Re:Show HN: Play rock paper and scissors against a untrained...
by atum47 on Thursday July 25, 2019 @10:58PM
(#20531994)
after the player makes a move the nn makes ones and add it to it's training data. the move the player does after that is added as a counter move to the nn move. this way I treat the data as time series.
[ Parent
| on HN ]
Re:Show HN: Play rock paper and scissors against a untrained...
by akovaski on Friday July 26, 2019 @12:11AM
(#20532295)
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.
Re:Show HN: Play rock paper and scissors against a untrained...
by klenwell on Friday July 26, 2019 @12:56AM
(#20532448)
If true, this seems like it would be a huge scandal. Or at least an issue in Github.
Re:Show HN: Play rock paper and scissors against a untrained...
by atum47 on Sunday July 28, 2019 @02:23PM
(#20549029)
it's not taking a pick at the player move. read the code, even after the pull request that brought this up the nn performed the same. even if the nn was taking a pick at the player's move, which is not, the data is shuffled before the training
Re:Show HN: Play rock paper and scissors against a untrained...
by GrumpyNl on Friday July 26, 2019 @09:21AM
(#20534557)
Isn't this just plain cheating?
Re:Show HN: Play rock paper and scissors against a untrained...
by camjohnson26 on Friday July 26, 2019 @01:42AM
(#20532638)
I took a stab at fixing this:
https://github.com/victorqribeiro/jokenpo/pull/3
Re:Show HN: Play rock paper and scissors against a untrained...
by seventytwo on Friday July 26, 2019 @05:22AM
(#20533464)
Well, it’s much easier with your code. I immediately opened up a 3x lead on the comp. I stopped at 17-6-17 (W-L-T). What I did was to play the hand that would have beaten the computer’s previous guess, and if the computer looks like it’s figuring it out, I play the hand that beats my strategy once or twice, and then resume.
Re:Show HN: Play rock paper and scissors against a untrained...
by scottlocklin on Friday July 26, 2019 @07:34AM
(#20533967)
He should hook it up to the stock market.
Re:Show HN: Play rock paper and scissors against a untrained...
by jerf on Friday July 26, 2019 @09:44AM
(#20534716)
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...
by 6gvONxR4sf7o on Friday July 26, 2019 @10:03AM
(#20534864)
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...
by jerf on Friday July 26, 2019 @12:19PM
(#20535922)
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...
by atum47 on Thursday July 25, 2019 @11:03PM
(#20532016)
I think it's fair, cause it's like the neural network is thinking "after I play rock the player plays paper" and train with that data
Re:Show HN: Play rock paper and scissors against a untrained...
by j-pb on Friday July 26, 2019 @02:19AM
(#20532780)
But that's not what you're coding.
If you trained it with every possible next move and response then you would learn that kind of relationship (though you would also overfit on the existing moves), but this way you just give it a peek into the probability distribution of the players moves, one thats so accurate that it comes from the future...