jokenpo
AI
game playing neural network
SHOW HN2019
101points
63comments
#482of 2,195 in 2019
Top 22%of 2019 by points
How HN took it
RoastedHalf or more of the comments are critical
1 positive, 11 neutral or asking, 0 mixed, 13 critical, out of 25 comments about the project. Thread score -0.37.
Execution: 1 for, 7 againstPerformance: 0 for, 4 againstIdea: 0 for, 2 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Surprisingly good opponent
From 1 comment
Wow it's surprisingly good
thirdmeow on HN
Objections
Training includes the player's current move before prediction, so it cheats
From 3 comments
Looking at the source code, the move you are about to make is included in the training dataset. This can be confirmed by playing “scissors scissors scissors rock” and then…
QuadmasterXLII on HNThe 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…
akovaski on HNI hate to say it, but I’m not sure it’s playing fair. I used random.org to play truly randomly, and the “neural network” beat me to 10 pts 6 times in a row.
QuadmasterXLII on HN
Beats random play more often than chance allows
From 3 comments
I hate to say it, but I’m not sure it’s playing fair. I used random.org to play truly randomly, and the “neural network” beat me to 10 pts 6 times in a row.
QuadmasterXLII on HNYeah, I am not sure what is going on, I just played it 1000 times from rand and the results were. 500 plays - Player: 144, Computer: 179, Tie: 177 https://youtu.be/g9Zo771HYpM…
mbrumlow on HNI just did the same thing, 500 plays - Player: 163, Computer: 179, Tie: 158 1000 plays - Player: 306, Computer: 365, Tie: 329 I've run it several times and the computer has won…
camjohnson26 on HN
Description says untrained but it trains on player moves
From 1 comment
In other words, the description is precisely inaccurate. Not only is it not untrained, it's trained against your exact plays through mysterious future-knowledge!
dTal on HN
Requests
Fix the prediction to train only after the move
From 1 comment
I took a stab at fixing this: https://github.com/victorqribeiro/jokenpo/pull/3
camjohnson26 on HN
Questions
Why does the network win against random play?
From 2 comments
Hm in my limited testing of not looking at the screen and selecting as randomly as I could I was surprised to find it not end 50/50 Not enough trials or is there something else…
thdxr on HNYeah, I am not sure what is going on, I just played it 1000 times from rand and the results were. 500 plays - Player: 144, Computer: 179, Tie: 177 https://youtu.be/g9Zo771HYpM…
mbrumlow on HN
Alternatives named
rpscontest.com bots
From 1 comment
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)…
timfoden on HN