Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Play rock paper and scissors against a untrained neural network

github.com

Post reply on HN
Print view View original

51–60 of 64 posts

Re: Show HN: Play rock paper and scissors against a untrained neural network

#51

Post by GrumpyNl »

klenwell wrote: post #30
akovaski wrote: post #27

Earlier quoted context omitted.

The problem is that that the player's move is actually being fed to the training data before the computer makes its prediction. Take a look at the variable 'y' after making your move and you'll see that it includes the player's last move. Because 'y' is updated before the computer makes its prediction, this shows that the computer uses the player's current move as part of the training set to decide its move.

If true, this seems like it would be a huge scandal. Or at least an issue in Github.

Isn't this just plain cheating?

Re: Show HN: Play rock paper and scissors against a untrained neural network

#53

Post by jerf »

scottlocklin wrote: post #49
akovaski wrote: post #27

Earlier quoted context omitted.

The problem is that that the player's move is actually being fed to the training data before the computer makes its prediction. Take a look at the variable 'y' after making your move and you'll see that it includes the player's last move. Because 'y' is updated before the computer makes its prediction, this shows that the computer uses the player's current move as part of the training set to decide its move.

He should hook it up to the stock market.

If it were that easy to beat the stock market, it wouldn't be that easy to beat the stock market. (Not a joke or snark.)

Re: Show HN: Play rock paper and scissors against a untrained neural network

#54

Post by 6gvONxR4sf7o »

jerf wrote: post #53
scottlocklin wrote: post #49

Earlier quoted context omitted.

He should hook it up to the stock market.

If it were that easy to beat the stock market, it wouldn't be that easy to beat the stock market. (Not a joke or snark.)

Two economists – one young and one old – are walking down the street together:

The young economist looks down and sees a $20 bill on the street and says, “Hey, look a twenty-dollar bill!”

Without even looking, his older and wiser colleague replies, “Nonsense. If there had been a twenty-dollar lying on the street, someone would have already picked it up by now.”

(99% joke and snark. Of course this isn't going to work on the stock market, but that kind of efficiency argument isn't perfect.)

Re: Show HN: Play rock paper and scissors against a untrained neural network

#55

Post by mikeash »

make3 wrote: post #26
sagebird wrote: post #18

I wonder about an arms race between two advanced AI’s which play RPS. I can’t fully put my head around this, but what would it be like if each AI could read the architecture of the other’s brain before each move. The AI’s would be permitted to reconfigure themselves as they play. An “obvious” strategy may be to simulate your opponent and ask what they are likely to play. Though, simulating their behavior is likely to…

don't you just end up with a (discrete) uniform distribution on both sides? anything else can be exploited by the opponent

Yep, RPS is only interesting to the extent that the players are imperfect. It’s most interesting as an illustration of how bad people are at behaving randomly.

Re: Show HN: Play rock paper and scissors against a untrained neural network

#56

Post by brokensegue »

jchw wrote: post #14
EGreg wrote: post #13

Earlier quoted context omitted.

That sounds like the gambler’s fallacy. Less runs than what? Most truly random input haa far more runs than what people “think” is random, and in fact that’s one of the statistical tests for whether a data set was random. You’re essentially saying that a good neural network can predict the next value of a good random number generator. Good luck with that one! Maybe while you’re at it, have neural networks invert cryp…

Here’s what I’m thinking: The neural network doesn’t have to be correct about which one you pick, it has to be correct about which you don’t pick. Only one option they pick is a loss, so if the other party can be somewhat certain you won’t pick a specific option, it can at least tie. So if a randomizer has pretty even distribution, I think it can win more than half the time, because it can gather roughly how likely t…

> So if a randomizer has pretty even distribution, I think it can win more than half the time, because it can gather roughly how likely the same choice is to be played in a row.

No.

Re: Show HN: Play rock paper and scissors against a untrained neural network

#57

Post by sambroner »

atum47 wrote: post #52

I have merged the first pull request that changes to the prediction first training after.

Nice. Seems to beat me. I performed significantly better when I used random.org to generate numbers than when I played with my own attempt at randomness.

Re: Show HN: Play rock paper and scissors against a untrained neural network

#59

Post by jerf »

6gvONxR4sf7o wrote: post #54
jerf wrote: post #53

Earlier quoted context omitted.

If it were that easy to beat the stock market, it wouldn't be that easy to beat the stock market. (Not a joke or snark.)

Two economists – one young and one old – are walking down the street together: The young economist looks down and sees a $20 bill on the street and says, “Hey, look a twenty-dollar bill!” Without even looking, his older and wiser colleague replies, “Nonsense. If there had been a twenty-dollar lying on the street, someone would have already picked it up by now.” (99% joke and snark. Of course this isn't going to work…

I was not making the efficiency argument in the abstract. I'm making it in the concrete of a neural network that can be trained in real time in a browser window.

There's a great deal of people who seem to mistake "the market isn't actually 100% efficient" for "oh, I guess we can just ignore the question of 'efficiency because if it's not 100% it must be 0%". Not that they say the last part out loud, of course.

Re: Show HN: Play rock paper and scissors against a untrained neural network

#60

Post by timfoden »

sagebird wrote: post #18

I wonder about an arms race between two advanced AI’s which play RPS. I can’t fully put my head around this, but what would it be like if each AI could read the architecture of the other’s brain before each move. The AI’s would be permitted to reconfigure themselves as they play. An “obvious” strategy may be to simulate your opponent and ask what they are likely to play. Though, simulating their behavior is likely to…

There's a site where AIs play RPS on an ongoing basis http://www.rpscontest.com/. Source code of the entrants is available. My best bot (called paper6) http://www.rpscontest.com/entry/5640686850277376 wins on average 67% of the time, but the top bots win around 80% of matches.
Post reply on HN