accurate aiming than a traditional controller. They're point was that game AI is usually braindead to make it reasonable to the players who are slightly hindered by an unnatural interface. It's common in video games for a character to stand without any cover at the end of a long hallway. This isn't because the programmers couldn't program the AI to look for cover. Game characters aren't often built to be tactical, because they'd creme the gamer. That's my take.
Smart not always smart (Score:3, Insightful)
RTS games (Score:3, Insightful)
So poor in fact, that on higher difficulty levels most of them resort to cheating in one way or another -- most commonly by upping the resource gathering/production rates (I've studied this by using cheat codes to show everything). Also, in many such games the AI plays 'perfectly' -- no mistakes as to when to develop which technologies, no problems controlling large numbers of units, and uncannily sending units just where I happened to be weakest for no reason (Age of Mythology seemed to be particularly bad at these sort of tricks). Having the computer cheat was no more fun than playing against a human who was using cheat codes, it ceases to be a battle of wits, which to me is what an RTS should be about.
A More Conceptual AI (Score:4, Insightful)
What I'd like to see is more AIs that are fed some concepts a priori, and then are able to manipulate those concepts in some way. Let me take a Civilization-type game as my example, since it is there I really wish I could see this.
I'd like to see an AI that has some concept of "launching an attack", beyond just massing troops and attacking in force. I'd like to see it know about "pincer", and "distraction", and other such concepts, and then use those to simplify its planning phases. Traditional AI techniques are still a long way from being fed the rules of Civ and deriving such things de novo, so I'd like to see some cheating, not with resources but by not starting almost from scratch with planning.
I'd like to see the computer have concepts of building a city vs. exploiting it, with corresponding "cheating" done in the computations, so the computer does a better job of building cities rather than just being handed resources to cheat. (Disclaimer: The last Civ game I played was Alpha Centauri, so maybe Civ 4 has addressed this, and cities actually get built; in AC it is not uncommon to take cities near the end of the game that have the AC equivalent of a Granary, and nothing else. However, I still bet human cities are still significantly better than computer-built cities. Feedback welcomed.)
I'd like extensive simulations to be run by the game author to adjust the weights of these concepts by playing tournaments. I'd like to see the AI guys have some time to actually refine the AI post-release because there's just no other way you're going to get a good, balanced AI.
While I've used Civ as an example, this generally extends to other genres reasonable well. In the FPS examples everyone is citing, I'm not sure about the exact concepts I'd choose, but what I'd like to see is the AI guys having time to load up some set of concepts and then firing a Genetic-Programming tournament at the concepts to see what happens, then iteratively refine the set of operators and concepts based on feedback from the results. (Most likely collapsing some obivously-useful trees into single nodes in some cases, breaking other concepts out, and adding new ones as needed.)
GP could be really interesting here because that is known to produce some interesting interactions with differentiated participants; you could evolve an entire squad with specialized members relatively easily, if your program nodes were rich enough.
Note: I'm not saying to run this on the client machine; GP techiniques would be inappropriate in general on a single, isolated client. On the other hand, for something like an XBox360 game played over live, that would be large enough to run a GP-based tournament against human players as "just another AI".
I'm not sure that game AI needs much more than more respect and more resources allocated to it so that you can do something other than The Simplest Thing That Could Possibly Work. The required ideas don't seem like they're that hard, it's just that they pretty much all involve having some time to work with them and not just slamming out code and shipping it.
stop these tactics (Score:2, Insightful)
1. Choke point: stupid AI's eventually run through a door, even if there are 20 of them and even if the last 5 guys to walk through the door are laying in a pile suffering from headshots. Can they figure out the pattern here?
2. Distract to higher firepower: you think the AI would wonder why the player is leading 10 enemies towards the gun turret? Probably not.
3. Shoot their legs: some of the slightly smarter AI will hide behind things, but usually leave a foot or hand sticking out. Sure, it takes 20 shots to kill them but they never seem to retract it.
4. Exploit routes: duh. Nearly every NPC follows a path until the player is noticed. Easy picking.
I'm sure there are many more of these, but it comes down to predictability, inability to learn, and inability to understand strong and weak positions within the level. One of my favorite game AI's is FarCry. Sure, they were still vounerable to the above tactics, but it would take a heck of a lot more coercing. Plus, NPCs would work together, always find cover, and try not to attack you from the front.
AI has been low priority for a decade (Score:3, Insightful)
And will continue to be low priority until the result of graphics and sound is indistinguishable from reality (another 5 to 10 years). Once all the eye- and ear-candy has been exhausted, then the game designers will have nothing left to do but enhance gameplay; one element of which is AI.
FPS and RTS games don't need highly sophisticated AI compared to RPG's. If developers wanted to (read: saw the business), sufficient AI from for FPS/RTS games could be achieved in 2-3 years.
An RPG needs AI capable of sustaining social interactions (at personal, econoomic, and political levels) between any 2 or more agents, in both speech and in writing. When a virtual population can sustain its society (then grow/adapt/react to stimuli) without the presence of players, then a true RPG is possible.
How cool would it be if you could walk through town in [insert fantasy franchise] and overhear the conversation between the butcher and the blacksmith's wife? Think of the ways quest hooks could be handled with such a mechanism. Your character is now the commander of legions, and it all started with eavesdropping in a tavern. Who hasn't played a D&D game that involved such a scenario?
(Psst... levels don't work at this scale... stop relying on them)
Eye candy sells games. Game play keeps the players interested. The more dynamic (and balanced) the game play, the better the game and the longer the player will (wait for it)... play. One player gets bored? Publisher just lost $10 per month. 10,000 players get pissed off because the mechanics get over-tweaked by a patch? Publisher lost $100,000 a month.
Artificial worlds need to feel self-sustaining (Score:5, Insightful)
But real AI has to involve some sort of learning, which is to say, letting game events "write" your behavior script. When would this be useful? The best example I can think of: Entirely stable environments that are "alive". Current games give you staged non-equilibrium situations that get triggered when your PC enters the scene. This sort of thing is just very obvious and unsatisfying if the goal is immersion. What good AI might do is this: before the game is released, the various separate settings might be populated with a bunch of artificial-life characters with specific motivations, needs, preferences, etc. (Maybe like the Sims, except more complex psychologically.) Then the game authors would let this initial system reach an equilibrium their big server. If they don't like the equilibrium that was produced, they tweak the initial AI and try again. Eventually, this will produce in a "natural" way something like a small, functioning village. When a PC enters the village, it will have been in an equilibrium which the actions of the PC will disrupt, almost certainly in unpredictable ways. That is how you give the player a true sense of freedom, like their actions really matter. Somebody like me might wonder: What would happen if I steathily killed the village miller, or gave him a gigantic horde of treasure, etc? That sort of scenario is impossible to play out in current games. And that sucks.
Now granted, writing Artificial Life that reaches an equilibrium similar to a real village, and still manages to react believably when a PC shows up may be a tall order, but I absolutely think it's a goal worth shooting for. For one thing, since many of the A-life interactions will happen in mutual isolation, the processing could be easily broken up into separate threads. Also, it's worth mentioning that this is not an all-or-nothing affair. If the equilibrium state produced at the end of several A-life generations is not exactly what you wanted, it's OK to slightly tweak the end result. The effect will still be much more convincing than the "village/dungeon/colony/factory eternally frozen in a moment until a PC triggers it."
One last bit: If you want to make AI characters seem realistic, maybe a good place to start is with Maslow's hierarchy of needs. Start there and build on that foundation. Everybody puts self-preservation ahead of other priorities, and so should AI. Ditto for all the other stuff on the hierarchy. So for example, if a fire I started destroys your hut, you will interrupt your routine to seek shelter, because this is your highest priority. For this, you may need to interact with other A-life, who might offer you a place to stay, financial help, or help with constructing a new hut - all for their own reasons, that depend on how much they like you, how likely they think you are to reciprocate, etc. If you saw me kill the miller, you will tell the other villagers, who may decide to ambush and capture you. How does a game produce that sort of behavior? Well, for one thing, planning requires some sort of awareness of expected consequences. But this should not be hard for a computer to do. It would guess that the PC would resist any attempt at capture, and it can (in the background) play out several "what if" scenarios compare their outcome to the goals of the villagers. This should show that a haphazard attack is a bad idea. Now it may look like I'm asking for a crazy amount of processing power. Maybe, but remember, we'll all have many CPU's to work with in the near future, so the ones that aren't running the game can be computing these "what if" scenarios. Also
Re:Turing (Score:5, Insightful)
Sure, NPCs should goof up now and again, but most of the time, they should at least be rational; they should always take steps not to die.
That means:
* No NPC should stand by idly as I charge toward it with weapons drawn.
* If I swiftly and easily kill all N-1 enemies in a group, the Nth one ought to get a clue and run away with its tail between its legs, beg for mercy or at least try a different strategy.
* No NPC should forget about me simply because I walk out of its view.
* NPCs should use teamwork.
Also, there should be variability among NPCs, even of the same type or class. For example, in "Halo," all Elites are the same, so once you figure out how to beat one, you'll be able to beat 'em all.
Watch the translation pitfalls (Score:5, Insightful)
The way things work in the real world is not nessesarily a good basis for a game.
Jonah HEX
Re:That's Not Quite What I Meant (Score:4, Insightful)
They do not necessarily need to learn from a specific set of players, but they can learn from what most players do against them. If Ragnoros is supposed to be a very powerful NPC, then it must have killed quite a few PCs along the way. That means he would know alot of the standard tactics, such as the standard Warriors aggro / Mages blast away / Healers heal.
I honestly do not understand how players in those MMORPGs can have fun doing the exact same thing over and over. If the NPCs would actually fight intelligently then PvE could actually be interesting.
--
Re:Maybe games have to advance for AI to advance (Score:4, Insightful)
You really don't want artificial intelligence. You want the game to behave in a way that seem plausably intelligent but are actually beatably stupid. It's much more exciting to be swarmed by 7 or 8 nameless mooks who die at the end of your sword than to spend 1/2 hour chasing down one guy who keeps hiding behind cover, shooting you from the back, and running away when injured.
Game AI isn't about AI any more than buildings in games are about livable architecture. AI is part of the illusion, but a small part. You have enemy groups that have goals, and feelings, and tendencies. And it's your job to kill them all. Or make them all like you. Or roll them up into a giant ball. Or what not. But they can't be too good at whatever it is they're trying to do, or the player's actions won't matter.
When AI is good, it takes center stage. It plays like it is the most important thing in the world, and to it... it is. But the player is what matters. And for the player to matter, he cannot generally be working against AI that is too powerful.
THAT HAVING BEEN SAID, it would be good to have better AI for NPC characters working with the player. NPC's that can figure out what the player's goals are. NPC's that can run through a level without bumping into freaking walls (Twenty years later and they STILL DO THAT!). They can't be too intelligent, or the player won't have anything to play, but they shouldn't be completely dumb either... An RTS where the player's commanders on the ground made tactical decisions based upon the enemy they were facing and the location they had been deployed to would be great. Imagine playing a game where you tactically deploy intelligent units, rather than micromanage the dumb shoot-and-runners we have now.
And for story-based games, it would be great to have more complex emotional simulators. Games like Oblivion or Final Fantasy fall down because simple human interactions are actually quite complex, and having characters that may care in heavily pre-scripted ways is a little dry. If you constantly take Tifa's materia and give it to Cloud, those two characters are eventually going to develop animosity. If character B keeps getting killed and character A keeps resurrecting them, a bond of either friendship or jealousy will form, depending on their internal states.
It would also be good to have some form of AI toolkit abstracted out. AI middleware, so to speak. I know they exist, but I also know they suck.
As a side note:
An AI research student came over to one of the companies that I had worked at. He was really excited to talk to the game AI programmer and find out what he did. "Do you use genetic algorithms? Adaptive data structures? Neural network pattern recognition?" The programmer looked over at him. "Uh... kid? We use timers."
Re:I don't know what I want to see (Score:1, Insightful)
I don't like "catch up" AIs in driving games either, but in a way it's more tolerable there than in a shooting game. If you do well in Max Payne, the AI gets lightning fast reaction and extremely good aim, and that just takes you right out of the game, especially when you consider that the enemiess are all supposed to be human beings.
If I see the enemy first, I want that to be a huge advantage. One level in Max Payne 2 starts out with an enemy nearby with his back turned to you. If you've done well up to this point, try zooming in on his head with your sniper rifle, enter bullet-time, pull the trigger... and watch the guy react and dodge the bullet immediately.
If they can't make games challenging without resorting to tactics like these, something is wrong. I don't know how to fix it myself, but I definitely know something's broken.
Just a very badly designed game (Score:3, Insightful)
Who on earth could have thought that including friendly fire was a smart move? Especially in a hack and slash. In a ranged combat game where you aim your weapon it is possible if you make sure no friendlies are about to make a headlong rush into your line of fire. But how do you stop yourselve from hitting a friendly in a melee when you can't control your swing and everyone dances about?
Please do note that this was a very real problem as well and massed melee combat was like walking into a grinder. The best armies were those who could control the amount of friendly stab. There is a reason all soldiers who fought side by side in thight formation did NOT wield large two handed swords desinged to be swung around.
No, this is very bad design. It is an attempt to introduce realism that is to real for the limited enviroment. If they wanted friendly fire they should have made sure you had far better control over who you hit. Yes those games where you can lob a firenuke at an enemy to fry him yet your mates inches away are unscathed are unrealistic. But they work and don't have endless rants on the net about how stupid it is when the guard that comes to your aid either buys the farm OR ends up attacking you because of an uncontrollable swing.
Bad Bethseda.
Re:That's Not Quite What I Meant (Score:4, Insightful)
Here's the trick. Balancing the encounter. You dismiss it in one sentence like it's easy, but it's by far the hardest part of the entire exercise; far harder than simply developing these ai heuristics you're suggesting.
These larger 40 player raid encounters have to be carfully balanced so that it's not too hard and not too easy and there's no silly 'ai exploits'. And it has to be fun. Trying to write a fancy ai algorithim that was properly balanced and fun would be a nightmare. There's all sorts of problems, including complaints from guilds who discover that Rag is harder for them then for some other guild because of some wierd ai learning code.
Ragnaros is the original end boss of WoW. That developers can't screw that encounter up. Scripting the fight is by far the most reliable for the developers to guarantee that the players have fun. Anything else is playing with fire.
Particularly obnoxious in sports titles (Score:3, Insightful)
The 2004-5 generation of EA sports titles was absolutely obnoxious with that trait. It came enabled by default, and made for countless vein-bulging moments as your NBA team, out ahead by 30 points in the fourth quarter, suddenly couldn't get a layup to go down. Meanwhile the other team's oafish third-string center is inexplicably draining deep three-pointers to close the gap. Not only was it frustrating, it just plain didn't look or feel like the game it was meant to imitate.
EA games have extreme play balance problems in maybe two of three years, partly because sports in general are so familiar that we expect pacing and so on to feel just so and when they tweak some lame thing to give us new features things get out-of-whack. The answer, though, is not to cheat the player. If your football title is routinely resulting in scores of 100 to 86, you need to fix something more fundamental.
Re:Turing (Score:2, Insightful)
The 'balance' in most games is artifical. Not actual balance, but perceived balance.
We tend to think of things as being fair or unfair in our lives and this reflects the balanced or unbalanced thinking in our games.
To make actually balanced games (which challenge our intellect and skills instead of our sense of fairness) a new approach must be made.
Unfortunately it will offend many peoples sense of 'fairness'.
With the millions of people playing I think actual balance would engender an impressive following fairly quickly of those of us who despise synthetic balance.
-ME®