Slashdot Log In
AI Researchers Produce New Kind of PC Game
Posted by
timothy
on Mon Jun 27, 2005 06:32 PM
from the learning-by-killing dept.
from the learning-by-killing dept.
Ken Stanley writes "In an unusual demonstration of video game innovation with limited
funding and resources, a mostly volunteer team of over 30 student
programmers, artists, and researchers at the University of Texas at
Austin has produced a new game genre in which the
player interacively trains robotic soldiers for combat. Unlike most games
today that use scripting for the AI, non-player-characters in NERO learn
new tactics in real-time using advanced machine learning techniques.
Perhaps projects such as this one will encourage the video game
industry to begin to seek alternatives to simple scripted AI."
This discussion has been archived.
No new comments can be posted.
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
Full
Abbreviated
Hidden
Loading... please wait.
Coral Cache (Score:5, Informative)
Re:Coral Cache (Score:2, Insightful)
Re:Coral Cache (Score:5, Interesting)
</rant>
Parent
Re:Coral Cache (Score:5, Funny)
http://everyone.com/growing.php?retarded=yes [everyone.com]
Parent
University of Texas. (Score:3, Funny)
Re:University of Texas. (Score:2)
Re:University of Texas. (Score:5, Funny)
If it's UT and it's anything but Unreal Tournament, you say what it is.
Parent
Never mind! (Score:3, Informative)
Apologies to the submitter!
If it's fun... (Score:5, Insightful)
Keep in mind though - entertainment is meant to be entertaining, not neccesarily realistic or academically advanced.
Re:If it's fun... (Score:2)
some people, hasve more fun if they are playing the most realistic game out there.
Re:If it's fun... (Score:3, Insightful)
The goal of most game AI is to get a lifelike and entertaining behavior, which can be pretty easily approximated in very simple algorithms.
I'm not knocking the game there either; I haven't played it. There was just a hint of "why don't games use advanced AI techniques" academic frustration in the post - I was po
Re:If it's fun... (Score:4, Interesting)
and then there's the fun factor. i seem to remember an article about one of the Id games in which they developed all sorts of interesting behaviors for the AIs, played with in for a while, and eventually came to the conclusion that "turn and move toward player" gave much better gameplay.
on a separate note, i remember a game from the late 80's in which you had to program logic circuits to get a robot to perform tasks of increasing difficulty... not a game with a lot of commercial appeal, i'm sure, but i spent many hours trying to solve problems using those little graphical circuit boards...
daniel
Parent
Re:If it's fun... (Score:5, Insightful)
-having an increased production rate
-having fights tweaked to the AI's favor
-starting with more units
-always being aware of all movement on the map, regardless if it'd be visible to that player
-controlling everything at once
-receiving all relevant information at once
I really don't think so. It's driving me nuts in all games that harder settings *always* means 'AI can cheat more'. This is the reason I don't like RTSs and hardly can stand to play CiV. Omnipotence and Omnipresence is not AI. AI (in games) should emulate how a human would play (advanced planning, patteren recog. etc) with all the strengths and weaknesses that come with that. A good AI in that sense would hardly overwhelm the player seeing how sucessful multiplay games are. Just face it, technology and AI research is just not capabable of pulling it of. Just say that instead of 'well, you really wouldn't want it'.
Parent
What is old is new again (Score:5, Interesting)
Re:What is old is new again (Score:3, Funny)
And we all know what that led to [imdb.com].
Re: What is old is new again (Score:3, Informative)
> Call me short sighted, but isn't it at least possible that training soldiers is different to training tic-tac-toe players?
Yes. Tic-tac-toe has a manageable decision tree, and all MENACE did was prune branches that led to losing. It still required many playings, because it always pruned at the last decision that led to the loss. (Thus it trimmed the decision tree from back to front.) It would be completely untractable for chess, let alone for continuous-state games or simulations.
Still, MENACE was a
Brains in the Training Loop (Score:5, Insightful)
Or perhaps... (Score:5, Funny)
The DOD will get interested, and use a similar technique to train -real- robots?
Re:Or perhaps... (Score:5, Funny)
The DOD is perfectly capable of creating robots that kill people. The hard part is making those robots NOT kill the people you don't want them to kill.
Parent
Re:Or perhaps... (Score:3, Insightful)
Yeah, because as humans, we do a really good job of making that distinction. Hopefully that's not the model we're using to train these robots...
Re:Or perhaps... (Score:5, Interesting)
Parent
Re:Or perhaps... (Score:5, Insightful)
I'm sure that you think that link is a slam dunk, but I think that it is telling that you haven't a single word of your own on the topic.
I think that your conception of combat is naive. I think these poor sons-of-bitches in the tanks that fired on their comrades made a gut-wrenching decision under impossible circumstances. In the dark, in a foreign land, in abject and immediate fear for their own lives they saw what appeared to be hostile troops firing on them.
These weren't guys who had been "in country" for weeks and months, and had developed an instinct for differentiating an RPG hit from enemy cannon fire. This was some 20-something guy, maybe a year out of West Point, or two out of ROTC, and some enlisted men, maybe 19 or 20. If they had the presence of mind to formulate a though more complex than, "Fuck! Those bastards are trying to kill me!" then they are probably better men than you or me.
Combat isn't like a game of chess. One can't sit back an contemplate the possible repercussions of one's actions. It's smoky, dark, dirty, hot, and freezing, windy, rainy mess. It's being hungry, scared, and confused. Sleeping standing up, and having rashes in places that we don't talk about in mixed company.
Now, I'm in favor of any technique or technology that you can come up with that reduces fratricide. But smug, flippant comments that show no application for the realities of combat make me sick.
-Peter
Parent
Re:Or perhaps... (Score:3, Interesting)
As the original "grandparent" poster, I have one thing to say to that:
Humans may suck as telling friend from foe in the heat of combat, but right now AI is worse.
In the past, AI has not allowed people to make calmer, more objective decisions. Landmines, to take one example, kill civilians more easily than they kill soldiers, and without the accountability.
How do you mix landmines
My cousin is in the military.. (Score:5, Funny)
Parent
Re:My cousin is in the military.. (Score:4, Funny)
Hey now - let's not get insulting here: robots are much smarter than Marines, and Marines are much tougher than robots!
(Note: JOKE! My brother was a Marine before he worked for NASA, my insurance agent is a Marine, and there are few people I'd rather have guarding my ass than Marines.)
Parent
Not at all new (Score:5, Informative)
Re:Not at all new (Score:3, Informative)
Re:Not at all new (Score:3, Informative)
(answer, after a quick google: http://www.toadstool.net/games/omega/ [toadstool.net] has the DOS and Amiga versions, as well as tanks and more)
uh-oh (Score:2, Funny)
403 Forbidden. Nice try, maggot
Geek Robots? (Score:5, Funny)
Probably not, but beware -- you may just create a robotic system administrator/repairman. Don't put yourselves out of a job!!!
Greetings, Professor Falken. (Score:5, Interesting)
Stephen Falken: Hello, Joshua.
Joshua: A strange game. The only winning move is not to play. How about a nice game of chess?
For those of you who actually look on a user's history of posts, yes this is a variant of another post I did, however it's apropos here as well.
hopefully it will (Score:4, Insightful)
> industry to begin to seek alternatives to simple scripted AI.
hopefully it will encourage the video game industry to begin seeking alternatives to Yet Another High Resolution First Person Shooter.
Sounds like "Galapagos" (Score:5, Interesting)
It could get frustrating--sometimes if he hit a particular deadly obstacle too often, he'd become traumatized, and would then refuse to go anywhere near it, which could make the level impossible until you had allowed him to wander around and petted him and calmed him down.
Great game, though. I wish there were more like it.
Torrent (Score:5, Informative)
Re:Torrent (Score:5, Insightful)
I'm not, but I could be.
Parent
Good, but... (Score:3, Insightful)
The AI Problem...From the Publisher's Perspective (Score:5, Insightful)
The total revenue for the game industry in 2004 was 1.2 billion dollars which was down 100 million from 2003. During this same period only two games had sales of over 500,000 units, but there were 18 games which had sales of 250,000 or more. Based upon the varying definitions of what constitutes a "new release" there were roughly 1,100 games released in 2004 of which maybe 6% earned a profit. The average budget for a competitive game is said to be around two million dollars with an average break even point of around 110,000 units sold. The average retail game price is $24.45 with only 5,000 total units sold.
Clearly, the open source community is willing to undertake these efforts on their own initiative or for other reasons related to research, as was the case with the student produced game. I am in no way denigrating the efforts of these students, what they produced with the resources available to them was simply amazing and of surprising quality. However, in the world of retail games it takes a certain amount of marketing, advertising, and Wal-Mart end caps to rise above the background noise, unless you are like the aforementioned established game companies and the reputation speaks for itself, at least until they release a real stinker. At the end of the day, when all things are factored in, there is simply not enough money in the budget of the average game to make this type of advanced artificial intelligence worth the risk and expense, at least right now. However, if there is any constant in the game industry it is change and this will probably change in the years to come. I would like to see some new and innovative games too, instead of Madden 2017, but it looks like we will have to wait a while yet.
can they learn suicide runs? (Score:4, Insightful)
I'd like to know if the NEROs can evolve more advanced tactics such as:
When its health is less than 5% and likely to die, make a final kamakaze run at a tough enemy to deliver a mega bomb, draw fire, etc...
Gang beat downs - Even though the NERO is closer to enemy tank B, focus your fire on enemy tank A since its damage is critical and about to be pushed over the edge.
Unload power ups - Before picking up a weapons upgrade that would replace my super grenade, go ahead and lob all of my super grenades before picking up the power-up.
Waiting for power ups to cycle - In some games, a power-up changes every few seconds. Could the NEROs learn to wait for spread-fire on one level versus lazer fire on another level? Okay, levels is too easy, how about depending on the situation, what my friends have, etc...
And most importantly, could NERO's be taught to perform "ethical cheats"? By ethical cheat, I mean take advantage of the game engine or environment in a way not intended by the developers. -Not by patching code or using network sniff bots.
Sure, these seem like pretty simple tactics, but YOU try programming this kind of AI. It's next to impossible!
Re:can they learn suicide runs? (Score:3, Interesting)
Re:can they learn suicide runs? (Score:3, Interesting)
pac-man with emotion-like behavior (Score:4, Interesting)
I think that will be the next stage of computer characters: to make them unpredictable even for the programmers. Rule-based learning can get you somewhat complex behavior, but it is all predictable. What we need is genuine example-based learning. So that the resulting behavior would be impossible for anyone to predict and constantly changing and evolving. Of course I am thinking along the lines of various neural network, connectionist architectures. Their unpredictability is generally considered a downside, but for a game the black box aspect seems perfect.
Finally!! Geeky Gameplayer Employment! (Score:4, Informative)
Will these things be marketable? "Ma, I'm not playing games, I'm training my robo-warrior!"
Money (Score:3, Interesting)
My thought was that you would train an entity yourself in a series of one-on-one battles or training bouts. These could be staged or otherwise constructed to make mini-games e.g. perhaps testing your entity in predefined scenerios. Once you were happy with its performance you could dump it onto a USB stick and take it around your friends house or upload it to a server for an online game. The main game would put your entity in an arena against a number of other 'gladiators'. They fight it out etc. Online this could allow for 'spectators' who watch the game and potentially even bet on the winner. This might allow for prize money or other revenue stream to be introduced.
Forza Motorsport (Score:3, Interesting)
More info about it here: http://www.drivatar.com/ [drivatar.com]
What about this (Score:3, Funny)
Maybe, after all, such a cluster exists because there is such a post on everything remotely clusterable.
Re:AI? on a video card? (Score:5, Informative)
False.
FLOPs are not generally useful for things like scripted AI which are very branch heavy with a lot of indirection, and many possible branch targets and data requirements.
The techniques described in this game are highly mathematical in nature with a small memory foot-print, (adaptive neural networks and genetic programming via Kenneth Stanley's NEAT algorithm) and would benefit hugely from parallel vector proccessing.
Additionally, at the end of the day, the AI decision making is not nearly as expensive as the proximity-query and pathfinding routines that affect the decisions. These routines also benefit hugely from vector processors and high bus-bandwidth.
So fittingly, the AI will only suffer if the human intelligence can't adapt and make the fairly obvious decision to move toward more mathematical AI routines.
Parent
Re:begin? (Score:5, Interesting)
Parent
Re:begin? (Score:5, Funny)
If you can suggest how better to prove that I worked on it, let me know.
Parent
Re:begin? (Score:3, Interesting)
I have one solution, but i'd like to hear yours, maybe yours is better than mine.
Re:The problem with this... (Score:5, Funny)
Parent