Slashdot Mirror
Machine Learns Games
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."
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.
Tiger Hand!?.
Your hair look like poop, Bob! - Wanker.
We wouldn't want it watching the paper and learning "rock, scissor, human" instead.
Haven't we learned anything from the new Battlestar Galactica?
Doesn't this pretty much invole picking a random action? Rock, Paper, or Scissors. Or at least thats how I always played!
_
Free 27" Sony WEGA TV
that is like wargames, the movie
Greetings Professor Falken.
How about a nice game of tic-tac-toe.
(On that note, I think it will be the one sure sign of true artificial intelligence when our programs start 'cheating' to win.)
When things get complex, multiply by the complex conjugate.
... so that the editors could learn that linking to a site containing direct links to 40MB+ movies will almost always kill the site
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.
Without a proper flamewar, Anonymous was undecided on what shell to run.
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.
welcome our rock-paper-scissor-playing robotic overlords :D
... that beyond what 3 motions can be played there was any "learning" involved in rock paper scissors.
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?
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.
These posts express my own personal views, not those of my employer
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
Fine
A strange game. The only way to not look like a dork is not to play.
D6 63 0D 70 89 81 BB 8E 7B 7C 5F 5D 54 EA AB 73
pray it never learns ro-sham-bo "machine..go...first" *goomph*
MORE FUZZY-LOGIC/INFERENCE ENGINE! GO PROLOG-AND-LIKE!
Meh.
Who am I kidding?
Nothing new. Nothing to see here. Even if it is kinda neat.
Silence is golden... and duct tape is silver.
You'd understand if you got to know my history with games.
Blessed are the pessimists, for they have made backups. -- 0 1 My two bits
How long before we have a man-vs-machine RPS championship
D6 63 0D 70 89 81 BB 8E 7B 7C 5F 5D 54 EA AB 73
Fun with Anagarams! LADS HOST, SHALT DOS. HAS DOLTS. AD SLOTHS, HATS SOLD. ASS HO, LTD.
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??
"We will remember not the words of our enemies, but the silence of our friends. " Dr. Martin Luther King, Jr.
But can it learn to placate my g/f after a night of me playing games?
"A learning experience is one of those things that says, 'You know that thing you just did? Don't do that.'" - DNA
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?
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.
Know your pads. One time pad: good for cryptography. Two timing pad: where to take your mistress.
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?
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.
paintball
y
How about global thermo-nuclear war?(Y/n)
... 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!
When I first read it I thought they were talking about Cog over at the MIT AI Lab.
I'm no robotics expert, but this seems so simple or at least first-generation in comparison.
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!
READY.
PRINT ""+-0
Yes, but can it cheat by throwing dynamite?
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)
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, 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
Damn it everybody I know has an awesome sig.
Sweet. I always wondered what that initial seed of digital intelligence would look like. Now i know... :)
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].
So it learns that it should pick at random. Cool...
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.
Table-ized A.I.
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.
even paper!
eat shiat and bark at the moon
Paper beats rock!?! Does not compute.
John Brunner says something similar in Stand on Zanzibar, when Chad Mulligan declares that supercomputer Shalmaneser is "bloody-minded"
-kgj
-kgj
Yes, but can it play "rock, paper, scissors, sucker-punch to the neck"?
garble
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)
------ The best brain training is now totally free : )
In the event it learns global thermonuclear war, make sure it can play tic-tac-toe against itself.
Or we will all DIE.
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.
Buy Steampunk Clothing Online!
...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.
You can hold down the "B" button for continuous firing.
always like to pick games they can win at. Whenever anyone wants to play rock-paper-scissors or chess they computers all gather round to spank the pathetic humans. But they're always late for an appointment whenever I bring out my Go board =p
Ok, ok, I have to admit that that was a lame attempt at whoring some karma. Sorry!
I also feel that I must confess that I have multiple personality disorder and use two other accounts to troll from. I'm a frustrated musician and a wannabee programmer who works phones for a help desk. I really hate anything open source since it means that I'll be out of a job (miserable as it is). I have no life, and even the people that used to like me think I'm a dick. I haven't been laid in seven years and as such I take out my sexual frustrations by obsessing over anyone who says anything negative about Microsoft, Bill Gates, Steve Ballmer, Fox News or the Republican Party. Even if it's true! I can't help myself! People keep telling me that I should get some professional help, but I just never seem to get around to it.
Thanks for listening. This has really been weighing heavily on me for the past year or so and I feel much better now having cleared the air. But if you want more confessions, look here to satify your curiosity.
I'm bonch and I'm a troll
I'll be impressed when the computer learns to play 'Cat, Tin foil, Microwave'
Presumably if it played against Bart Simpson it would learn to always pick paper.
If you actually want to understand what they did, some research publications put out by the CogVis lab have better information regarding the technical side of things.
Towards an Architecture for Cognitive Vision Using Qualitative Spatio-temporal Representations and Abduction (Cohn et al, 2003)
Modeling interaction using learnt qualitative spatio-temporal relations and variable length Markov models (Galata et al, 2002)
Its amazing that this is possible! I read the article and couldn't believe it. Cognitive recognition is one of the first stepping stones to proper artificial intelligence.
Yet when AI reaches the point that it becomes almost human-like, problems are going to form. If the programming of an AI system leads itself to thinks it understands that it is sentient, would it mean that the AI is in fact sentient?
After all, intelligence is intelligence. By any means, an electrical intelligence could be regarded equal, because the only difference between us and "them" would be that we use a chemical and electrical method of processing data, whereas atrifical intelligence-based systems would be using purely electronic methods.
Surely, if input (a video stream coming from an optical sensor, such as a human eye or a digital video camera), and auditory input (ears, or microphone-based) which gets processed (human brain, or CPU) and then output (screen, face, voice, speaker, etc) should not be perceived differently. Humans are data processors (data in, data out in the form of a reaction). Advanced Computer AI would be the same (data in, data out).
Would humans really be that special then?
As a fun aside, I found this RoShamBo (a.k.a. Rock, Paper, Scissors) Programming Competition entry that guesses what action is optimal based on Lempel-Ziv data compression. As the author explains, "there exists a duality between data compression and gambling. The basic idea is that if you have a sequence of data which you can compress well then the data must be predictable in some sense."
.500 -- which is interesting, because that implies that perhaps subconsciously we're always applying patterns...
Anyway, try it out. In the long run, it kicks my butt. I try to make 'random' decisions, but still go below
- sm
Like Doom III or GTA... let the machines play the games, and then we can finally get some work done!
Am I missing something (the article didn't really explain it well enough for me), or is this not simply a case of pattern recognition?
Presumably, at the early stages of its learning, it has to be told who won which game, or at least be given some way of knowing who the winner was.
Given that, is it not simply a case of 'computer sees image of hand A with 2 fingers up and hand B in the shape of a fist, and having previously been told that this image means a win for B, can deduce the same thing again.
They learn how to win against all other (including humans) just by playing against themselves with an additional teacher (a program) who tells them, if the have won or lost. ...g ammon.html
Tesauro with his TD-Gammon was the first one
search on Goolgle for it, or try this one:
http://satirist.org/learn-game/systems/gammon/td-
Would you like to play a game?
I think what he was trying (and failing) to say was that THIS game is on specific type of game the machine can learn. THAT game refers to any one of the set of all possible games - an impossible feet arguably. I think it would be nice if they could take this project further and create a machine that can learn any game similar to rock, paper, scissors. So I could just invent a game out of my head that requires hand gestures and the machine could learn it.
The only problem with that is that it's a lot easier trying to predict the actions of someone who is trying to predict your next move and counter it.
My own observation is that most people tend to throw "Scissors" at the first time. So, the "Rock" is more likely to win. This is because if you look at your hand's position for every figure, you can see, that "Rock" is completely closed hand, "Paper" -- completely open. "Scissors" is the average, that is why average person chooses it.
May Peace Prevail On Earth
those damn 250 meg hard drives fill up so fast though!
..on my Commodore PET..
5 PRINT "HELLO, I AM THE HAL 9000 COMPUTER."
10 INPUT "WHAT DO YOU CHOOSE (ROCK, PAPER, SCISSORS)";I$
15 I = 0
20 IF I$="ROCK" THEN I = 1
30 IF I$="PAPER" THEN I = 2
40 IF I$="SCISSORS" THEN I = 3
50 IF I=0 THEN PRINT "I'm sorry Dave, I'm afraid I can't do that.":GOTO 10
60 ME = INT (RND(1) * 3) + 1
70 IF I=ME THEN PRINT "SNAP!" : GOTO 10
80 IF ME-I = 1 OR ME-I = -2 THEN GOTO 110
90 PRINT "You win. Dave...my mind is going...I can feel it...I can feel it."
100 GOTO 10
110 PRINT "Are you sure you are making the right decision? "
120 GOTO 10
ps. The HAL-9000 rock/paper/scissors emulator is untested & supplied "as is". The software algorithms used above ("choosing 1 of 3 random numbers, US Pat 124710947") are (P)(C)(T)adeyadey, $1 payable for each time you run it, look at it, or think about it when sitting on the bog.
"You lied to me! There is a Swansea!"
Haven't you ever played Metal Gear Solid? Cheating is already here.
Mercy was given to me by Christ...I must give the same to others.
Against random play, it doesn't matter what you choose, because the results will always be random.
You could always choose "rock", or have a looping pattern or anything else, but against a purely random opponent, you will both statistically tie.
It's because Dave is -the- traditional Comp Sci name. We had no less than three in a 12-person company when I started work in IT, and the name-coverage in Uni was worryingly similar.
Calling out "Hey, Dave!" in a crowded Comp Sci lecture theater is not a useful action...
I'm sure they spent a lot more time trying to give the computer a 3D face than they did on the actual algorithms. Come on, seriously. Why do we even need that? Stupid publicity photos.
I have no shame
Saying Apple is better than MS is like saying Botulism is better than rabies.
I think he might have been trying to quote The Simpsons.
Bart thinking: "Good old rock, nothing beats rock."
Lisa thinking: "Poor predictable Bart, always chooses rock."
I'm going to dust off by Commodore 64 tonight and create the BASIC program that'll randomly pick one of three options: Rock, Paper Scissors. SHouldn't be more than 5-6 lines.
Do I get mention in Scientific American too?
The visual recognition part is impressive, but learning the game does not impress me. I mean, come on! Computers were psychic back in the 80's and would tell us what animal we were thinking of.
I love my sig.
But alas, like so many other AI experiments, they probably wouldn't dare release the details of their experiment. So this will probably never rise to the level of credibility even if it does work.
Forget tic-tac-toe... it better know D&D.
I keep my
It was kicking my ass for the first 15 games, then I started beating it. I stopped at 30 games, but my win % was about 40% to its 20%, so I would have had to lose 6 and tie the other 4 for it to beat me over 40 games.
...I thought the first thing they were supposed to do is teach it to sing "Daisy"
Toronto Man Becomes 2002 International Rock Paper Scissors Champion Rock beat Scissors in the Winning Throw in Toronto Last Night Toronto, ON - Nov. 17, 2002...The World Rock Paper Scissors Society is pleased to announce that Pete Lovering from Toronto, Canada is the 2002 International Rock Paper Scissors Champion. Mr. Lovering beat 255 competitors for the Championship trophy, $1,200 in prize money, an Xbox game system, and the gold medal in the International Championships held in Toronto on November 16.
In the final game, Lovering played a combination of Rock, Paper, Rock, Rock to take the Championship title in front of an enthralled and vocal audience. Lovering won three out of five sets against the Silver Medalist as the audience cheered, jeered and chanted the competitors' names.
"For the first time, our experienced, international players competed against unranked players in an open tournament," said Graham Walker, Event Chair. "This made for some tense and exciting tournament play, with some of the more seasoned players knocked out earlier than expected by fresh talent. I hope to see players of this ilk compete in next year's Championships."
Throughout the evening, more than 600 competitors and spectators filtered through the doors to witness or participate in the tournament.
"The key to my win was maintaining a clear mind before each throw, and judging each opponent individually," said Mr. Lovering, 2002 International World Rock Paper Scissors Champion.
As the governing body of the sport of Rock Paper Scissors, the World RPS Society (www.worldrps.com) helps to set the strategic direction of tournaments, conferences, symposiums and retreats across the Globe.
This machine learns how to referee games, by structured watching. Though I'm a longtime fan of RPS, I know that there's little to learn in strategy except cute names, and timing the throws more (or less ;) simultaneously. The only skill to learn here, which itself is quite impressive, is recognizing which player has won. Frankly, I think that role is more important for a machine, as long as the players agree to its authority.
--
make install -not war
... they rebelled ... ... they evolved ...
Why, oh why, didn't I take the Blue Pill?
The server hasn't tanked due to /.
1011010110001101 cats = 0
0101101000110010 s/cat/human
1011001001101010 exec
Why, oh why, didn't I take the Blue Pill?
If you're interested in this story, you should read the book Blondie24.
It's been awhile since I read it, so I apologize for any inaccuracies in my recollection.
The book is about a couple of guys who set out to make a checkers playing program. Only, they didn't just hard code in the rules for checkers, they gave it as little actual checkers information as they could. Then they had it watch, and learn, and play, and watch, and learn, and play... eventually the program started catching on and became a fairly adept checkers player. The program learned to recognize certain patterns and board positions on its own, and learned to weight certain positions and moves based off what it "observed". After doing that enough it had compiled its own ruleset for playing checkers.
I thought that was an excellent way to go about making an AI for a game. I'm a big believer in the bottom up approach, and this book demonstrates that approach wonderfully.
It's certainly not as fast as just hard-coding the rules, or giving it a table of end-game moves, (which it sucked at for awhile) but it is a very innovative, and interesting, (to me) approach.
Wyrd One
But will it learn to say: "WTF? How can paper beat a rock?"
Mike van Lammeren
It will challenge your head, your brain, and your mind.
Sorry for my misunderstanding, but couldn't the computer just generate a random variable to play the game? After all, the game is just about luck in a sense. If someone has a more in depth explanation of this, please stop me from making myself look foolish.
"Instant gratification takes too long." - Carrie Fisher
Not to take the defense of anyone. But why hide behind AC ?
This is a stolen sig.
Good ol' rock ... nothing beats rock.
Gamingmuseum.com: Give your 3D accelerator a rest.
Make it watch all the "Super Computer Takes Over the World" movies, Colossus, War Games, etc... and then see what it learns....