Slashdot Mirror
Adaptive AI in Games - Does it Really Work?
qasimodo asks: "I was recently reading a preview of Splinter Cell: Pandora Tomorrow, and then I came across this article at GameSpot saying Pandora Tomorrow will feature adaptive AI which 'will adjust itself to players' skill level'. I remember (and is also mentioned in the PT article) Max Payne also featured this, but I never noticed it. I guess that's the best way to know if it works, since it adapts to your gaming skills, but does it really work? Have you noticed it? Do you have proof of it?"
Maybe it just determined you suck.
Deep breath, its a joke.
I remember reading an article about Gods by the Bitmap Brothers where they had helper triggers for people that had been stuck for a few minutes. They called it a shandyometer, after shandy drinkers obviously.
X-Com had a shandyometer, my old housemate used to send men who were very poor and irritating out, let them get slaughtered, then send in his main team and the game would have made it easier.
(For the non-Brits, Shandy's a mix of lager and lemonade (as in 7up/sprite), the old lore is that its drinkers are somehow unable to handle real beer)
Descent 3 always had adaptive AI. I remember when I first played it. I had played the prequels so I went into 3 with the same strategy I always had. It got me through quite a bit of the game, but it wasn't easy. Early in the game I was able to fly around really fast picking enemies off one at a time. As I played more they started to run away, regroup and attack in force. I countered that strategy by using bigger guns to destroy them. They then started to change formation to minimize the damage I could do to their whole group. While Descent 2 was the pinnacle of the series Descent 3 had revolutionary AI.
Also, I think that the sea battle AI in puzzle pirates could possibly be adaptive in some way. A couple updates ago they allowed brigands (computer controlled boats full of booty) to fire canonballs. Since then it has been widely agreed upon by players that they have increased in difficulty each and every day. There was an update last night, so we'll have to see what happened. I'm still a little unsure of this because if the AI was adaptive in some way, wouldn't they tell us?
The GeekNights podcast is going strong. Listen!
it wasn't really adaptive, simply when you die too many times, the difficulty level is reduced, which includes the accuracy of the enemies, their damage, and your damage, many games have similar features, Warcraft III comes to mind, the only difference is that Max Payne does it automatically, no big deal.
The IT section color scheme sucks.
After reading that little snippet on gamespot, I've got the feeling that the game will be 'letting you win'. It states that if it takes you 20 tries to do something, the game will lower it's standards for you. Why did finishing Splinter Cell make me feel good? Because it makes me feel I've accomplished something. I've mastered the game, no matter how difficult the timing was, no matter how pixel-perfect I had to aim to kill that guy, no matter how hard it was to master. Unless they (Ubisoft) implement this Adaptive AI perfectly and unnoticeable (and I hope they will), I'm going to feel as if no matter how bad I play, or how crummy my timing is, I'm still going to master the game. Adaptive AI could really take the challenge out of any game.
What's the main reason players get disinterested in a game? Because they come across a level that they can't beat, and they get sick of the same ol' stuff over and over again.
If less people are buying these games, because they just aren't the master that you apparently are and would rather not get halfway through the game only to quit in frustration, it hurts the company so this move makes sense.
However, to satiate you, they should add an option to set the AI on the hardest possible skill level.
"I only speak the truth"
Karma: null(Mostly affected by an unassigned variable)
as much attention as it is. After all, I believe it was NBA Jam which introduced this concept, though they called it "CPU Assist". Essentially, a player who was losing would get more and more help from the computer as his deficit grew and grew, making his shots much more likely to go in and letting him knock opposing players over much more easily. On the flip side, a player with a big lead would find most of his shots hitting iron, and his players would lose the ball and get knocked over if opposing players even looked at them.
I also recall reading many years ago in an issue of Sega Visions (Sega's failed answer to Nintendo Power) that the Jurassic Park game for the Genesis would have "Dynamic Play Adjustment". The only example I can recall of this is that if the player was doing well, gaps to jump would get wider. I'm sure there were other examples, but that's the only one I remember.
So, in other words, this ain't new.
This is the NFL, which stands for "Not For Long" if you keep making those bulls*** calls.
Maybe its becoming more sophisticated in games like Pandora Tomorrow, but as a general game design concept, it's been around for a while.
The concept is mentioned in Rules of Play. Although I don't have it accessible right now, the example they used was in Wipeout XL (but could be any other Wipeout game for that matter). If your racer took a spill in the first lap and the AI of the computer racers didn't change, you'd have no chance at making it back up to the front of the race. However, because Wipeout XL used apadaptive AI, the conputer racers slowed down a little bit in this kind of situation making it possible, although more difficult, for the player to still win the race. That's not to suggest that this was the first instance of adaptive AI either. Conceptually, I'd wager that its been in games (probably in the sports genre) for quite some time.
What that game really needed was a way to adapt to your attention span. When he would launch into one of those speeches about the rain on the pavement and how it made him feel, I wanted to shoot my Playstation.
the catch 22 is: make the game too easy, and players will complain. make the game too tough, and players will complain.
personally, i don't think a 'difficulty' slider should come into affect with AI. The AI should always -try- to behave the same way.
Whether you intend for them to be tacticians, civilians, or just mindless grunts. on 'Easy' or 'Difficult' a bad guy should still know he should take cover, call for backup, etc.
The 'difficulty' should come into play when deciding their accuracy, movement speed, 'scoring' (penalties for shooting hostages, raizing conquested territory, etc). It could also come into play in deciding the scarcity of resources. on Easy, there should be extra resources for the hero, and less for the enemy.
Adaptive -AI- is the wrong approach. Adaptive -difficult- is still a good idea though. but don't make enemies dumber; just make them slower, more inaccurate, fewer in number - don't give them as many grenades and leave more health packs around.
oh, and i also don't appreciate the 'difficulty' sliders that just scale the damage you receive up and down. that is an awfully 'cheap' hack imo.
// "Can't clowns and pirates just -try- to get along?"
The "adaptive AI" in Max Payne was simply a dynamic difficulty slider. I wouldn't be surprised if it was simply a matter of monitoring your kill rate, perhaps adjusted by your injury rate, and increasing enemy effectiveness (fire rate, accuracy, maybe damage multiplier if they really wanted to be devious) accordingly. I imagine the AI topped out fairly low, though, so the overall effect was negligible. I don't believe it was adaptive in the sense that it dynamically adjusted its battle tactics according to your battle tactics, as opposed to simple numerical effectiveness.
Say I tend to shootjump to the right when I head into battle. The AI couldn't care less. Now if it _did_ notice that enemies tended to die more often when I did so, and cause them to proactively fire where I would, statistically speaking, very likely end up, that'd be an AI to write home about.
The most remarkable AI in modern gaming that I've encountered of late is that of Virtua Fighter 4: Evolution (a bargain at $20 new, btw), in which battle profiles of players in the Japanese arcade circuits was distilled into what prove to be fairly different AIs. Dynamically speaking, the game tracks the areas that you tend to attack successfully (high, middle, or low), whether those attacks are strikes or throws, and whether you won or lost with those percentages...and, judging from its effectiveness at smushing me in the long run, adjusts its behavior accordingly. So while a given AI profile might tend to, say, try to counter middle throws often, that tendency might be further exaggerated as the bulk of my throws tend to come from that area.
Quite impressive not only for its dynamism but also for the wide and finely graded range of difficulty among the AIs. As you gain ranks in the Quest mode (from 1st kyu to 10th, 10th dan to 1st, and beyond), your opponents very slowly become more difficult such that you can actually observe effective tactics emerging and adjust your _own_ behavior accordingly. Quite a far cry from Street Fighter II, mm?
IIRC, Doom and Quake had adaptive AI, too.
No, I guess it doesn't really do anything different from a random number generator.
"Lawyers are for sucks."
- Doug McKenzie
Considering the advances made in computing, I'm surprised that current gaming AI is still so sucky. It seems that our games have advanced only graphically and in size (I'm thinking world size -- but physical size has also grown) -- largely due to advances in memory and storage media.
As far as I can tell, AI has not advanced with current technology. I'm reminded of this while playing modern RTS games, where it seems that all computer opponents have similar stratagies, but never seem to ever actually "learn" anything (or even show a hint of adaptability). Of course, this is all purely antecdotal, but not without merit.
Any game developeres care to back me up? Or am I full of shit on this?
-Turkey
If there was a point where it became unbeatable, then it was not very good at adapting, was it?
The essential point in adaptive AI on games is to be difficult enough for anyone to be entertaining, without getting frustrating, or the opposite, that it's so trivial to beat it that it becomes uninteresting.
The best cure for insomnia is realizing that it is already time to get up. EsteEncanto.com - Blog on technology, urban
I can vouch for Max Payne's variable AI working. I played the game through once and thought "This is fantastic." So I decided to play the game through again. The first level was a breeze. I single shot to the headed every single enemy. Then, next level, all hell broke loose. The enemies were rolling, took at least four shots each, ducked bullets, hid behind things, shot back very accurately.. they couldn't kill me but I ran out of ammo quick. I never made it past the second level because the AI had jacked up to the highest level. If I recall correctly, when you die on a level it lowers the AI's abilities just in case it had them too high.
Aren't you guys messing the adaptive difficulty level with adaptive AI. Adaptive AI should learn, not simply adapting number or speed of enemies to the lameness of player.
What they need to do is adjust to the players styles. I like to camp and snipe in just about every game. I wish it would then cause the AI to start moving more rapidly, and check sniper spots more often. Do you always do something when you enter a room? Then the AI should brilliantly counter it, so I have to get a new strategy. Do I always camp in the same place? Then nade me.
Second of all I dont want it to turn pathetically easy, even though every game should have a difficulty setting called baby or wuss. (especially racing games like Gran Turismo) that would let you win. I labored so many damn hours perfecting my skills to no reward in Gran Turismo Three and I want my Formula One cars NOW!!! But what is the fun if I never die and never get hurt and don't get that rush when you complete a challenge. Because when I beat GT3 I will be so happy and thrilled and I will feel my $50 and racing wheel paid off. I will buy GT4, hence a happy customer and money for the corporations giving a financial incentive to the suits.
What it should do is offer a hint, to really bad players(flash bang a room with possible enemies and friendlies!!). Adapt to my style. If I want to snipe, then those guards better give up the grenades and take up some binoculars and a rifle. If a player is good at one method, make the objectives possible using that strategy, but encourage all the others too! Adaptive AI should enhance game play and make the game last. If I completed the it the first time sniping, and I want to be forced to try close quarters combat next time, without setting something I have not done any harder and make me have to vary my strategies to complete it. If Splinter Cell pulls off what I want, then UbiSoft will be very rich and I will be one very happy gamer.
Mod Wisely.
When playing Max Pain I found out about the adaptive AI the hard way.
I naturally adapt a one shot kill strategy in most games to be more efficient (less ammo wastage/less health wastage), unfortinatly in max pain this ended up with the first few level being very easy and then suddenly becoming impossible to complete.
Never the less max pane was religated to the dust bin as I was so fustrated and anoyed by this that I hardly felt like replaying half the game.
Just goes to show that Q&A testng is vital when implimenting a new tech as this should have most definilty been picked up.
GPLv2: I want my rights, I want my phone call! DRM: What use is a phone call, if you are unable to speak?
Not entirely true. Racing games don't HAVE to have adapative ai. The Grand Prix series never has. Grand Prix Legends, from what I gather, is kind of adaptive. It will set the ai times by your best lap to a degree.
NASCAR Racing never used to have it until this last iteration. As I said, it works pretty well. Starting a race from the back at Daytona, I managed to fight up to 17th place by the end (10% race distance) which is pretty good, and it was a huge fight all the way.
One thing a racing games DOES need it for is consistency. Many people find themselves great at one track, and not so hot at another. Without adaptive ai, you can crush the AI at one track, then lose badly at the next. It's more a question of realism than anything else. It's rare these days to see a driver lead a race at one track, then get lapped by everyone at the next.
Well, adaptive AI in gaming has always meant that the AI adapts to the player's skill level. What you want is a Learning AI, which in gaming generally means that an AI adjusts a slider to better counter a move that a player will make.
This isn't rocket science people. There have been, for example, nearly perfect Ai's that have played within the rules of a game and can still kick a player's tail. All games are developed with the idea in mind that every move has a counter, and every counter has a counter. Now, the AI development team knows the best instantaneous moves to counter other moves, and as they are the development team know most of the higher-level strategies that will be tried. If a development company wants an AI to beat you senseless, it can do so without changing the rules of the game. Is that fun? No. So you weaken it, and change difficulty levels around. Now you have a system that isn't learning, but is playing with the player. And playing is fun.
The ______ Agenda
See my comment here for an old, old case that I do consider learning.
I've had this sig for three days.
> The essential point in adaptive AI on games is to be difficult enough for
> anyone to be entertaining, without getting frustrating
I think you want the player to get *slightly* frustrated *occasionally*. Not
badly, and not often, but if the player always wins without putting in some
extra effort, that's no fun either. When the player's tactics and skills
stagnate, you want to start beating him some of the time. (Not all of the
time. Not, even, most of the time, I think. But some of the time.)
One way to make game difficulty adaptive, without serious AI, is to make
expectations scale with accomplishments. This is easier in some types of
games than in others. Tetris is a great example of a game that can become
infinitely hard. Is the player stacking perfectly, covering no empty spaces?
Well, then, raise the probabilities on the hard pieces. Is the player in
deep doodoo, stacked past the middle of the board? Throw him some easy
pieces. (Most tetris games don't do enough with easy and hard pieces.)
And of course there's the ever-increasing speed. Not all games have such
easy ways of raising or lowering the expectations, without fundamentally
changing the consequences of the player's actions and therefore the strategy.
Games like freeciv are particularly in need of good AI.
Cut that out, or I will ship you to Norilsk in a box.
I'll be the first to praise Descent's great AI, but I honestly don't think it's adaptive at all. Doing a search yielded no pages that indicated an adaptive AI. I even found an interview with one of the developers, and although AI was discussed briefly, no mention was made of adaptability.
The Descent robots were definitely smart - they could find you ANYWHERE in a level, could call for reinforcements, and some knew how to sneak up behind you when you weren't looking. But they didn't adapt to your playing style or learn from their mistakes. There were five difficulty levels: Trainee, Rookie, Hotshot, Ace, Insane. From what I can remember, the bots were just a little bit better at dodging on the higher difficulty levels (and did more damage, too).