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."

is this really all that new?

[krudler]

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.

Re:And in other news computer beats world chess ch

[mtrisk]

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

[TexVex]

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.

Comment removed

[account_deleted]

Comment removed based on user account deletion

Re:Better be reliable...

[RichDiesal]

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...

[Apro+im]

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.

the Roshambot

[Kafir]

If you'd like to play rock-paper-scissors against a computer, there's always the WWW Roshambot [stanford.edu]. It's not at all related to the CogVis project, but interesting in its own right:

The WWW Roshambot utilizes an Artificial Intelligence algorithm in order to determine the optimal move for each round. It does NOT cheat (i.e. it does not use your move on the current round to determine it's move for the current round), nor is it random (except on the first move).

Presumably if it played against Bart Simpson it would learn to always pick paper.

RoShamBo and Data Compression

[shadowmatter]

As a fun aside, I found this [berkeley.edu] 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."

Anyway, try it out. In the long run, it kicks my butt. I try to make 'random' decisions, but still go below .500 -- which is interesting, because that implies that perhaps subconsciously we're always applying patterns...

- sm