Next Gen Beautiful But Brainless?

Next Generation has up a short piece discussing a Guardian Interview with AI developer Steve Grand. Grand opines that next-gen graphics are deepening the uncanny valley. More than just plastic looks and inhuman faces, the weakness of game AI is increasingly becoming glaring compared to the graphical prowess in games. "AI isn't so much unappreciated as nonexistent. Most of what counts as AI in the games industry is actually a bunch of 'if/then' statements. If a computer character doesn't learn something for itself then the programmer must have told it what to do, and anything that does exactly what it's told and nothing else is not intelligent. This is changing, and neural networks and other learning systems are beginning to creep in. But games programmers tend to devalue the phrase 'artificial intelligence."

When was the game AI good?

[jandrese]

There are always a handful of titles with good AIs, but over my years of playing many different games I can say with some certainty that the AI isn't getting any worse. In fact from what I've seen, the AI has been slowly but steadily improving over the years in general. It used to be in FPS games that the enemies always just walked straight at the player and shot. Nowadays they're likely to use cover, team tactics, and even a bit of misdirection. Sure it isn't as good as human players, but they're a lot better than the Doom or Wolfenstein AIs of old.

RTS AIs are a mixed bag, but in general they're doing more with less cheating than ever before. A lot of the old games cheated a LOT to make the AI competitive, but often now you'll find that they do a decent job with only minimal cheating.

Fighting games certainly aren't any easier than the ones of old, yet the AI seems to do fairly well. In some games it's almost punishingly good (Guilty Gear has some very hard AI opponents) and the player might even feel resentment over the computer's calculated reflexes.

Driving game AI hasn't improved much but frankly that's because there's not a lot to think about with driving games. Stuff like Mario Kart where there are powerups and whatnot can require a bit more smarts, but even then it's pretty simple. It's not hard to program a bot to drive around a circle. On the other hand, it's clear that in today's driving games the computer has to do a lot more work to make it around the corners. This isn't like F-Zero on the SNES where the computer completely cheated by setting its cars not to slide (in a game where controlling your sliding was 90% of the challenge).

Re:AI has never been important

[sesshomaru]

The purpose of AI isn't to make the game more difficult, though, it's to make the game more fun. I'll admit, it doesn't make sense to adapt AI techniques that will not make a game more fun.

Put it this way, have you ever had a conversation with a character in a PC RPG? Well, they don't have conversations do they? They just spit out a set of canned responses. Currently, part of AI research is the Turing Test [wikipedia.org] which is to create a machine that can fool a person having a conversation with it into believing that there is a real person there.

This isn't a win/lose scenario. The machine you are talking to may be an ally or a neutral character in a game. But it would make the game more interesting if the conversation you were having seemed realistic. [youtube.com]

There are other applications of AI as well. For example, they could add unpredictability to an enemy behaviour in a game. The enemy AI still wouldn't be the unbeatable uber player the machine would be, but you'd have to vary your tactics during a game to beat it. Yes, you are still "creating a loser," but a less predictable loser.

What's the point? Well, the point of playing the computer is to learn the nuances of the game. Obviously, there's no great sense of accomplishment in beating a computer. If computers follow a predictable pattern, you eventually plateau on the useful knowledge you can learn from them.

I concur.

[Heffenfeffer]

I agree wholeheartedly with this. I consider the ultimate quote about AI from one of Looking Glass's designers (yeah, he said it quite a ways back...unfortunately I'm paraphrasing a bit until I find the book where it was written): "Gamers don't want good soldiers. They want good babysitters. In Thief, we had guards patrolling around loudly saying how they can't find you. Now, we could have easily made the guards mercilessly hunt you down, but then it wouldn't be fun..."

This is also a big problem with AI people on your side as well. I just love how in just about every game with people following you, they manage to get stuck in corners or put themselves in front of you right when you fire the rocket launcher.

That's why over the past few years I've been playing more and more games that don't depend on AI, such as puzzle and rhythm-based games. Either that, or use other people to fill in for AI-based opponents/friends.

Re:Pre-programmed Learning System Invalid, Then?

[nuzak]

> First, a neural network is more of the same "if/else" logic as any other AI engine.

At the neuron level, sure, but AI is largely seen as a matter of the emergent properties -- behavior coming out of a system not specifically designed for it. Now you CAN get passable emergent AI out of triggers (passable for the limited scope of a game), and indeed that's what the real masters of game programming AI get paid the big bucks to do, but it's never going to get to "True" AI that people are demanding.

"True AI" always seems to be "whatever we can't do yet". If you analyze it too far, you might find out that WE don't have intelligence :)

Oh, and if you think there's an uncanny valley for visuals, imagine an AI soldier that has all his complex scripts replaced with an intelligence ... of a three-year-old.

Re:When was the game AI good?

[jtogel]

"Driving game AI hasn't improved much but frankly that's because there's not a lot to think about with driving games."

If you were right in the second part of your statement, everything I've been doing in the last two and a half years would be completely meaningless. As I don't want to have wasted these years, I prefer to think that you are not right.

There's a lot to do about driving game AI. First of all, learning to drive well on complicated tracks - without cheating - is not at all straightforward. Keeping the same performance when the user is allowed to create his own tracks is even harder - most racing games rely on knowing their prefabricated tracks well, tracks which are made from a set of standard segments in order to be tractable for the AI. When you introduce more than one car on the track it gets even trickier, as you have to deal with overtaking, collision avoidance, forcing collisions, etc.

And these are just the challenges associated with generating good driving. Interesting driving has even more challenges - should you drive nicely or aggressively? How do you make the driving look human-like? How do you adapt your skill level to that of your opponents? Etc...

You can see this blog post [blogspot.com] (with videos) and this paper [togelius.com] for some of the research we are doing into this.

Games don't "devalue" AI

[ZombieRoboNinja]

It's just dumb to say that games "devalue" AI in the mind of the public. In fact, I'd say game AI is the only medium wherein the public gets any real sense of AI as something intelligent - as a hypothetical "person" and a viable adversary.

The most obvious example is Deep Blue, which is probably still the most famous AI in the world. Nobody cares about the efficiency of its sorting algorithms or any other academic-level AI questions; what they care about is that it can match the world's best human in one particular game.

The same is true of the more mundane, even crappy AI you see in fighters, FPS games, etc. Those bots in Quake 3 probably weren't getting any invites to Robot MENSA, but they FELT almost as real and as dangerous as human adversaries.

Re:AI has never been important

[Chris Burke]

The computer knows exactly where you are, exactly what you are doing, and exactly where and when that rocket will blow up. The challenge is to make the computer ignore that enough of the time to convince you that its stupid. The bot does not "see" you, it's programmed to respond to your location only when you're within X of it.

While obviously "the computer" does know where you are, that information does not necessarily have to be given to the AI algorithm. Of course many times the information is given and the AI just selectively ignores it, yes. But it needn't be (and isn't in most games in the last few years as processor speed has gotten high enough) so simple as "within X", since computing visibility is a reasonably well solved problem. Making the AI not take into account the oracle knowledge of player location isn't really that hard. Heck, games as old as Doom did a decent job of making monsters react only when they would "see" you.

Game AI is currently an Artificial Stupidity problem, and will remain that way until we have bots that play via a video camera (or screen-scraper) pointing at a monitor and running the mouse itself.

No, it's artificial ignorance, because you're only limiting knowledge. And that's the easy part. The hard part is, given limited information, make a good choice, adapt to behavior by reacting in different ways. That's the artificial intelligence part, and it's the part that doesn't work well yet, only with good scripting.