Beta

Slashdot: News for Nerds

×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Next Gen Beautiful But Brainless?

Zonk posted more than 7 years ago | from the hard-to-love dept.

Games 131

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."

cancel ×

131 comments

The market will decide (1, Insightful)

yada21 (1042762) | more than 7 years ago | (#18814537)

If that's what people want, they'll buy it. If they don't the producer will try a different tack. That's how market's work.

Re:The market will decide (4, Insightful)

Pope (17780) | more than 7 years ago | (#18814619)

"The market" can't decide on something that it doesn't have a chance to buy in the first place, now does it?

Nothing's stupider than some pithy comment about "the market." The market is people, and people can be irrational about a lot of things. The invisible hand deserves a rap on the knuckles from time to time.

Re:The market will decide (4, Funny)

7Prime (871679) | more than 7 years ago | (#18814803)

Me thinks the invisible hand needs a shiny new pair of handcuffs, from time to time, to teach it to stop groping people.

Re:The market will decide (3, Insightful)

pureevilmatt (711216) | more than 7 years ago | (#18815661)

i'm a fan of free markets... getting things without having to buy them is quite rewarding.

Re:The market will decide (2, Insightful)

Reapman (740286) | more than 7 years ago | (#18816475)

If I'm reading this right, your basically saying that people have no choice, because all publishers value graphics over AI, so even if people did'nt care about graphics, only AI, it would'nt matter, because there's no developer out there, right?

If so people will vote with their dollars still. If NO developer meets what people want, then ALL developers will suffer, just look at the Video game crash in the 80s. Everyone (for the most part) produced crap, and the people responded by saying screw you guys.

Of course if I'm reading what you said wrong, then nevermind :)

Re:The market will decide (0)

Anonymous Coward | more than 7 years ago | (#18817065)

The market is people, and people can be irrational about a lot of things.

Absolutely.

The invisible hand deserves a rap on the knuckles from time to time.

The inherent flaw with that idea is that the only ones who can do that are governments, and governments (be it a monarchy or a democracy) are ALSO people, which can be irrational from time to time.

As individuals we can't opt out of government (law) the way we can out of markets... and that's the inherent flaw in non-capitalist polito-economics: the loss of freedom that is necessary to any sort of "rapping the market's knuckles".

Re:The market will decide (0)

Anonymous Coward | more than 7 years ago | (#18815131)

"If that's what people want, they'll buy it. If they don't the producer will try a different tack. That's how market's work."

Or, to extend the evolutionary/market model even more than you have, the producer goes extinct.

AI - non-existent (2, Insightful)

SQLGuru (980662) | more than 7 years ago | (#18814539)

The problem is that AI in general is "hard". Not just for games. We still don't understand well enough how our own intelligence behaves to model it successfully in games. As a programmer, I can model a process pretty easily. I can model objects fairly well. What I can't model is something that is nebulous and undefined.

Layne

Re:AI - non-existent (1)

User 956 (568564) | more than 7 years ago | (#18814737)

What I can't model is something that is nebulous and undefined.

You wouldn't happen to work for a government oversight agency, would you?

Re:AI - non-existent (4, Insightful)

twistedsymphony (956982) | more than 7 years ago | (#18814849)

With the already ridiculously high cost of development to bring graphics up to modern day standards for "bleeding edge" it's not like they have much time to develop a good system for something they can't show you a screenshot of. Spending the time to develop a real AI as you described doesn't really add much value to the game in terms of marketing.

Another reason AI isn't advancing is because modern games in addition to concentrating on graphics also concentrate heavily on multiplayer and online aspects. Sure the "AI" in an FPS or RTS might not be all that great but how good does it need to be? most people will just breeze through the solo missions in a few short hours and then spend the next 6 months to a year playing online where AI doesn't even factor into it. Once again, some solid multiplayer features are much more valuable use of development time then computer AI.

Honestly I see us moving to a point of being less depend on AI before AI actually gets better... it's just not a cost effective use of development.

Re:AI - non-existent (2, Insightful)

cosinezero (833532) | more than 7 years ago | (#18814949)

Arguably, many gamers would be perfectly happy playing a room full of AI players than have to deal with the garbage inherent in online play.

Re:AI - non-existent (1)

twistedsymphony (956982) | more than 7 years ago | (#18815155)

Arguably, many gamers would be perfectly happy playing a room full of AI players than have to deal with the garbage inherent in online play.
You'll get no argument from me, it's just that it seems the way games are moving more concentration is going to the online portion then the offline. Though when I do play online I only play against friends, very rarely do I play against random people that I've never met before.

Re:AI - non-existent (2, Informative)

Saige (53303) | more than 7 years ago | (#18815705)

Though when I do play online I only play against friends, very rarely do I play against random people that I've never met before.

It's a bit off topic here, but I think the key with online gaming is to merge these two where possible. I think that's one of the things that made Halo 2 so popular on Xbox Live - you could play WITH your friends as a team, and take that team against a team of strangers. And not just random people, but people of approximately the same skill level.

It's an incredibly fun way of doing it that blunts the annoyingness of asshats you meet online - since you're still on a team of friends, and you don't hear the other team much during the game.

Re:AI - non-existent (3, Insightful)

Tha_Big_Guy23 (603419) | more than 7 years ago | (#18815071)

most people will just breeze through the solo missions in a few short hours and then spend the next 6 months to a year playing online where AI doesn't even factor into it.
I can see where you're coming from. There have been, however, several games where the cooperative modes in the game were nearly as entertaining as the multiplayer modes. The first example that leaps to mind is Halo. Just because the "in" thing is 400-way multiplayer deathmatch, etc, doesn't mean that you shouldn't spend time creating a great AI for cooperative mode.

Imagine for a moment, you have a single player FPS. Now, take that FPS and add to it an outstanding AI. Then add in cooperative play for up to 8 players. Now, you have a game that you and your friends can play cooperatively, a computer that learns your tactics, and can develop new tactics on the fly. This to me seems so much more entertaining than fragging the same guys over and over again in a deathmatch. I'm pretty sure I'd buy it.

Re:AI - non-existent (1)

metamatic (202216) | more than 7 years ago | (#18817279)

Another reason AI isn't advancing is because modern games in addition to concentrating on graphics also concentrate heavily on multiplayer and online aspects. [...] most people will just breeze through the solo missions in a few short hours and then spend the next 6 months to a year playing online where AI doesn't even factor into it.

You seem to be conflating "online" with "PvP".

I believe that there's an enormous untapped market of people interested in social and cooperative gaming.

I've got 3 consoles with online capability, I've got broadband. I've hardly ever used the online features, because I have no interest in deathmatch lameness.

"/."AI - non-existent (0)

Anonymous Coward | more than 7 years ago | (#18814879)

"What I can't model is something that is nebulous and undefined."

Why are you trying to model slashdot?

Re:"/."AI - non-existent (1)

Jarjarthejedi (996957) | more than 7 years ago | (#18815181)

Psh, I could model /. any day of the week.

Editor Code:
If X days have passed since article A was posted, change summary and post as article B

Comment Code:
If keyword Windows or Microsoft found post comment flaming microsoft
If topic has nothing to do with computers post "Does it run Linux?" or "Think of a beowolf cluster..." comment
If topic can in any way be russian reversed do so
If topic names a specific group post "I for one..." comment
If topic sounds even remotely like an older topic post "Slashdot, home of dupes" comment

Repeat

Re:"/."AI - non-existent (1)

SQLGuru (980662) | more than 7 years ago | (#18815547)

You forgot random Troll posts (religious, political, sexual, etc.), Frosty Piss posts, and numerous other posts that have no relevance but need to be injected occassionaly in order to model the complete experience.

Other excluded memes: Comic book guy (Simpson quotes in general?), Profit!, etc.

Layne

Re:"/."AI - non-existent (2, Funny)

MBGMorden (803437) | more than 7 years ago | (#18816059)

You forgot "insensitive clod" you insensitive clod!

Game AI is hard, but not nebulous. (4, Informative)

MS-06FZ (832329) | more than 7 years ago | (#18815783)

Well, AI is not limited to what we'd classically think of as attempts to mimic thought. The term "Artificial Intelligence" also includes algorithms that solve problems that are merely difficult - things like combinatorial searches (A* and min/max searches, in particular) - and the general approach of attempting to model an AI character's actions based on their state and their goals, rather than going just for the desired effect of making them reasonably tough game opponents.

In the context of this discussion, "AI" means broadening the use of those algorithms (they are already necessary in some situations anyway) and in general producing game AI that's more capable - better able to deal with obstacles in the environment, predict player strategies and determine which of its strategies are most effective against the player. The goal being to create automated opponents which don't need to rely on unfair advantages (such as superior car performance in a racing game) to compete against human players.

In the context of, say, a mech combat game (as an example, racing games are a bit more of a static problem, and flight sims wouldn't require so much obstacle navigation), a capable AI would likely need the following:
- A predefined set of tactics. These would be designed by the people who create the game. The important thing would be that the tactics are effective and that the game AI has sufficient information about when each tactic is useful. Supplying this kind of "playbook" information decreases the demands on the AI program significantly: they no longer need to be able to synthesize these tactics, they can merely choose the right one.
- A system for selecting tactics to use: a good design would include considerations like the state of the AI's mech, the weapon being used against it, and general parameters of the enemy machine. (For instance, a good AI operating a sniper machine should know not to close to close range with a player machine that specializes in close combat... Likewise, if the AI's machine is running out of power, it shouldn't attempt an "overboost" move - unless it is clear that such a move could work sufficiently to win the fight.)
- An adequate navigation system for moving around in the environment. This must be tied in to the tactics being used - so that attempts to dodge a missile, for instance, aren't foiled by collision with an obstacle.
- An adaptive factor - a process that attempts to determine how effective various tactics have been against a particular opponent, and why certain tactics may have failed - so that tactics that are likely to fail again are disregarded.
- A random factor - the AI's next move is randomly selected from among the best candidates.

See, that's not so nebulous, is it? Pretty well-defined, I'd say. It's just, as you say, hard. It's hard to create a system that's dynamic and complex, it's hard to make sure you've got it right when you have created it - and the problem with game development is that there's so many other places that effort could be directed which aren't as easily dispensable as good AI. Most game AIs nowadays have a moderately good playbook (it's one of the easiest elements to add - humans know how to play the game and so they can record sequences the computer can repeat - so it's easy to add a small playbook - though providing good static information about how to choose a tactic from a larger playbook is harder), and a random factor is easy to introduce. Selecting tactics is often reduced to a static problem, and navigation is either made static, or solved by making the AI able to get through the environment in other ways, if necessary. (For instance, an AI that is always shooting and frequently moving forward - but gets caught behind a building - if the building is destroyed when the AI shoots, then moving forward no longer gets the AI stuck.) But navigation often is not tied in to the tactics and adaptive factors usually aren't adequately implemented in a way that makes a real difference.

Re:Game AI is hard, but not nebulous. (2, Insightful)

ClassMyAss (976281) | more than 7 years ago | (#18817541)

The term "Artificial Intelligence" also includes algorithms that solve problems that are merely difficult - things like combinatorial searches (A* and min/max searches, in particular) - and the general approach of attempting to model an AI character's actions based on their state and their goals, rather than going just for the desired effect of making them reasonably tough game opponents.

To call A* and finite state machines artificial intelligence is, in my opinion, an extreme twisting of the term; these things only fall under that label because early researchers were still under the delusion that they could hand-code an enormous tree of if statements and if they gave it enough feature-bloat it would seem intelligent. In my opinion, the simple algorithms used in today's "AI" engines should more be labelled pre-AI, as in useful procedures that incoming data might be preprocessed through before it's sent to something that actually does something smart with it.

In my opinion games are never going to push the bleeding edge of true AI, simply because to even model the inputs that (for instance) a group of five or six enemies should be taking in starts to tax the processor - to do it right one would need a separate render pass for each NPC, not to mention enough computational mayhem happening behind the scenes to figure out what to do with the data (yes, I'm aware that the second bit of this problem is entirely unsolved). And I somewhat doubt that even with infinite programming resources most companies would be willing to give up much if any precious processor time for something that doesn't have an immediate visual impact. Why waste time on a few thousand multiplications per frame per NPC so that you can have a decent neural network when you could use that time to push a thousand extra particles through the renderer, have even more realistic explosions, and hack together the AI just well enough using a finite state machine and some pathfinding to satisfy the average gamer? Not that I would even call a neural net AI - again, preprocessing! [Though this is less cut and dry than the simpler algorithms - the real issue here is that just about every application of neural networks involves feed-forward nets of some form, which aren't capable even in principle of learning on the fly. If someone figured out a way to train and use recurrent nets effectively, I might be persuaded to reexamine the issue, but to date I've never seen a practical architecture that even has the theoretical possibility of active learning.]

Re:Game AI is hard, but not nebulous. (2, Insightful)

MS-06FZ (832329) | more than 7 years ago | (#18817743)

The term "Artificial Intelligence" also includes algorithms that solve problems that are merely difficult - things like combinatorial searches (A* and min/max searches, in particular) - and the general approach of attempting to model an AI character's actions based on their state and their goals, rather than going just for the desired effect of making them reasonably tough game opponents.

To call A* and finite state machines artificial intelligence is, in my opinion, an extreme twisting of the term; these things only fall under that label because early researchers were still under the delusion that they could hand-code an enormous tree of if statements and if they gave it enough feature-bloat it would seem intelligent. In my opinion, the simple algorithms used in today's "AI" engines should more be labelled pre-AI, as in useful procedures that incoming data might be preprocessed through before it's sent to something that actually does something smart with it.

Yeah, I tend to agree. In my AI class at college we learned things like the "Customers who bought this also liked" algorithm, as well as the search tree stuff I mentioned. Like you, I don't think that stuff is a likely candidate for the problem of synthesizing an intelligent mind. But within the context of most games, AI just means the perception of intelligent strategy, within a very limited domain. It's easy to make an "AI" capable of piloting an Armored Core or driving on a small set of pre-defined tracks. It's harder if you also expect that AI to carry on a conversation. Being capable of behavior dynamic enough that it's able to compete with intelligent opponents is all that's really necessary - the complexity of that problem is determined by the complexity of the game.

As for learning - it can be done rather more simply. For instance, if an AI tactic in a Street Fighter game were to dragon-punch enemies jumping toward them - now suppose there's an aerial move the opponent can do that will defend against that attack and counter. Really, that knowledge should already be a part of the AI's play book: it should know that in cases where the opponent can do this move, it's not a good idea to do the dragon punch - so each time the attack is attempted and countered, the preferentiality assigned to that move is reduced for the duration of the match. It's a very simple type of "learning" - and the AI character certainly isn't "intelligent", it's just accumulating rudimentary data about what does and doesn't work, and using it. But nevertheless, the AI character is better at playing the game as a result.

Re:Game AI is hard, but not nebulous. (1)

ClassMyAss (976281) | more than 7 years ago | (#18818851)

Yeah, I tend to agree. In my AI class at college we learned things like the "Customers who bought this also liked" algorithm, as well as the search tree stuff I mentioned. Like you, I don't think that stuff is a likely candidate for the problem of synthesizing an intelligent mind.

Yup, that sounds about right. I was a math major in college, but I was very interested in AI, so I sat in for the first lecture (my school had a shopping period where you "sample" your classes before registering), and I ultimately decided that the state of the art was really not that advanced in AI and I didn't want to waste a slot on the class; nothing that we were to cover seemed very forward looking, and the syllabus just read like a hit list of fairly difficult classical problems to solve.

IMO, the problems with real AI actually are not necessarily rooted in the algorithms as much as the languages used to write them - to me it seems that we don't currently have a syntax that would let us write the kinds of algorithms strong AI would require. The crux of this problem is that we need a language that is flexible, error-tolerant, can manipulate procedural information (code is equivalent to data), is mostly syntax-free, and is transparent to code in. LISP comes close, but it's not error tolerant (some would argue that it's not transparent, either, though I'm not going to bite on that one) and this means that it's very difficult to set up evolutionary algorithms that can turn one useful behavior incrementally into another without passing through a region of parameter space where your code doesn't run at all. Neural nets, on the other hand, (which to some extent are full fledged interpreted programming languages, at least the time-dependent ones) have everything but transparency, so you can set them up, but they are difficult to train because we can't add by hand useful routines that we know beforehand the computer will need to solve the problem we want it to solve, nor can we pick out useful pieces of functionality and reuse them elsewhere, at least without extreme difficulty.

So I think that at least until a better programming language comes along, things are going to stagnate a bit on the hard-AI front. Not that I have a solution...if I did, I'd be coding it, not complaining about the current state of affairs!

Game AI is hard, but not moddable.. (0)

Anonymous Coward | more than 7 years ago | (#18817877)

Just to interject here. One of the things I like about the older games (some with released source code) is that it's easy to write one's own AI routines (some researchers do this. e.g. agent behaviour). I'm not certain how easy this is with later games, but I'd like that feature to be added into the modding catagory.

woot (-1, Offtopic)

Anonymous Coward | more than 7 years ago | (#18814593)

omg first post.

agreed! (2, Insightful)

butterflysrage (1066514) | more than 7 years ago | (#18814597)

I always get a little miffed when games use "AI" to describe what they do.

OTOH, I do see why true AI doesnt make much of a play in games... how long does the average bad guy live in a FPS anyway? If they learned from one guy to the next it would be more like a 'hive mind' then indviduals learning. For RTS games it could make a little more sence, since the "commanders" wouldnt be amung those slaughtered on the battlefield on each level. MMO's present a whole bucket of issues beyond the life span one... would they learn against EVEYONE or only their current PC opponents? if everyone, would it really be worth it as due to the MASSIVE diversity in player styles the AI would become muddied and non-specific.

Re:agreed! (1)

Turn-X Alphonse (789240) | more than 7 years ago | (#18814675)

what's wrong with a hive mind though? in games like Half life this is exactly what would fit. It would be extremely interesting to see how monsters would react to you if they had a hive mind. Would they rush you after a sniper area or would they figure the best idea is the snipe back? It could be very very interesting..

Re:agreed! (1)

butterflysrage (1066514) | more than 7 years ago | (#18814763)

oh it would work for some games... but the vast majority of FPS out right now either state, or imply that their opponents are indviduals (any WWII sim, Ghost Recon / Rainbow 6, Halos etc...)

Re:agreed! (2, Insightful)

Astarica (986098) | more than 7 years ago | (#18814755)

MMORPG AI has to be massively stupid. I know all the MMORPG talks about how much progress their AI has, but the fact is if you're a nearly omnipotent being with thousands years of expeirence plus an army of inexplicably powerful minions, it takes a lot of skills to actually lose to X ragtag adventurers. Just ask yourself, if you're controlling the guys you're fighting against in a MMORPG, would you possibly lose to your own party? The answer, hopefully, is no. But then this has to be the case because the opposition is usually has at least 10 times the raw firepower/stats compared to the player side, so if they actually had any brain, no player would ever win.

When people say AI, they really don't mean something that can beat them, because that's easy. They really want something that pretends it's doing something before ultimately losing. MMORPG fits this exactly.

Re:agreed! (1)

DreadSpoon (653424) | more than 7 years ago | (#18814937)

The answer of course then is to increase AI and decrease fire power.

A far, far weaker opponent can defeat an enemy if its clever enough.

The big problem with boss fights in MMOs is that they are one guy vs. a party, and pretty much rely on raw firepower, zerging, or number balancing to beat.

I've always been a fan of games like Zelda where defeating an enemy is not based on fire power (you don't generally get many "stat ups" in Zelda), or even that much on skill with a controller, but is instead based on figuring out a puzzle.

Unfortunately, that tends to reduce replayability.

The best "AI" I can think of for a game is not AI that controls the actions of monsters, but AI that builds the actual series of obstacles and puzzles. Then you can have games oriented towards thought and problem solving that is also highly replayable.

Of course, from an industry standpoint, that's not necessarily a good thing. It is better for the bottom line to simply make multiple games than to have one game that lasts for a long time.

Re:agreed! (1)

Astarica (986098) | more than 7 years ago | (#18815165)

That model is inherently impossible in a MMORPG. If you look at your standard fantasy lore, usually you'd expect 1 'hero' to defeat tens if not hundreds of 'minion' characters, which is why the evil boss has an army of those to try to slow/wear down his opposition. Further the evil boss, while powerful, is not insurmountable powerful compared to the heroes so that's why he might not be attacking with just himself + his army at the same time because it's possible to just take him out first while ignoring his mostly ineffective army of minions. This is how we get our model of 'fight everything and then fight the boss' as per your standard RPG.

But when you go to MMORPG, where if five minions wised up and decided to charge together, they can wipe out an army of heroes, this paradigm obviously falls apart. But due to the time requirements of MMORPG, it is not really possible to have the normal RPG power ratio because otherwise it'd be too easy to get to the boss. As long as MMORPG continues to stay with the scheme where even a minion of the bad guy needs an army to defeat, the AI must always be incredibly stupid for there to even be a chance that the player might triumph. If you look at a standard RPG, any enemy usually attacks a character completely at random, which isn't exactly smart. Yet this is infinitely smarter than any enemy in a MMORPG, who is inclined to attack the person who is least likely to die due to the aggro list concept.

A time and a place for AI (1)

pescadero (1074454) | more than 7 years ago | (#18815281)

Yes it's true that good AI does not belong in some games, and yes, that includes MMORPGs. The current formula for MMO boss fights (boss has predetermined behavior, adventurers need to execute predetermined strategy to kill him) is really popular and not in need of replacement.

However there are lots of games out there that would definitely benefit from better AI. So lets not discount the entire field just because it doesn't apply to one genre.

Artificial? Natural? (0)

Anonymous Coward | more than 7 years ago | (#18814627)

"But games programmers tend to devalue the phrase 'artificial intelligence.""

Kind of hard to have artificial intelligence when we don't even understand natural intelligence. Plus there's still the computational load issue.

AI has never been important (4, Insightful)

Astarica (986098) | more than 7 years ago | (#18814645)

You already have the suspend your sense of belief to really think that you will actually beat a computer in say a FPS where it can aim perfectly, or a fighting game where they can simply react to any move you might do. For example you can play the training mode in Soul Calibur and you'll quickly realize that the computer can guard counter every move you ever do forever, but of course they don't do that in the real game. Even on the super duper hard setting they give up after a while, even though they can do it forever on the training mode. Shin Akuma in various Street Fighter incarnations counters almost every move perfectly. You throw a fireball, he'll jump kick you. You jump kick him, he'll dragon punch, and the only way to beat him is hit him with moves that he isn't programmed to counter. There's no reason why the computer can't play like that aside from it'd make a very boring game when you repeatedly get owned by a computer.

If by being smart means 'better at a game' the AI is already a super genius. If by smart means 'flailing your hands around while pretending to do something before losing to a human player', then whatever that creates the best sense of illusion works the best. If it's a bunch of if/else statements, why not? There's no reason any fancy technique will get you a fancier loser.

Re:AI has never been important (1)

LordNimon (85072) | more than 7 years ago | (#18815033)

For example you can play the training mode in Soul Calibur and you'll quickly realize that the computer can guard counter every move you ever do forever,

That's not really AI, though. If you're playing a computer opponent, then the AI behind that opponent is supposed to simulate the behavior of that opponent. The real behavior of that opponent is how it would act in real life. If I'm playing an FPS against AI-controlled people with machine guns, then the AI's job is to make the virtual characters behave as closely as possible to real people with machine guns. Real people with machine guns can't always hit their target within 1 second of spotting it. So the AI has to simulate the imprecise aiming and reaction of real people. If the computer just aims the gun at the mathematically exact direction and fires a bullet immediately, then it's not an AI.

Re:AI has never been important (4, Interesting)

sesshomaru (173381) | more than 7 years ago | (#18815079)

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.

Re:AI has never been important (2, Informative)

isaac (2852) | more than 7 years ago | (#18815149)

AI sounds better than "Artificial Stupidity" but I think you're missing the point.

The goal isn't "create better losers," it's "create characters whose actions are lifelike." In the problem domain you specify (FPS and beat-em-ups), this can mean (among many other things) having computer players with a limited "view" of the game space, the ability to learn, and the ability to initiate actions that aren't directly coupled to the human player's inputs. This isn't easy even in such a limited (read: boring) problem space.

Now, get into RPGs and the like where language and manipulation of abstract concepts are important and you're really into the domain of difficult problems. We're still in an era where "if you bring item X to NPC Y and you've equipped Z then NPC Y smiles and gives you item ß" is hardcoded. Not all games are about shooting or beating up the computer player.

-Isaac

Re:AI has never been important (4, Informative)

Chris Burke (6130) | more than 7 years ago | (#18815369)

You already have the suspend your sense of belief to really think that you will actually beat a computer in say a FPS where it can aim perfectly, or a fighting game where they can simply react to any move you might do. For example you can play the training mode in Soul Calibur and you'll quickly realize that the computer can guard counter every move you ever do forever, but of course they don't do that in the real game. Even on the super duper hard setting they give up after a while, even though they can do it forever on the training mode. Shin Akuma in various Street Fighter incarnations counters almost every move perfectly.

That's absolutely true, but is in some ways dependent on the game. In a fighting game, you can always see what your opponent is doing, so if you had perfect reaction time you could counter every move. In this type of a game, a computer could theoretically play "perfectly" and never lose.

In an FPS, this is not necessarily the case. Bots that can aim perfectly are quite potent, to be sure, but sometimes being smart can be just as important to actually winning. For example, if the AI bot has a predictible pattern through the map (as most bots I've played against do), then when you know where the bot's pathing takes them you can have fired a rocket at where they are going to be so it smacks into their feet right as they round the corner. Unless the bot "cheats", and sees your rocket through the wall, it won't be able to avoid it nor will it be able to retaliate because you've moved around the next corner already to line up your next ambush shot. An actual AI that attempted to learn your patterns, and change its own pattterns when it realizes that you've discovered them, would be a truly deadly opponent.

This is where the difference between algorithmic precision and speed vs actual intelligence becomes obvious. Parts of the game that require fast reflexes and precise aiming are where the computer dominates. Parts of the game that require strategy are where the computer lags severely. One can compensate for the other to various degrees depending on the game. Look at chess. Simply by examining as much of the tree of potential moves as possible it can beat a human player even though it has none of the strategy or intuition that makes the human player good. And ridiculously powerful computers can only just barely compete with the top human players by using the massive computation model.

But that's only talking about victory. To make an immersive experience, AI could do a much better job than if/else statements, at least in theory. An enemy character that reacted to your actions in a believable way would be much more immersive than one that only responds to a couple specific stimuli and has only a couple scripted strategies. A lot of FPS AIs I would call blatantly retarded and completely wooden and predictable, and that takes you out of the game regardless of whether you give the AI unnaturally perfect aim or not.

On the other hand, I'm realistic, and AI that really behaves in a believable way without scripting is a long way off. For now, if/else is the most bang for the buck. I'm just saying good AI could make for a much better gaming experience, and much better opponents, ones that are truly vexing to beat without having to make use of perfect aiming/reaction times. And it wouldn't feel as cheap as Akuma to boot.

Re:AI has never been important (1)

Astarica (986098) | more than 7 years ago | (#18818371)

Just what is a 'believable' reaction in most games? If you take a fighting game, where the computer and I start off with character of roughly equal strength (ignore bosses), it would be believable to have the AI act slightly below the average human (after all I, an average human, am expected to win eventually) on the normal level of gameplay. It'd be believable that the AI acts slightly above human on the hard settings. This works for FPS where you and the enemy are of equal strength too.

But let's say you're in some kind of standard one against the world FPS, what is a believable reaction on the AI? If they reacted even barely intelligently, the player would be dead because the average player is not a super gamer able to overcome odds of 10X or even 100X of his firepower. The AI must act in a way that, despite having 10X or 100X the firepower of the player, still allows them to be defeated by the average player. This means it must act in a very stupid way.

The worse the odds of player versus computer, the dumber the computer necessarily has to become for there to even be a chance for the player winning. Like I mentioned elsewhere, in a MMORPG the computer AI is necessarily dumber than even random, because if the computer just randomly attacks whoever, as they do in a typical RPG, you'd never be able to win due to the sheer power disparity. Indeed the computer AI is usually maximized on stupidity in a MMORPG by focusing on the hardest guy to kill. MMORPG features some of the crazinest power disparity between player and the computer, and it is not surprising that the MMORPG AI basically actively tries to lose to the player, because otherwise no one could ever win.

The general problem, then, is that there are far more games that feature you against insurmountable odds as opposed to games that give you 50/50 odds, so AI necessarily has to be dumb in general. It'd actually be pretty cool, I think, if you have a game where you as the player have a raw power advantage, but the computer is allowed to do really clever things to try to beat you.

Re:AI has never been important (1)

Qzukk (229616) | more than 7 years ago | (#18818583)

Unless the bot "cheats"

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. Likewise, it knows exactly where and when to shoot in order to hit you, it's programmed to miss Y% of the time. Not just FPSes, the computer in Starcraft knows exactly where your base is and how many units you have defending it. It also knows how much damage each unit does and how much damage each can take and assign attackers to units appropriately.

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.

I concur. (2, Interesting)

Heffenfeffer (888559) | more than 7 years ago | (#18815467)

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:AI has never been important (1)

rarel (697734) | more than 7 years ago | (#18815725)

"If by smart means 'flailing your hands around while pretending to do something before losing to a human player', then whatever that creates the best sense of illusion works the best." /quote

I read here not long ago there's a agme that does just that explicitly, I think it was _Galactic Civilizations_ or something similar. Basically during training, it sends you a message saying "I see you're building up an army to invade my/your allies but I'll pretend not to notice until you launch an attack"

Wicked! :) I'm not too fond of RTS but I might get that one.

Re:AI has never been important (0)

Anonymous Coward | more than 7 years ago | (#18815765)

I believe that the real power of AI in video games comes into play in supporting the player's gameplay style and creating a better experience.

One example would be the use of an AI system to provide better team mates for a player; teammates who can learn what the play style of a player is and adapt to it (e.g. the player prefers stealth over direct encouters, so NPC's helping the character will not rush into combat but hang back and try to remain undetected). It can also be used to create worlds which are more dynamic than the ones currently being offered in games. Oblivion has a very nice setting, but even with the Radiant AI, it is still a pretty static environment. There will never be an overthrow in any of the guild, towns will remain the same through out the game session, etc.

Another examples is to have the game create the story around the player. For example, there is a system to which you can give plot points and it will try to keep the player within the story arc while still allowing them to explore the world in a manner of their choosing (e.g. the story requires that a player hear a conversation between two players at a certain location, but the player never goes there. The computer detects this and either nudges the player in the correct direction by hints or moves the characters to an area which the player frequents).

You are right, when it comes to winning computers have the advantage hands down, but creating cool opponents is just one of the things that they can do.

Re:AI has never been important (1)

tnk1 (899206) | more than 7 years ago | (#18816483)

Well, the computer can beat the crap out of you in terms of reflexes. This is basically due to the fact that the computer is not just your opponent, but it is the very generator of the game world you are in. It is also given certain information you will never have. It knows your moves before you can execute them, because in order to execute them, the computer has to know them. The opponent program does not have to be given this information, but frequently the programmers do grant this information so as to avoid having to actually have the computer look at what you are doing and make a decision. This is called "cheating" generally, because your computer opponent did not acquire the information in a way you could have.

Still, for the computer to execute those moves and to make use of what it knows, it has to know that the counters exist and when to actually make the counters. For a fighting game, with relatively few possibilities and generally an unobstructed movement area, this is fairly easy for a computer to master. But consider a game like a MMO where you have obstructions all over the ground and multiple classes with different and varied abilities. Then, your NPC may execute his abilities rapidly and flawlessly, but it doesn't matter, because it can't predict every move that can be made against it. The programmers can't actually program those NPCs with enough static logic to deal with every possible situation. That is where AI would come in. Without AI, the mobs are still dangerous if you fight them straight up, but if you change the rules on them, they can't cope with it and their rigid logic can be exploited so much that their defeat is trivial.

Re:AI has never been important (1)

DigitalCrackPipe (626884) | more than 7 years ago | (#18817413)

The term AI is hijacked quite often. The field of AI involves much more than just autonomous computer actions. The failure of AI in video games is not a matter of it being not useful here, it's a matter of not being used properly - or at all.

can simply react to any move you might do
An appropriately designed AI character would react to what the caracter would see (and how that character would respond to the input) rather than just reacting directly to the keyboard. Some games over the years have exibited good AI by, for example, having the NPCs learn from player actions (so you can't pull the same trick repeatedly - they learn and react). I suggest that good AI in games is not about beating you more soundly, it is about enhancing the experience of interacting with non-human entities in the game.

Re:AI has never been important (1)

Astarica (986098) | more than 7 years ago | (#18818207)

So instead of detecting that you did the D DF F + punch combination for a fireball, what do you propose the computer to do? Detect the frame rate animation? Again there's no reason why a computer can't tell on the first frame that you're about to do a fireball and counter appropriately. Do you give the computer 5 frames before it can determine what move you just used? 10? 50? Some really good players in fighting games can react with a few frames of whatever move you choose to do. Are those players cheating? No, we say those guys have great reflexes. So why is the computer cheating if it is quite capable of discerning what move you're about to do in the first frame?

Again when you say some computer can 'learn' from what you do you're just saying it's a fancier way of losing. A human player deduces that someone is about to do a fireball by a combination of visual and audio cues. In the computer case, even without knowing your input, it can certainly discern what move is used in fewer frames than a player can. There is no need for the computer to 'learn' when it is quite capable of countering your moves as it sees them due to its incredible reflexes.

If a computer is supposed to 'learn', it should be able to execute any combo of arbitrary difficulty that has ever been used by its opponents, since there is obviously no way the computer will screw up its timing. How exciting would it be to play a fighting game and get hit by the best combos in the game every time without fail? And yet how is that any different from you trying to learn someone else's combo? Unless you're one of the top fighting games players, we all learn our moves and combos by watching/copying someone better than us. But in the human case it's intelligence because it takes a while to copy something effectively, but in the case of computer it's cheating because they can do it correctly on first try?

Re:AI has never been important (1)

Jim Hall (2985) | more than 7 years ago | (#18818101)

Shin Akuma in various Street Fighter incarnations counters almost every move perfectly. You throw a fireball, he'll jump kick you. You jump kick him, he'll dragon punch, and the only way to beat him is hit him with moves that he isn't programmed to counter. There's no reason why the computer can't play like that aside from it'd make a very boring game when you repeatedly get owned by a computer.

That sounds similar to Kya: Dark Lineage (PS2). It had a neat feature where your enemies would "learn" your hand-to-hand combat moves the more you used them, and over time the bad guys would get better at blocking your attacks. The only way to be effective in the game was to continually learn and use new fighting moves (and to use a variety of moves, not just the same old attack.) I thought it made for a much more interesting game. I'd love to see more of that in games today.

Unfortunately, Kya didn't sell well. It was a multi-layered game, but it didn't resonate with a lot of gamers at the time.

Re:AI has never been important (1)

Astarica (986098) | more than 7 years ago | (#18818587)

But ultimately that's just a fancy way of losing. The computer does not need to 'learn' how to counter your moves because it already knows how to. When I play Street Fighter against someone with better reflexes I don't call them a cheater just because they have better reflexes. Almost everything Shin Akuma does is solid fundamental fighting game stuff. You should always dragon punch when someone is airborne. We just can't do it 100% correct like Shin Akuma does.

I saw a Street Fighter 3 movie where a guy parried a 10 hit Super Arts, and that guy is considered one of the best fighting game players. A computer can easily replicate the same feat, and now it's cheating? Would it be fair for computer to use this after X hours of gameplay to pretend it's been learning something it always know how to do?

I guess ultimately it's really just a matter of perception. The best AI would be the one that can best convince the human player that it really is playing with the same rules as we do, and that it has the same reflexes as we do, even though clearly it does not. As long as superior reflexes can overpower strategy, which is true in many types of games, the computer doesn't even need to learn anything if its goal is merely to beat the human player.

When was the game AI good? (4, Interesting)

jandrese (485) | more than 7 years ago | (#18814651)

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:When was the game AI good? (1)

happyemoticon (543015) | more than 7 years ago | (#18815139)

F-Zero AI cars also teleport directly behind you at fairly regular intervals. Just play the 1vs1AI mode (whatever it's called) and watch the enemy's blip on the map.

Re:When was the game AI good? (1)

kannibal_klown (531544) | more than 7 years ago | (#18815871)

NFS: Most Wanted still has this. You can be blowing the AI opposition away, then miraculously they'll fly across the map and be on your rear bumper.

I guess the AI has a hidden button to unleash the hidden Kryptonian hampster wheels under the hood.

Re:When was the game AI good? (1)

AKAImBatman (238306) | more than 7 years ago | (#18815801)

When was game AI good? I'll tell you when.

The Reaper Bot [mindspring.com]

I remember playing that thing when it first came out, and thinking to myself that we were on the verge of some major game AI breakthroughs. I mean, this thing played like a HUMAN, not a robot! You had to beat it with skill and cunning rather than the typical, "find the flaw in the bot and exploit it" scheme.

Of course, the Reaper wasn't perfect. Which isn't surprising when you consider that it was the first of its generation. Unfortunately, the industry pushed in two directions that were mostly incompatible with the further development of such AI:

1. Scripting - The introduction of Half Life kicked off a scripting craze that we still feel today.

2. Online Play - Quakeworld sealed this deal.

We could develop better AI if programmers put their minds to it. The problem-space of simulating how humans are supposed to react in a simulated environment isn't anywhere near as hard as trying to respond to real-world stimuli. (Especially since the AI can use shortcuts and cheats behind the scenes.) Unfortunately, there is little incentive to focus on such AI. So it may take a very long time before we see any real improvements in that area.

Re:When was the game AI good? (1)

penp (1072374) | more than 7 years ago | (#18817821)

Isn't it a bit ironic that you're trying to point out an example of "good" AI when the link you provide picks apart the reaper bot and shows that most of its "AI" was really just cheating?

Still, an interesting read.

Re:When was the game AI good? (3, Interesting)

jtogel (840879) | more than 7 years ago | (#18816309)

"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.

Hence Microsoft's Next-Gen Business Plan: (-1, Flamebait)

Anonymous Coward | more than 7 years ago | (#18814709)

Sell a bunch of games that are only good for playing online because the single-player campaign is only like three hours long. That way you don't have to worry about AI since the game is too short for anyone to notice.

This also increases revenue by allowing developers to sell half-finished games, then soak players for more money by selling the other half of the game as "additional content".

Sony, of course, would be using this strategy as well, but they've only sold about five PS3s, so it's not really an issue.

Pre-programmed Learning System Invalid, Then? (3, Insightful)

_bug_ (112702) | more than 7 years ago | (#18814843)

"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."

First, a neural network is more of the same "if/else" logic as any other AI engine. It's only different in how the AI processes it's input. Sounds more to me like a programmer/theorist who's pissed at all the tricks in existence that can emulate (fairly well) basic intelligence without the use of any "classical" system like a neural network.

Furthermore, neural-network-based AIs would have to come pre-programmed. This means a neural network that starts at a certain level of development rather than a blank slate. Should bad guys have to learn when and how to fire a gun while you're playing the game? It'd make for some boring encounters.

Furthermore, most games are quite linear. There's a story to tell and you can't really insert many uncontrollable variables into a linear system and still be able to maintain consistent play experiences for your users.

I wonder if this guy has seen Spore.

Re:Pre-programmed Learning System Invalid, Then? (1)

Lord Bitman (95493) | more than 7 years ago | (#18815111)

Why would we hire human programmers instead of having a series of if/then statements do it for us? Should they have to learn how to use a computer while you're trying to give them things to do?

Re:Pre-programmed Learning System Invalid, Then? (2, Interesting)

nuzak (959558) | more than 7 years ago | (#18815541)

> 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:Pre-programmed Learning System Invalid, Then? (1)

LKM (227954) | more than 7 years ago | (#18816149)

I don't think he means the "if/then" part literally, as in "uses if and then in code." I think what he's trying to say is that AI in games thinks like that. "IF unarmed THEN look for weapon. IF you see gamer, THEN cover. IF nothing to do THEN walk around in pattern."

This is different from real AI, even though things like neuronal nets obviously also use if and then.

Pre-programmed Learning System Fuzzy. (0)

Anonymous Coward | more than 7 years ago | (#18818039)

Some AI expands upon the IF...THEN by making the variables fuzzy.

Relevance depends on game type (0)

Anonymous Coward | more than 7 years ago | (#18814885)

I think the problem here is that Grand is attempting to apply his model to games that really aren't designed to be intelligent. Of course in games like Rome AD 92 and Civilization, a strong AI is necessary to enjoy the game. But seriously now, how advanced does Goomba intelligence really need to be?

Multiplayer (1)

Threni (635302) | more than 7 years ago | (#18814907)

I used to give a shit about AI in games, until I discovered multiplayer online games. Now I don't give a shit. Sure, some better AI would be nice, but it's not as badly needed now as it was 10 years ago when we all had was dial-up. I don't even think the AI has to be that smart to be better than we've currently got - it just hasn't been seen as important.

Shit. (0)

Anonymous Coward | more than 7 years ago | (#18815409)

Shit.

Re:Multiplayer (1)

Eideewt (603267) | more than 7 years ago | (#18816847)

I sort of agree, but in AI I'm also looking for something other than more skilled opponents. One thing AI can provide is characters that seem real. In a game like Thief, it's very important that the NPCs behave in a realistic fashion, because you spend most of your time watching them rather than forcing them to react. When you do want them to notice you, they behave in an entirely predictable fashion (they always run to investigate noises when you fire an arrow or throw something into a corner). The better you are, the more you watch them, and the less real they seem. But online play isn't a substitute in this instance, because it's impossible to put a player into a guard's position. A human player would always know there was a thief about, since that's the point of the game. Human players can't provide the same range of characters that NPCs can. Neither can they emote in the same way.

It's a question of quality (2, Insightful)

15973 (861573) | more than 7 years ago | (#18814997)

It's not about whether or not it's there, it's about where the focus of the developers is. For example, anyone who's played EA sports games knows about the poor quality of AI. Sports games are a little easier for users to justify, because exceptional things happen, but when the computer is cheating, it's cheating (careful use of save states can prove it). The problem is that the shiny graphics generate hype, which makes publishers want to sell games (like Doom 3, which had great graphics, and crappy gameplay). And since the mindless masses LOVE shiny, there's your forumla. How come I still have fun playing the old arcade games from the 80's and 90's? Because they're actually fun, and since we didn't have graphical power back then (or even colors), developers could focus on gameplay, which includes AI. Sure, the computers may not have adjusted to your every move back then, but at least they weren't as mindless as the people who think that good graphics == good games and bad graphics == bad games.

just wait...you ain't seen nothing yet... (1)

insanius (1058584) | more than 7 years ago | (#18815005)

I'm sure the guys at NaturalMotion developing Euphoria [wikipedia.org] (wiki) would argue...and i'm sure the guys at Lucas Arts and Rockstar would back them up on that.

Re:just wait...you ain't seen nothing yet... (1)

spun (1352) | more than 7 years ago | (#18815539)

What does a beefed up rag-doll physics engine have to do with AI?

Re:just wait...you ain't seen nothing yet... (1)

insanius (1058584) | more than 7 years ago | (#18816629)

you obviously haven't seen the demo...

from NaturalMotion's site:

Q: Is euphoria a physics engine? A: No, euphoria is not a physics engine. euphoria simulates the human (or animal) motor nervous system on Xbox 360, PLAYSTATION 3 and PC. One can think of it as biology meeting robot control theory. euphoria integrates with a game's existing physics engine, which provides the basic body physics (commonly known as 'ragdoll physics'). euphoria adds life to the dead physics simulation. In short, ragdolls are dead, floppy bodies. euphoria characters instead are alive and adaptive.

Re:just wait...you ain't seen nothing yet... (1)

spun (1352) | more than 7 years ago | (#18817657)

That's why I said "beefed up." It is NOT AI. It simply provides a set of reflexes instead of simple physics. From the front page of their web site:

[It] is called by the game's AI whenever synthesised motion is required instead of canned animation.

You have to learn to separate marketing hype from reality.

The challenge is balance (1)

Leo Sasquatch (977162) | more than 7 years ago | (#18815015)

A computer can micro-manage its resources in a strategy game within a second, whereas it might take me ages trawling through menus and sub-menus to find out just why production isn't at capacity. The computer is drawing my character on screen and responding to my inputs on the joypad/keyboard - it *knows* where I am in an FPS or action game. Truly realistic, learning, intelligent AI probably wouldn't be fun to play a lot of games against, because it would be better than you, or at least have faster reactions and virtually instant access to information.

My pet hate is the 'AI' in a lot of driving games, which consists of a rubber band attached to the back of your car. Did you just drive the best lap of your life ever and shave 3 seconds off the lap time? Well, what a coincidence, so did all the CPU drivers; what are the odds, eh?

Making you feel like you're succeeding against all the odds is one really clever part of games programming. Making that success still feel like a game, rather than work, is another. I don't believe these have as much to do with AI as they do with careful design, good controls, proper cameras, and plentiful save points. Miss any or all of those out, and 'AI' won't make it a good game.

Re:The challenge is balance (1)

tkrotchko (124118) | more than 7 years ago | (#18815339)

"Well, what a coincidence, so did all the CPU drivers; what are the odds, eh? "

But there's also a rubber band on the computer's car, no matter how well the computer drives and how badly you drive, you generally can catch up.

In a real race, if you run a terrible lap, you're 20-40 seconds behind. You have no chance of catching up. You're done. Unless it's NASCAR, there's no reason to run the rest of the race, and even in NASCAR, the only reason you run is because you get points for lapping.

Imagine making a space game where each move took months and years because space is really really big (you have no idea...).

So what's the right answer? Something completely accurate and deadly dull, or something that's silly and fun? This the age-old debate over computer game design.

Re:The challenge is balance (1)

LKM (227954) | more than 7 years ago | (#18816217)

This may be somewhat OT, but I agree with the car racing AI. It's not only that they're simply rubberbanding, it's also that they're often driving exactly the same course each time. I like how some Burnout games have aggressive AI where the cars try to push you into oncoming traffic or smash you into walls, or push you out in corners. That feels very realistic, and much more like human racers.

AI isn't the problem, Gamedesign is (1)

grumbel (592662) | more than 7 years ago | (#18815031)

I really don't think that AI is the problem, it of course can be hard, but the main issue is that the underlying gamedesign simply doesn't allow good AI. Simple example: God of War. Where exactly do you want to add the better AI? You are a one men army fighting against thousands of bad guys, they have to be stupid and easily defeatable to make that game work. Another game would be Half Life 2: Same problem, one men vs thousands of bad guys, if they actually would behave half as clever as a real person, the player wouldn't stand a chance. And so it goes on with tons of other games.

The issue isn't AI, but game design, as long as most games are designed as linear roller coaster rides no amount of AI development can fix their dullness. The solution would be to go more free form, game design that actually allow enemies to be clever without making the games impossible to beat. Such games are really not impossible to design, many games did it a decade ago already (XCom, EF2000, etc.), its just that most mainstream ones don't really try very hard to create believable worlds and instead continue down the "you vs rest of the world" approach, even the free form ones likes GTA.

Re:AI isn't the problem, Gamedesign is (1)

spun (1352) | more than 7 years ago | (#18815607)

Well put. One would need a flexible plot engine to deal with AI. As long as the story itself is hard coded, there is no room for real AI. Bethesda had to remove their advanced AI engine from Oblivion because the AI kept doing unexpected things and breaking the story. If one instead made stories that were generated on the fly based on in-game circumstance, AI would have a place.

I don't want AI (1)

mythar (1085839) | more than 7 years ago | (#18815047)

why would i want to play against an artificial intelligence when i can play online against real people? in my mind, there is no going back to single-player gaming once multi-player games have taken root (even if human players are often less intelligent than the typical computer AI). so, this notion that computer games need better AI is like saying that we need faster cd-rom drives.

Re:I don't want AI (0)

Anonymous Coward | more than 7 years ago | (#18815279)

Many people get fed up with playing online quite quickly. With the advent of mics and voip the benefit of realtime tactics is far overshadowed by immature people stating fallicies or just generally insulting other players for no reason. Im not singling out a single game or system, in that it is present in most.

I learned my lesson in TFC on public servers. People complaining about team balance or how Im cheating since I am playing a Pyro and have the higest score. Granted you got that back in the days before voip, but it is far easier to ignore a string of text than a voice - for sometime I just stopped playing with sound.

Re:I don't want AI (1)

metamatic (202216) | more than 7 years ago | (#18817353)

why would i want to play against an artificial intelligence when i can play online against real people?

Because for some people, playing with other people is more entertaining than playing against other people.

Consider D&D. Would it be more fun if it was a D&D deathmatch with 2 opposing teams of players?

Re:I don't want AI (1)

mythar (1085839) | more than 7 years ago | (#18818827)

so, then the questions becomes: why would i want to play alongside computer controlled characters when i can play alongside real people?

Do players really want smart AI? (1)

psiogen (262130) | more than 7 years ago | (#18815049)

Most single player games have always been based on the idea that the player can overcome seemingly insurmountable odds because the enemy is stupid. Most of the time, if it's important that the enemy be realistically smart, then it will be a multiplayer game.

Graphics vs. A.I. (2, Insightful)

hansamurai (907719) | more than 7 years ago | (#18815089)

There's been some great reasons listed already, but the obvious one to me is that the skill of the A.I. isn't apparent in commercials and trailers and screenshots, the graphics are. Graphics are driving the industry, they always have. In my opinion, there was a time when the discrepancy between graphics and A.I. were smaller.

Consider the days of Civilization II. The graphics were decent for the day but the A.I. was generally pretty good and coupled with a good game engine (not without its faults though), the discrepancy was not that apparent.

Fast forward a few years to the console game Goldeneye. Very good graphics for its day (especially on a console) but the A.I. was starting to stagnant. There were cases where infinite baddies would flood through a door, getting mowed down continually. Of course, Goldeneye came out almost exactly a year before Half-Life, a game usually praised as having a good graphical engine (on the PC) and good A.I.

Now a few years later again, we have Half-Life 2 and FEAR and many other first person shooters which are hailed as having great A.I. But all these games still suffer. Why is that soldier jogging against the wall? Why is this character I'm supposed to be leading around getting stuck on corners and running around randomly? The developers are spending so much money on graphical engines that they expect us to be entranced immediately by the world they created, and then all of a sudden, one of the enemies (or teammates for that matter) does something extremely stupid or so abnormal, we're ripped out of this trance and forced to remember that yes, we're just playing a game.

I'm sure it's not always the developer's fault. They have a lot of pressure from all sides to make the presentation of the game great, but it's apparent that the presentation can fall flat on its face when the A.I. is brain dead. But they don't have to show the A.I. being stupid in the commercials, they can show off the graphics and the pre-rendered cutscenes.

Graphics are driving the industry and thus the industry is being driven by Nvidia, Intel, and ATI/AMD. If developers were allowed to put some of the money they used to build a state of the art graphics engine into A.I. development, I think we would be taking some great steps. Here's to no more wall-jogging Nazis.

Re:Graphics vs. A.I. (1)

cowscows (103644) | more than 7 years ago | (#18816791)

While there's definitely some truth to what you're saying, I don't think that completely explains it. I think the truth of the matter is that A.I. is just plain harder than fancy graphics. In the world of academia, there have been plenty of people devoted specifically to work on AI. They aren't distracted by graphics, because that's a non-issue in their research. They've been working on this stuff for decades, and progress is still moving pretty slowly.

Compare that to graphics technology, which has advanced at a pretty relentless pace. Regardless of the economic incentives one way or another, I refuse to believe that there aren't some very smart people out there dedicated to AI research.

Whenever a gamer talks about HL, as you said the comparatively good AI is quite often mentioned. If it wasn't a marketable feature, then nobody would care enough to talk about it. I think if your AI was amazing and blew away editors at gaming mags/websites, they would rant about it plenty, and you would get a lot of great publicity which would help you move lots of extra units. It seems plausible enough that I can't believe that at least a few developers wouldn't have already gone that route if it were already possible.

I don't know if the hardware isn't powerful enough yet, or if the underlying research isn't far along enough, or if we need a whole different computer language paradigm before AI can make serious steps forward. But I think that it would've already happened if it was just a matter of someone throwing some significant resources at it. If you could figure out how to write some really competent general AI, the return on investment would be huge, extending well beyond gaming.

FEAR? (1)

Mobkey (1086895) | more than 7 years ago | (#18815105)

I don't know if I'm alone in this, but I thought the AI in FEAR was pretty awesome. Maybe because I thought crashing through windows and waiting for me in ambush was cool, but whatever. But yes, most of the time they're dumb. Call of Duty 3 really pissed me off for that in particular. I guess we just have to make sure we buy good games when they come out.

AI in some games can be smart (1)

427_ci_505 (1009677) | more than 7 years ago | (#18815201)

Some modern games seem to have pretty convincing AI's. The Fear demo from a year ago seemed pretty smart. And doesn't Forza Motorsport use a neural network somewhere in the AI?

How is this any different from real life? (0)

Anonymous Coward | more than 7 years ago | (#18815217)

Most of what counts as AI in the games industry is actually a bunch of 'if/then' statements.
If my wife tells me to do something, then I do it or else I'm sleeping on the couch.

This is not game specific (2, Insightful)

pclminion (145572) | more than 7 years ago | (#18815551)

It is a common phenomenon in the AI community. When a new method or algorithm is first proposed, which achieved gains over prior methods, it is consider "new AI." But as time goes on and the algorithm is put into common use, it degrades into "just another algorithm."

AI is really just whatever the bleeding edge happens to be. For instance the A* algorithm to find "good" paths. It's certainly an intelligent algorithm, but nobody really considers it "AI" anymore. It's just a search method.

So, is a series of if-then statements "AI?" If it's new and powerful and does stuff that no other algorithm can do, probably yes. But as time goes on it becomes just another algorithm. AI, pretty much by definition, is simply "The smartest stuff we can do as of yet."

Re:This is not game specific (1)

jeffasselin (566598) | more than 7 years ago | (#18816253)

But as time goes on it becomes just another algorithm. AI, pretty much by definition, is simply "The smartest stuff we can do as of yet."
Maybe in marketdroid speak. In the world where I live, we use a definition of intelligence which is slightly above the congitive ability of a meat pie.

Re:This is not game specific (1)

pclminion (145572) | more than 7 years ago | (#18816367)

Maybe in marketdroid speak. In the world where I live, we use a definition of intelligence which is slightly above the congitive ability of a meat pie.

Jesus, man, the implication was "The smartest stuff we can get the computer to do unsupervised." Try reading between a lines a bit.

don rose colored glasses (0, Troll)

nuzak (959558) | more than 7 years ago | (#18815569)

Yet more old fogeys shaking their canes at "those whiz bang fancy dancy graphics". The previous generation's AI was always as bad or worse, full stop.

Steve knows what he's talking about (1)

greenreaper (205818) | more than 7 years ago | (#18816089)

Creatures [wikipedia.org] was a masterpiece for its time, and is still a good game for children today - the author [wikia.com] did some technically challenging work, without a background in AI. Perhaps that's what we need - more general developers thinking about how to do AI rather than people who have been trained in current techniques.

AI = obsolete (0, Flamebait)

duckpoopy (585203) | more than 7 years ago | (#18816205)

'AI' refers to an obsolete field of CS which is rapidly being replaced by NN, pattern classification and statistical learning theory. 'Game AI' refers to heuristics that programmers hack together at 3am before shipping a title.

Games don't "devalue" AI (2, Interesting)

ZombieRoboNinja (905329) | more than 7 years ago | (#18816331)

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.

Hmm (1)

brkello (642429) | more than 7 years ago | (#18816351)

How do we know our own intelligence isn't a bunch of if/then statements? Sure, if we are presented with the same situation, we can do different things (though I would argue that it is impossible to ever have the same situation perfectly...one you experience something once, you have an experience with it, once you have the experience again, you have two, etc.). But say we are presented with the same situation and do different things...just add a random number generator and probablilty in to the statements and you can imagine ourselves as code. Very complex, very long, very ugly code...but code. Our brain just develops our if/then statements faster than a programmer can program it. The only thing lacking from the AI in most games is the ability to add more if/then statements on its own.

Creatures (0)

Anonymous Coward | more than 7 years ago | (#18816481)

This is the guy that created Creatures, and signed his royalties away for a paycheck. One presumes he thought it wouldn't sell very well. It sold 16 million copies apparently. He also feels that AI researchers don't take his work seriously.

Ironic really. As a "Game AI" programmer, I can say that his comments about game AI are uninformed. The talk on FEAR's AI at GDC 2006 was extremely informative, and, no, it wasn't a bunch of if/then statements any more than a neural network is. I bought creatures and found it immensely boring. I bought FEAR and found it very entertaining.

Try a thought experiment. Imagine putting a real AI (an "I" if you will) in a game like FEAR. Make it feel pain so its "real". Let it know that the player has like 200 times as many hit-points. Given the choice between taking multiple badly aimed shots from the player, or just shooting itself quickly in the head, which do you think it would choose? Not much fun. Games are about fun.

Define your objectives first. (0)

Anonymous Coward | more than 7 years ago | (#18816557)

If the objective is to make an AI that wins, thats trivial. The computer can react instantly, know everything, and... well, cheat.

The real objective is to act as much as possible like another human player would, while not messing up the plotline. Be good, but not too good. Share human weaknesses.

Take an RTS for an example, as they have the most potential for employment. The AI needs to share the same weaknesses as a human, for a start - if you attack the resource-producing facilities, then it needs to run out of stocks if they arn't fixed quickly. The AI component of the game needs to remain unaware of any information that it would lack as a player - if the player's units are sneaking up, then they must be ignored until spotted. It needs to dynamicly adjust the size and direction of attack forces after a while - if thirty units attacking the player didn't breach his defences the first three times, then the AI will look like an insect colony if it keeps trying exactly the same stratagy over and over.

Perhaps some real AI experts should turn their attention to this problem - dabble with neural networks and genetic algorithms. Perhaps they can come up with an AI that is close enough to human that players feel as though they are playing against an opponent, and not just an ant colony.

Ive just been playing supreme Commander. Antyness shows very clearly.

Stardock... (1)

Jaysyn (203771) | more than 7 years ago | (#18816793)

Has pretty decent AI in it's recent Galactic Civilization games.

Games are getting better (2, Insightful)

Sciros (986030) | more than 7 years ago | (#18816807)

For one thing, games are getting better and better when it comes to AI every year, and it's not "just" because it's hard. It's also because good AI is resource-intensive, both in terms of processing power and in terms of storage space (depending on what you want to do) ... on and in terms of time it requires to develop.

A simple rules-based system that has a bunch of if-then triggers is sufficient for a lot of things, but once you get into sophisticated behavior the number of rules becomes simply to large to generate, and the process for selecting the best action nontrivial as rules get bunched together due to equivalence, etc.

Statistical learning systems (Bayesian, etc) can be very powerful, but have not been seen in games until recently (for a great example check out Forza Motorsport 2 coming out in May, for which the AI was developed in Cambridge, UK, the MS Research building next-door to where I took my lectures on comp. text and speech processing ^_^).

The main reason that game AI is not as advanced as folks might expect is that "sophisticated," learning AI takes a significant time to develop and train. Most importantly, it requires expertise that goes beyond just being able to code C++ or Java or CLIPS or what have you. People with this expertise don't go into game programming because there they get underpaid. Rather, they go to Google or Microsoft or Yahoo or make their own company. (Indeed, Forza's AI was developed by MS rather than a 3rd party middleware dev house.) Why? BECAUSE THE REAL MONEY IS IN SEARCH!!! That's where the AI experts go, folks.

Not just AI (1)

linvir (970218) | more than 7 years ago | (#18817505)

It's not just the AI that's not progressing. Behaviour in general is lagging behing hardware capabilities. For example, the newest Splinter Cell game. Consoles by now should be able to at least simulate an enemy's field of vision accurately. Apparently not. The NPCs in Splinter Cell have a very boolean field of vision, and you can be in plain view looking right at them, in good light, and they don't see you. And then if you trigger an alert, suddenly everybody's vision improves.

Crackdown is another example: The enemies seem to "see" and track you from hundreds of feet below despite the fact that you are sprinting around rooftops, outside their line of sight.

Both games look spectacular, I might add.

Work it from the other end (3, Funny)

WilyCoder (736280) | more than 7 years ago | (#18817797)

Instead of making enemies smarter with better AI, lets make players dumber.

Should even things out quite nicely IMHO.

whats the problem (1)

cpt.hugenstein (1025183) | more than 7 years ago | (#18817873)

some men like beautifull but brainless...

AI pointless? (1)

Arch24 (1091167) | more than 7 years ago | (#18817947)

I only beg the question, is AI pointless? Have gamers decided that a computer, at least eventually, will be able to out think and outwit a human mind every time? If so then what is the point of playing against an infallible (lol) machine. We should instead concentrate on conquering humans (so to speak). I love online play and consider it the quintessential place for a real challenge. If developers want to concentrate on multiplayer, and consider single player "extra" then so be it. "Total Thermonuclear War FTW" Arch
Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Create a Slashdot Account

Loading...