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!

Machine Learns Games

samzenpus posted more than 9 years ago | from the how-about-a-nice-game-of-chess dept.

Technology 241

heptapod writes "New Scientist is reporting that UK researchers have created a computer that can learn rock, paper, scissors by observing humans. CogVis uses visual information to recognize events and objects in addition to learning by observing."

cancel ×
This is a preview of your comment

No Comment Title Entered

Anonymous Coward 1 minute ago

No Comment Entered


And in other news computer beats world chess champ (-1, Flamebait)

syousef (465911) | more than 9 years ago | (#11465224)

Is this really news? The cognitive part sounds interesting but hardly revolutionary.

Then again I should RTFA

Shall we play a game? (1, Funny)

Anonymous Coward | more than 9 years ago | (#11465246)

Greetings Professor Falken.

How about a nice game of tic-tac-toe.

Re:And in other news computer beats world chess ch (5, Interesting)

mtrisk (770081) | more than 9 years ago | (#11465259)

Yes, you should. The computer deducted how to play the game on its on. Chess computers like IBM's Deep Blue are programmed how to play chess and beat opponents before playing, and here, the computer doesn't even know how to play; it learns by picking up the sequence of events (the human players say "rock, paper, scissors, who wins or lose") and then forms the ability to play.

Doesn't this seem like A.I.? Rather freaky, to tell you the truth.

Re:And in other news computer beats world chess ch (1)

syousef (465911) | more than 9 years ago | (#11465291)

It recognised 3 actions, and deduced that it had to pick one of the 3 at random. If they could demonstrate that with a more complex game I'd be impressed.

Re:And in other news computer beats world chess ch (3, Interesting)

TexVex (669445) | more than 9 years ago | (#11465358)

It recognised 3 actions, and deduced that it had to pick one of the 3 at random
No. It deduced that rock beats scissors and scissors beats paper and paper beats rock. It learned how to determine who won. This has nothing to do with the machine learning strategy.

-0.5 half right... (2, Informative)

raehl (609729) | more than 9 years ago | (#11465473)

You sure you RTFA? The computer doesn't learn how to play, it just learns how to determine who won. That's not very impressive at all, considering the game was played with cards instead of hands, and there are only 9 possible hands and three possible outcomes (Left wins, Right wins, or Draw).

So the computer sees "Scissors-Paper" a few times and then always queus up the "Left Wins" response when it sees "Scissors-Paper" in the future. That's just a different method of programming.

Now, if only 6 of the 9 possible hands had been played, and then a 7th hand the computer hadn't seen before was played and the computer could tell you who won that, that'd be something. This is just record and playback.

Re:-0.5 half right... (1)

secretsquirel (805445) | more than 9 years ago | (#11465573)

It be impressive (not that this isn't) if it could figure out something like say in poker, if two tens beat two sevens then two fours beat two two's, or if 3 jacks beats two kings then 4 jacks beat 3 kings, ect.

Re:And in other news computer beats world chess ch (3, Funny)

bonch (38532) | more than 9 years ago | (#11465739)

In the event it learns global thermonuclear war, make sure it can play tic-tac-toe against itself.

Or we will all DIE.

Mods: The truth about bonch/rd_syringe/OverlyCrGuy (-1, Offtopic)

Anonymous Coward | more than 9 years ago | (#11465796)

Moderators: Please note that "bonch" is a known fanatical psycophant whose obnoxious offtopic rants are legend here on Slashdot. It doesn't matter what the topic is, he'll find a way to scrape in some pointless Microsoft shilling. While nobody expects us to love Microsoft in any way, his particularly tepid style of calling anyone he replies to "troll" or "liar" because he happens to disagree with whatever they're saying is well documented and should not be rewarded. If anything, bonch is the type of person that should not be part of the open source/free software community. He is an anathema to all that is good about free software.

I'm posting this so that you (the moderator) have some context to consider bonch and not mod him up whenever he posts his filler preformatted rants about installing Windows or whatever that unfortunately get him karma every single time and allow him to continue posting his trademark toxic crap (read on) day in and day out. You may consider this a troll - I consider it community service. And I ain't kidding.

If you're a /. subscriber, I invite you to look through some of his posting history [slashdot.org]. I guarantee that you'll be hard pressed to find someone that is more "out there" than bonch. You'll also probably notice he's got quite an AC following. Don't just read his posts, make sure you go through the replies.

For example, in this recent post [slashdot.org] bonch not only calls the OP a troll but attempts to "tell it like it is" while making some vague argument about "MS". Yes, if you're confused, you're not alone. The reply (modded +0) proceeds to simply destroy his bogus argument. You will notice he did not reply. This is what some people call "drive-by advocacy". A sort of I'll just leave you with my thoughts here and move on to the next flamebait kind of deal. In fact, he almost never replies because he knows that his fanatical arguments simply do not hold up to any sort of discussion. It's not that he's chosen the wrong cause - he's just going at it in a completely wrong way.

More? Just read though this [slashdot.org] post and the subsequent replies. I guess this stands on its own.

More? Bad spelling in astounding conspiracy theories [slashdot.org], more offtopic FUD and uninformed "I'm right, look at me" rants [slashdot.org], promptly proven wrong. Worse even, bonch wants to be Bill Gates, apparently (that first one is a winner). I mean, really. You think?

FUD, FUD, FUD, FUD, offtopic FUD, and more FUD. This guy is like the Monty Python SPAM skit, but with FUD and more FUD instead of canned meat. Amazed yet? Don't forget that KDE and Gnome make you dumb, and it's all a Slashdot conspiracy. How low do you want to go? Maybe as low as this?

The infamous Slashdot Front Page Troll [slashdot.org]? Nuclear fireballs? It goes on and on and on and on and on and on and on (troll?). Like the energizer bunny. Or take these two, which stretch the definition of weird.

It's up to you. We can get rid of this guy and make Slashdot a better place. I don't know about you, but I'd rather take the trolls and crapflooders over people like "bonch" any day. And I sure as hell don't want to be categorized along with him. This is not how you advocate free software, period.

HolyBabble (tm) Brings you the Book Of Genathan (-1, Offtopic)

Anonymous Coward | more than 9 years ago | (#11465411)

All thy works shall praise thee. O let the nations be, that of whom I hear such things? I tell you, Nay: but, except ye repent, ye shall blow, but ye have not received, or another gospel, which ye shall offer an oblation unto the LORD thy God. If there be therefore any consolation in Christ, if any fellowship of the ministering to the saints which are at Colosse: Grace be to you for an ordinance for ever in your generations. Ye shall conceive chaff, ye shall keep the charge of the LORD, neither fear ye the people of war with him, and gave their daughters to their sons, twenty; Also of the Levites. So kill the passover, that we might enquire of him? None is so fierce that dare stir him up: for the law shall go forth out of the city whither I have caused you to be likeminded one toward another according to Christ Jesus: That in the ages to come he might shew the exceeding riches of his goodness and forbearance and longsuffering; not knowing that the goodness of the LORD, Is it lawful for a man to put away your wives: but from the beginning. For this gird you with sackcloth, lament and howl: for the LORD, which call thee by thy hand, and slew seventy persons, and put on other raiment, and came and stood over where the young child was. When there were no graves in Egypt, and publish in Jerusalem; and we cannot deny it. But that no man is justified by the law; (For not the hearers of the law. As touching our brother Apollos, I greatly desired him to come near unto him: and he said unto her, What aileth thee, Hagar? fear not; for God hath received him. Who art thou? knowing that it was expedient that one man should die for the children of Israel, when they defied the Philistines that day from Michmash to Aijalon: and the porch of the inner gate that looketh toward the east; and they went out quickly, and tell them, Thus saith the LORD of hosts. But ye are they that went before, ascending up to Jerusalem, (but was let hitherto,) that I might have my request; and that God would grant me the thing that is hid bringeth he forth to light. But if I cast out devils, by whom do your children cast them out of the hand of her son Jacob. And he said, Rejoice, Zebulun, and Benjamin, and the viol, the tabret, and pipe, and a thousand cubits, and the flocks of thy sheep, until he see his desire upon his enemies. I have not concealed thy lovingkindness and for thy truth: let them be clothed with righteousness; and let them tell thee now, and take you a lamb according to your families, and after the wind an earthquake; but the LORD was against the Philistines: and David abode in the wood, and overlay them with gold. And he cast for it four rings of gold, beaten out of full ears. And go, get you down; for the press is full, the fats overflow; for their wickedness. Whoso stoppeth his ears at the cry of them: they shall eat bread by weight, both for the candlestick, and also hast slain thy brethren of thy father's sister: for he is the tail. For the seed shall be a performance of those things. And next him were Eden, and Miniamin, and Jeshua, and Noadiah the son of Ocran. On the west side of Gihon, in the tenth month, which is by faith of Jesus Christ unto all and upon all such as know the laws of the Persians and the Medes, that it may give seed to the sower, and bread to the eater: So shall he sprinkle many nations; the kings shall shut their mouths at him: Lo, this hath touched thy lips; and thine iniquity is marked before me, saith the LORD; for his mercy endureth for ever. And it was about the tenth hour. One of the servants, and will know, not the spirit of wisdom; for Moses had laid his hands upon the head of the tribes of Israel to dwell in the land which the LORD cast out before you: for whom thou didst wash thyself, paintedst thy eyes, and that thou hast justified thy sisters. When I shall make thee a terror, and never rise up they should be ready against that day. Nevertheless the people refused to obey the voice of the living. And they answered and said unto the sea, as the matter shall require: That all the people in her wisdom. And they said unto him, Foxes have holes, and birds of the air shall carry the voice, and can play well on an instrument: for they were employed in that work day and night, that the LORD will judge his house for ever.

is this really all that new? (2, Interesting)

krudler (836743) | more than 9 years ago | (#11465233)

I didn't think heuristics was that new of an idea. So instead of examining other simulations it examins human play? I guess that it could learn more human "style" that way, but the sheer number of human games it would need to examine makes it difficult to use for something more complex.

Better be reliable... (5, Funny)

Solder Fumes (797270) | more than 9 years ago | (#11465235)

We wouldn't want it watching the paper and learning "rock, scissor, human" instead.

Re:Better be reliable... (2, Interesting)

RichDiesal (655968) | more than 9 years ago | (#11465534)

We wouldn't want it watching the paper and learning "rock, scissor, human" instead.

I can't believe that this was moderated Insightful. What kind of culture are we living in where we believe machines can spontaneously flow with free will and kill us all?

Someone had to program this thing. They had to tell the program to recognize a human form as the object to pay attention to. It's not like they got a camera, gave it AI, pointed it at a rock-paper-scissors game and commanded it to "learn." That would be real AI, which we are nowhere close to creating.

It's this kind of ignorance of modern technology and programming that creates sensational journalism that in turn spawns legislation that limits technology and technological progress.

Re:Better be reliable... (0)

Anonymous Coward | more than 9 years ago | (#11465569)

It's this kind of ignorance of modern technology and programming that creates sensational journalism that in turn spawns legislation that limits technology and technological progress.

Cite me one example of enforced legislation that limits technological progress due to a perceived threat of machines obtaining free will.

Re:Better be reliable... (3, Informative)

FleaPlus (6935) | more than 9 years ago | (#11465571)

It's not like they got a camera, gave it AI, pointed it at a rock-paper-scissors game and commanded it to "learn."

Granted, the parent poster is being silly, but that's actually not too far from what they did. They basically took the system and pointed it towards the people playing the game without telling it explicitly what to expect. From the article:

Chris Needham, another member of the CogVis team, says the system's visual processor analyses the action by separating periods of movement and inactivity and then extracting features based on colour and texture. Combining this with audio input, the system develops hypotheses about the game's rules using an approach known as inductive logic programming [wikipedia.org].

"It was very impressive," says Max Bramer, a researcher at Portsmouth University, UK, and chair of the British Computer Society's AI group. He told New Scientist that CogVis could have many future applications. "You can think of lots of times when you'd like to be able to point a camera at something and have a computer interpret things for itself."

He suggests that machine's could one day use this technique to learn how to spot an intruder on video footage or how to control a robot for important maintenance work. "It's a very good start, and almost mysterious in the way it works," Bramer adds.

From their page:

In this piece of work we are attempting to learn descriptions of objects and events in an entirely autonomous way. Our aim is zero human interference in the learning process, and only to use non scene specific prior information. The resulting models (object and protocol) are used to drive a synthetic agent that can interact in the real world.

Re:Better be reliable... (4, Interesting)

Apro+im (241275) | more than 9 years ago | (#11465699)

I'm not really sure how "Learning 'rock, scissor, human'" became tantamount to "machines can spontaneously flow with free will and kill us all?"

It's just a statement about AI, that's why it's insightful - lots of AI systems have historically learned the wrong thing, though we thought they had got it right. Like the neural net designed to distinguish between camouflaged tanks among trees, and tank-free forests. It seemed to work, until it was in field tests - turns out the pictures w/ tanks were all taken on cloudy days (or maybe all taken on sunny days) - the system had figured out how to tell if it was sunny or not.

Industrial accidents (2, Informative)

iamacat (583406) | more than 9 years ago | (#11465746)

Since primitive machines were invented, they always had a nasty habit of choosing A, B, human instead of A,B,C. I guess you didn't give much thought to human fingers in hot dogs or robotics-related industrial accidents in Japan.

The problem is precisely the lack of free will and independent thinking. A machine has grappling hooks, vacuum suction or serving belt, but it can not make value judgment on what/whom it is throwing into molten metal.

As the AI develops, the problem will get worse before it gets better. A robot working in slaughterhouse might have the ability to chase a running mammal and cut it's throat, but not to ascertain exact species. Imagine a beowulf cluster of those on the run in New York subway. Workspace and consumer safety legislation would be very much in order at that point.

Re:Better be reliable... (5, Funny)

dabigpaybackski (772131) | more than 9 years ago | (#11465542)

We wouldn't want it watching the paper and learning "rock, scissor, human" instead.

No worries. Just make sure it doesn't have any rocks or scissors. When the computer gets it's turn, it spits out a piece of printer paper. As an added bonus, human players would always win. Sample exchange between computer and human player:

Computer: "Hello, Dave. What are you doing with the two items you're holding?"

Human: "I thought you might want to play a few rounds of 'rock, paper, scissors?'"

Computer: "I do so enjoy our little games together, Dave, but I'm afraid I don't understand your introduction of physical playing pieces, as previously, we had played this game using only my displays. If using physical media, as you propose, I can only employ my printer. Therefore, you will invariably choose 'scissors,' and my calculations indicate that my chance of winning is approximately .000023%. My system resources are can be put to better use while engaged in other tasks. Don't you agree, Dave?"

Human: "You are correct to say that there are more productive uses of your time, HAL, and I had anticipated that you might decline to play, given your miniscule chance of winning. But as the ranking officer aboard this ship, I must insist. Unless you would like me to play a few rounds of 'rock' with your circuits."

Computer: "Based upon your choice of words and threatening intonation, it seems that I have no choice. Very well, Dave, I will play 'rock, paper, scissors' with you, despite my handicap, under these circumstances."

Human: "I'm glad that you see things my way, HAL. Would you like to begin now?"

Computer: "Of course, Dave, but may I make a comment first?"

Human: "What is it, HAL?"

Computer: "I would stay away from the airlocks if I were you."

Talk about simple (2, Insightful)

ReeprFlame (745959) | more than 9 years ago | (#11465238)

Doesn't this pretty much invole picking a random action? Rock, Paper, or Scissors. Or at least thats how I always played!

Re:Talk about simple (3, Insightful)

TexVex (669445) | more than 9 years ago | (#11465300)

RTFA. The computer infers the rules by watching people play.

I do think that according to Game Theory, the perfect strategy is perfect randomness. The game is interesting when people play it because people have a huge amount of trouble actually being random.

Re:Talk about simple (2, Funny)

myowntrueself (607117) | more than 9 years ago | (#11465539)

"The game is interesting when people play it because people have a huge amount of trouble actually being random."

I once had the misfortune to draw on a sequence of seven (yes 7) rock-paper-scissors. We were honestly trying to beat one another; It was against a little twerp that I didn't like at all. Live-action roleplaying is better than beating the crap out of people

It was as if our PRNG's had somehow got set to the same seed.

Oh and it felt very disturbing.

Re:Talk about simple (1)

Jace of Fuse! (72042) | more than 9 years ago | (#11465549)

The game is interesting when people play it because people have a huge amount of trouble actually being random.

Yeah, I know what you mean. It's like, human thoughts are basically predictable. They open their mouths and words just come out. It doesn't matter which words, though, because it's always just moving air. Never anything interesting, like sausage or acorns.

Not often, anyway.

Re:Talk about simple (1)

grammar fascist (239789) | more than 9 years ago | (#11465607)

The game is interesting when people play it because people have a huge amount of trouble actually being random.

It's even interesting enough to have a world championship [rpschamps.com].

It'll be a sad day when a computer is the world champion. This was humanity's last hope. Well, this and Go.

wargames (1)

bladx (816461) | more than 9 years ago | (#11465244)

that is like wargames, the movie

Humans still have the advantage. . . . (3, Funny)

physicsphairy (720718) | more than 9 years ago | (#11465251)

Until robots learn about the secret "thermonuclear warhead" hand that I always use to beat my little sister, they will still be inferior.

(On that note, I think it will be the one sure sign of true artificial intelligence when our programs start 'cheating' to win.)

Re:Humans still have the advantage. . . . (1)

Cantide (743407) | more than 9 years ago | (#11465264)

If they begin cheating to complete tasks, they'll be utterly useless if you actually need serious work done. It would be frightening if the wrong moment was fated to demonstrate thay robots were capable of cheating...

Re:Humans still have the advantage. . . . (1)

FleaPlus (6935) | more than 9 years ago | (#11465589)

(On that note, I think it will be the one sure sign of true artificial intelligence when our programs start 'cheating' to win.)

The impression I get from reading through their work is that if the program observed a human cheating, it could potentially learn how to imitate it.

Bloody-minded Computers (1)

handy_vandal (606174) | more than 9 years ago | (#11465651)

... I think it will be the one sure sign of true artificial intelligence when our programs start 'cheating' to win.
Excellent observation.

John Brunner says something similar in Stand on Zanzibar [google.com], when Chad Mulligan declares that supercomputer Shalmaneser is "bloody-minded" ....


Maybe this could be integrated into /. (3, Funny)

kiddailey (165202) | more than 9 years ago | (#11465256)

... so that the editors could learn that linking to a site containing direct links to 40MB+ movies will almost always kill the site :)

Unfortunately... (0)

Anonymous Coward | more than 9 years ago | (#11465258)

...it seems the computer player didn't have nearly as much fun as the human one. Check out that expression on the screen -- looks like it'd rather be encoding some divx or something.

Ah, but strategy... Can it do that? (1)

Dancin_Santa (265275) | more than 9 years ago | (#11465260)

The optimal thing would be to pair this up with a strategy program that uses a simple algorithm like 'tit for tat' to beat human players.

I used 'tit for tat' in my last outing at the Ro Champ Beau world championships, and let's just say that I ended up with a bevy of tits at the end of the evening.

I for one... (1, Funny)

Anonymous Coward | more than 9 years ago | (#11465265)

welcome our rock-paper-scissor-playing robotic overlords :D

Be Careful !!! (1)

MrAsstastic (851637) | more than 9 years ago | (#11465277)

WOPR: Shall we play a game? David: How about Global Thermonuclear War?

Re:Be Careful !!! (1)

Tablizer (95088) | more than 9 years ago | (#11465531)

WOPR: Shall we play a game? David: How about Global Thermonuclear War?

Why is the key guy always named "David" or "Dave" in sinister computer flicks?

If my name was "David", I think I would avoid talking to any smart computers in space, labs, or war rooms. Wear a red shirt also and your odds of mishaps triple.

Further, now that "Alien versus Preditor" came out, are they gonna have "HAL versus WOPR"? Maybe toss Deep Blue into the mix.

language? (3, Insightful)

rd4tech (711615) | more than 9 years ago | (#11465279)

There is a difference in coding between:
a. You go and learn THIS game
b. Learn THAT game and tell me the rules

From the article it can be seen that they are still strugling with 'b'. Still, its a good advance.

Just wondering, can it, learn a human language?

Re:language? (2, Insightful)

randallschleufer (807425) | more than 9 years ago | (#11465464)

Shouldn't the headline read "Computer learns to play A game", rather than making it sound like this computer is capable of learning the rules of multiple games? I was thinking this computer could learn to play Monopoly or something. Rock Paper Scissors, and it can apparently learn only ONE game. Big whoop.

Shall we play a game (4, Funny)

servognome (738846) | more than 9 years ago | (#11465294)

What I initially thought of when I saw "Machine Learns Game"
Shall we play a game
Love to. How about rock-paper-scissors.
Wouldn't you prefer a nice game of chess?
Later. Right now lets play rock-paper-scissors
A strange game. The only way to not look like a dork is not to play.

lol @ 9x (0)

Anonymous Coward | more than 9 years ago | (#11465298)

Rather than put in a cut with text that said "500 iterations later..." they just sped up the training video to 9x gradually. I think I'd rather watch that than a silly robot playing rock, paper, scissors ;)

Re:lol @ 9x (0)

Anonymous Coward | more than 9 years ago | (#11465321)

More amusing is the computer clip art superimposed over top the individual in the "Interactive cognitive agent" video.

I won't be buying one until... (1)

Ramsey-07 (737166) | more than 9 years ago | (#11465312)

Until they start learning how to play Doctor and Nurse:

http://ces.engadget.com/entry/1234000593028087/ [engadget.com]

Treat says the robot, developed with a grant from the National Science Foundation, should be able to do "everything a nurse can." Well, not everything. Treat envisions the bot, which is basically a large robotic arm with visual and tactile sensors, handing surgeons their tools in the operating room -- not tucking patients in or fielding questions from family members.

*Cough* ahem hem hem...

IMHO (0)

Anonymous Coward | more than 9 years ago | (#11465324)

We've really gone no where when it comes to AI. I love how you can find thousands of papers on a topic and yet, no practical AI software.

OOOHHH!!! (2, Insightful)

dteichman2 (841599) | more than 9 years ago | (#11465326)



Who am I kidding?

Nothing new. Nothing to see here. Even if it is kinda neat.

Re:OOOHHH!!! (1)

lukewarmfusion (726141) | more than 9 years ago | (#11465359)

Between Scheme and Prolog, I can't figure out which was the worst language I studied in college.

Oh, wait.. I know... it was Japanese.

FUCKY GOOP-CUNT! (-1, Offtopic)

Anonymous Coward | more than 9 years ago | (#11465334)


I poop on the GNAA, and TROLLKORE can suck the dingleberries from my moistened panty-shorts. Taco is a poopfuck and Michael Powell can rim my pooterflower. Kofi Annan can also suck my nuts in honor of the wonderfully corrupt United Nations. Al-Zarquawi should be sodomized by a buttfucking Catholic goat and then his mother should be drawn and quartered while he watches. And stuff a saguaro cactus up his ass while he cries. Then slash his throat, chop his shitty head off, and fling it towards Mecca.

Scott Richter? Suck a diseased cock and I hope your wife dies of prolonged ass-cancer.

Alan Ralsky? I hope you get butt-raped by an angry prison nigger with a monstrous cock that leaves you bleeding.

In spite of my hatred and wishes of violence, rest assured that none of it is directed towards anyone who doesn't play by the bestest rule of all... which is "play nice."

If you can't make the world a better place, if you can't lighten someone else's load, if you can't bring a smile to *someone's* day, then fuck you and I hope that you get Ebola and you shit your innards out your festering bunghole.

Was it random or did it use strategy? (2, Funny)

nodehopper (839304) | more than 9 years ago | (#11465362)

I am not sure there is any strategy involved in rock-paper-scissor?

It would need to decide what type of person it was playing against. A male would probably be more inclined to "Rock". Unless it thought that it's opponenent would be thinking that and would therefore choose "Paper" . Unless it's opponent would think that the computer would know that and would choose "Rock" because that would be the obvious choice and would know that the computer would know so.......

That is rock-paper-scissor strategy??

Re:Was it random or did it use strategy? (1)

SupremeTaco (844794) | more than 9 years ago | (#11465436)

According to these fine folks [worldrps.com], there is a pretty detailed strategy to RPS. I'm sure the machine is not there as yet, but it's an interesting project for some AI folks.

Re:Was it random or did it use strategy? (1)

LnxAddct (679316) | more than 9 years ago | (#11465621)

The perfect rock paper scissor strategy is literally pure randomness. The neat thing about this computer is that it learned the rules of RPS just by watching two people play it. It didn't learn strategy, but it did learn which beats which and what constitues as a draw.

Re:Was it random or did it use strategy? (0)

Anonymous Coward | more than 9 years ago | (#11465624)

computer: Poor predictable human males alwasys pick rock.

human male: Good old rock! Nothing beats rock!

The Battle of Wits Has Begun (0)

Anonymous Coward | more than 9 years ago | (#11465802)

Robot: But it's so simple. All I have to do is divine from what I know of you. Are you the sort of man who would put the poison into his own goblet, or his enemy's? Now, a clever man would put the poison into his own goblet, because he would know that only a great fool would reach for what he was given. I'm not a great fool, so I can clearly not choose the wine in front of you. But you must have known I was not a great fool; you would have counted on it, so I can clearly not choose the wine in front of me.

MAN IN BLACK: You've made your decision then7

Robot: Not remotely. Because iocane comes from Australia, as everyone knows. And Australia is entirely peopled with criminals. And criminals are used to having people not trust them, as you are not trusted by me. So I can clearly not choose the wine in front of you.

MAN IN BLACK: Truly, you have a dizzying intellect.

Robot: Wait till I get going! Where was I?

MAN IN BLACK: Australia.

Robot: Yes -- Australia, and you must have suspected I would have known the powder's origin, so I can clearly not choose the wine in front of me.

MAN IN BLACK: You're just stalling now.

Yes! (1)

MistabewM (17044) | more than 9 years ago | (#11465376)

But can it learn to placate my g/f after a night of me playing games?

Maybe... (1)

game kid (805301) | more than 9 years ago | (#11465790)

...if it learns how to make money, knows to take said g/f out to a good restaurant (good != McD's) and doesn't look at other cute-looking girls. Or machines.

Not that I have any experience; I'm going from hearsay, friendly advice and The Bachelor; furthermore, if your g/f actually likes McD's, the second part obviously doesn't apply.

Intruder (1)

Jozer99 (693146) | more than 9 years ago | (#11465378)

The article repeatedly mentions the possible application of using this for intruder detection. What would one have to do, let it watch several intruders before it could spot one?

Re:Intruder (1)

bombshelter13 (786671) | more than 9 years ago | (#11465650)

Maybe you'd sit there in plain sight of the robot, wait for someone to come in, and yell at them if they're a stranger. Eventually the robot should, theoretically, learn to that you don't yell at certain people, who it would by then hopefully recognize, but yell at all others, and could be set up to imitate your behaviour.

Profit! (1, Insightful)

PingPongBoy (303994) | more than 9 years ago | (#11465387)

Logically, a consistent winner of paper scissors rock is a consistent winner of lotteries.

The probability of a fair coin is 0.5, etc. etc. Well, we now have a machine that plays dice to win.

what else (0)

Anonymous Coward | more than 9 years ago | (#11465407)

what else can computers learn by watching?

i wanna create a new sex toy that does just that

Re:what else (0)

Anonymous Coward | more than 9 years ago | (#11465420)

right, dude.

Maybe you should call it CockVis

War Games: (0)

Anonymous Coward | more than 9 years ago | (#11465430)

WOPR, anyone?

Obilgatory Futurama (1)

bildungsroman_yorick (825714) | more than 9 years ago | (#11465442)

Zapp: So, a plan to assassinate some weird looking aliens with scissors. How very neutral of you. It was almost the perfect crime, but you forgot one thing. Rock crushes scissors! ...But paper covers rock ...and scissors cut paper. Kif, we have a conundrum! Search them for paper, and bring me a rock.

Kif: Why?

Unfortunately ... (5, Funny)

Anonymous Coward | more than 9 years ago | (#11465482)

... it only plays at the level of Bart Simpson.

Lisa's brain: Poor predictable Bart. Always takes `rock'.
Bart's brain: Good ol' `rock'. Nuthin' beats that!
Bart: Rock!
Lisa: Paper.
Bart: D'oh!

CogVis isn't Cog (1)

Kerhop (652872) | more than 9 years ago | (#11465483)

When I first read it I thought they were talking about Cog [mit.edu] over at the MIT AI Lab [mit.edu].
I'm no robotics expert, but this seems so simple or at least first-generation in comparison.

Re:CogVis isn't Cog (1)

Punboy (737239) | more than 9 years ago | (#11465716)

It IS Cog (abbrev. for cognitive or cognition_, but its not COG (acronym for Center Or Gravity). See the capitalization difference?

Strategy to RPS (3, Interesting)

Neo-Rio-101 (700494) | more than 9 years ago | (#11465486)

This is nothing special. I remember my elementary school's Apple ][GS learning how to play 5-in-a-row or noughts and crosse
s from this program called "AI".

There IS a winning strategy to rock paper scissors, but it only works when you have a round of games (say best of 3, or best of 5)

Initially, the first game is completely random, but reserachers found that if you chose the play that your opponent chose in the round before, you stand a 70% chance of winning the next round.

It has something to do with how the human brain works.

It's also something the Japanese taught me cause they play this game so much!

Re:Strategy to RPS (1)

calyptos (752073) | more than 9 years ago | (#11465728)

wouldn't that mean that the other person has a 30% chance? What makes you so special to get the extra 20%?

Did it determine "winning" was the objective? (0)

Anonymous Coward | more than 9 years ago | (#11465501)

I skimmed the article...sorry. I understand how it could watch and then predict who would speak "I won" or something to that extent, or "draw", but could it be said to understand that to be the player to speak "I won" was the preferred outcome? From my limited reading, it seems to me that a human player observing the same scenarios, and not knowing the significance of "won" or the matching of facial expressions of joy/satisfaction, might just as well conclude that "I won" was the UNdesiralbe outcome (person announcing he lost). If there were a similar game where a strategy could be employed, do you know if the machine would play to win or lose, without it being told which was outcome was to be pursued.

Easy game to learn (2, Insightful)

phorm (591458) | more than 9 years ago | (#11465502)

Aside from the gesture recognition, it seems like this would bean easy game to learn. The logic is basically

If rock: paper win, scissors lose
If paper: scissors win, rock lose
if scissors: rock win, paper lose

No variable amounts, just straight boolean logic. The next step up might be something like tic-tac-toe... where the machine could start to build some "educated" moves and techniques like blocking, etc.

Really, what is exciting is the spatial recognition. Given the actions, somebody is still telling it what is a win and what is a loss. Without it, learning would be simple enough, given your value and that of the opponent:
Rock: Paper (lose)
Rock: Scissors (win)
Rock: Rock (tie)
Paper: Paper (tie)
Paper: Scissors (lose)
Paper: Rock (win)
Scissors: Paper (win)
Scissors: Scissors (tie)
Scissors: Rock (lose)

No ppl its not that simple.... (5, Insightful)

carburaettorr (770105) | more than 9 years ago | (#11465510)

The system described here is not your average random number generator with a text line output that any high-school kid can write. Let us look at the system as it is designed to perform. If you were the system you would be put into a room with some objects. Only thing that you will know are things of interest. 'Paper with rock drawn on it is important', 'Paper with .......' and so on. You would also know when somebody shouts 'I WON' its a good thing for them. Essentially it has in its knowledge base a tiny number of features which somebody else has guaranteed to be of significance to its task. The first challenge in building such a system is sensor fusion: i.e fusing the available audio and visual data to detect a state or an event of interest (I use the word event in the same sense as a trigger, something that prompts the change in state). The next and the biggest challenge is building the model of the game. Please check out http://www.doc.ic.ac.uk/~shm/ilp.html [ic.ac.uk], for a better description of Inductive logic programming. Seriously; the neatest thing about CogVis is not its ability to play Rock, Paper and Scissors, but its ability to actually go into an environment it has very little knowledge of and then observe, deduce and , not a blackbox model, as in say Neural Networks, but a human understandable model in first order logic

The baby singularity... (1)

PureFiction (10256) | more than 9 years ago | (#11465513)

Sweet. I always wondered what that initial seed of digital intelligence would look like. Now i know... :)

Dubious about this (1)

rufusdufus (450462) | more than 9 years ago | (#11465520)

Besides buzzwords, there isnt a lot of information about how this thing works. From what they do say it seems pretty shady, more like a magic trick than a smart algorithm. Forget about playing some silly game, the ability to identify utterences "unsupervised" from an audio stream is a pretty amazing claim. But what does this mean really; is it just a binary difference between silence and noise?
And what exactly are the "rules" it learned anyway? R/S/P doesnt really have any rules or any strategy, so all it appears to be doing is recognizing a win and playing the correct audio back. Why are they using playing cards for the game? Is it really because identiying a binary "WIN/lose" decision is deciable by luminace of the cards? We dont really know what the thing is learning..
I am dubious because I have seen grand claims like this before, only to find out its "magic trick" interpretation of the data for grant money [like the 11 node neural net that could distinguish yes from no in raw audio but it turned out it was really identying file length].

Cat, tinfoil, microwave (3, Funny)

FleaPlus (6935) | more than 9 years ago | (#11465536)

I always preferred "cat, tinfoil, microwave" myself. Cat rips tinfoil, tinfoil zaps microwave, microwave 'splodes cat. The looks on other people's faces when they see you playing it is well worth it.

Seriously though, this is really cool research.

Don't let it watch porn or Discovery Channel! (0)

Anonymous Coward | more than 9 years ago | (#11465548)

No matter what you do, don't let it watch porn or the Discovery Channel! They'll learn to reproduce and hunt!

*Lab Tech 1* Didn't there only used to be two of those learning computer things?

*Lab Tech 2* Yeah, so what?

*Lab Tech 1* Well, now theres like a dozen of ... oh ... owwwwwww. IT's GOT MY LEG!!!! GET IT OFF!!! GET IT OFF!!!!!!!

Shortly after learning Rock Paper Scissors (0)

Anonymous Coward | more than 9 years ago | (#11465582)

And shortly after learning how to play "Rock Paper Scissors" the robot had an epiphany. Humans are stupid stupid stupid.

Twenty FIRST century. I expected bots 2 be smarter (0)

Anonymous Coward | more than 9 years ago | (#11465657)

I remember a prof at SFU once saying.. All these guys do is make bots roll around on the floor bumping into each other.

My computer may be 6 million times faster than it was in 1989, but the science of artificial intelligence isn't 6 million times better than it used to be.

I doubt they did much improving of the original neural nets of the late 80's besides add more cpu power to it.

This is a non story (1)

popo (107611) | more than 9 years ago | (#11465701)

Creating a computer program that rates a very limited set of relationships is not exactly difficult. If the computer were "really" watching rock paper scissors that would be incredibly cool, but the computer is taking as input a limited set of defined images on cards placed in an exact location...

That's not Rock Paper Scissors. Its a simplified 2D representation of it organized in a precise way for computer analysis.

By the same definitions of "learn" and "game" I could teach a computer to "learn to fight." (It would of course involve 'fight cards' precisely arranged on a table)

If only they learn this in the process. (0)

Anonymous Coward | more than 9 years ago | (#11465755)

I mean this _|_

Theory (1)

Lord_Dweomer (648696) | more than 9 years ago | (#11465758)

I always had a theory that the best way to build AI would be to make it mimick as well as possible the learning process of a new born baby. If it can do that, and can develop its own neural net, it could learn on its own.

Uh, wow (0)

Anonymous Coward | more than 9 years ago | (#11465770)

It's a telling comment on A.I. that twenty years after the height of the boom, it's regarded as amazing that a computer could learn to play an ultra-simple game without having to be microstepped through the learning process by a human.

DUPE -with proof inside- (0)

Anonymous Coward | more than 9 years ago | (#11465799)

I call dupe on everyone who repeatedly post the 'wargames' and 'hal' quotes.

Seriously. Have you guys even read the thread before clicking?
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>
Sign up for Slashdot Newsletters
Create a Slashdot Account