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.
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
(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.
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?
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
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.
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.
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
... 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!
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
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.
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.
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.
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
Yeah, they solved that problem a long time ago. It's called a vibrator.
Well, it could just watch several people *pretending* to be intruders.
When presented with a new game, the first thing you do is learn how to play. The second thing is to learn the best strategy to win. This is just concerned with the first part and that's the novelty - looking at human actions and learning what they're doing, not necessarily how to beat them.