Quake Bots Rock The Prefrontal Cortex

0x4B writes "Some researchers from Vanderbilt University have used id Software's Quake III Arena to test a model of the human prefrontal cortex. The model was injected into the control systems of a Quake Bot, allowing it to flexibly adapt to changing enemy characteristics. The bot was required to identify the vulnerability of its enemies to different types of weaponry through repeated combat trials. Not only are the bots busy shooting each other relentlessly, but you can catch the action by joining the battle as an observer. Source code and Quake virtual machines are available for download."

Comments

Caught

[JohnFluxx]

Sounds like they were caught playing quake during work hours, and had to make up an elaborate story :)

nah just kidding.. But from the /. blurb, it's not that cool if all they can learn is what weapon is best.

Re:Caught

[Hogwash McFly]

With my experience with bots from various FPS games on several platforms is that the bots autoswitch to the most powerful weapon and stick with it until they die and/or run out of ammo.

The result? A close quarter battle where the bot is trying to snipe you from four feet away when he has a shotgun in his inventory. Or a map with copious amounts of one weapon becoming a single weapon map (Rocketfest, Sniperfest etc.)

If a bot can select an appropriate weapon based on a multiple factors than it serves to add to more realistic bot gameplay. Have I just popped in to a dead end? Then the bot should bounce grenades into my little enclosure. Am I clearly running for the flag? Then the bot should line the corridor with bio sludge to hinder my efforts. Am I flying through the air from a rocket jump? Then the bot should try and place a rocket at my landing spot as well as/instead of trying to continually fire rails at me.

Re:Caught

[HTPC Junky]

I think this is a great step towards Agent Smith. Normal game AI is just scripted and predictable (boring). If this makes it harder to tell a person from a bot, then bring it on. I would love to see Half Life 2 with 32 internet players, and another 32 learning bots in the mix. I wonder how long before the bots consistency beat the real people!

Re:Caught

[Hogwash McFly]

Imagine if, in the near future, as well as a testing period, FPS developing houses have a 'learning period'. In this time there would be extensive testing of all maps/modes/mutators with just bot games. Over, say a one week period, the bots are left to their own devices, fragging 24/7, developing their algorithms on a daily basis as to become more and more adapted until at the end you, hopefully, have a very intelligent bot.

All you need are a little 'human' boundaries - +/- percentage of aiming error, +/- path deviation distance etc. defined at the start and you're set.

Re:Caught

[Devir]

that would be genetic algorithms. The menioned bots use what I believe is Neural network modeling specifically the frontal lobes of the brain. If genetic, neural and fuzzy algorithms could be merged into one bot you'd have one hell of a killing machine. of course you'd need some super computer to run them. Unless you only used the genetic algorithms for in house creation.

bots don't piss about or be irrational

[DrSkwid]

they day the bot switches to grapple and follows PCs round laughing at their hopelessness all the while grappling them to death I'll know their finished.

Or shooting someone with shotgun cos they'll fall backwards into the lava.

Or camp under the stairs when their bored

etc.etc.etc.

Output...

[wowbagger]

The output from this mod, after it has been running a while:

I frag, therefor I am.

How long until Valve adds this to HL2?

Perhaps this is what is holding up Duke Nukem Forever?

slow learners?

[den_erpel]

I just tried it for about 5 minutes (seems to me that this should be long enough for beasic learning), but the bots (with Quad colours) just seem to run around and do not react at all, no mather how many slugs I shoot at them.

I tried it with various settings of difficulty :( Am I mssing some README?

Re:slow learners?

[JBv]

Just a suggestion to make tthe pics clearer:

\seta r_vertexlight 1
\seta r_drawgun "0"
\seta com_blood "0"
\seta cg_brassTime "0"
\seta cg_drawCrosshair "5"
\seta cg_crosshairsize "24"
\seta cg_marks "0"
\seta cg_gibs "0"
\seta cg_blood "0"

Not Close Enough

[Acts of Attrition]

An interesting development, but if they really want to replace human players they still need algorithms for name-calling, complaining and cheating.

RE: I didn't read the article, but I ran the mod

[monkeyserver.com]

Ya, RTFM, the point of this isn't to make them good at kicking your butt. This bot is supposed to be pitted against two special dummy bots, name one and two. Then it can react to the bots chaning their sheild. blah blah blah, it's actually a very cool use of nueral nets, but you wouldn't know that unless you read it :)

Re:AI programming

[tamer*f]

The model of PFC that we used is a simple backpropagation artificial neural network with some modifications. Recurrent connections to layers with special activation weights enable the working memory and cognitive control functionality of the model. It would be a little much to clearly describe it here, but if you are interested you can check out http://psych.colorado.edu/~oreilly/pubs-abstr.html #01_id_ed -the original paper describing the model. I've made an effort to describe it in simpler terms on the site we are commenting on. There are plenty of neural net resources and sites on the internet. If you are interested in Game AI I suggest checking out the book "Game AI Programming Wisdom" edited by Steve Rabin. Even if it's too technical or you're too busy to use the techniques yourself it's interesting to see what's going on behind the scenes in your favorite games. Also, the source to our mod is available and includes some very simple and useful NN utilites written by my Professor. I believe I listed the names of those files at the bottom of the downloads page. Please read the GNU public license first. Hope this helps. -T

How to run the mod

[tamer*f]

It seems like it is a little unclear to some people how to correctly run our mod (largely due to me leaving out significant details on the download page). It is intended as an experiment involving one learning bot utilizing the PFC model and two special dummy bots. You need to make sure you run the game using the map I made so that the bots have constant interaction. Using the command line listed on the download page, start the game, and then switch yourself over to be an observer. Run the following console command: /idscenario

Now you have some very colorful dummy bots with unoriginal names running around doing nothing. But it gets better....

Use the console command /addannbot just like you would /addbot to put a learning bot in the mix. For best results, use a bot that doesnt suck. Now switch over to the learning bot's first person view to see the status of its Neural network and PFC layers changing as a result of its perception. Igor, its aliiive.

Now, there is no damage or death in the mod because we didnt want this to complicate the experiment. What you should see is a blue icon appear above an enemy that is hit. A deflected shot will bounce off like it hit the invulnerability sphere. When the bot hits, you will notice the little white box at the top of the network status overlay (upper right corner of the screen) go solid. This signals that the bot got a reward.

Directly under that are two yellow boxes, these represent how much the bot wants to choose each weapon (full is highest). Once the bot learns something you will notice these switching dramatically in response to the characteristics of its enemy. The bottom row of red boxes shows the characteristics of the current enemy (shield color, gun color, position, ID).

Now with all this information the bot tries to figure out what about its opponent is important in deciding how to kill it. The top row of yellow boxes at the left of the screen encodes what dimension the bot is considering, shield color, gun color, location, or ID(name). When the bot picks the right dimension, it can reliably slam its opponent with the right beam color. When it chooses the wrong dimension, it performs miserably until it gives up and explores something else.

Our experiment is set up such that the first correct dimension is shield color. After the bot figures it out the experiment will autoswitch to the ID dimension. When this happens you will see a message appear at the top of the screen in red. When its behaving well, the bot will catch on quickly.

Thanks for checking out the mod, and sorry about being late with this info. If you've got questions a lot is explained in the code walkthrough on the site, otherwise just ask me here. cheers,

-Tamer