[{"data":1,"prerenderedAt":348},["ShallowReactive",2],{"project-20531307":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":28,"sentiment":29,"stance_mix":30,"scored_comments":35,"aspects":36,"strip":43,"post_text":46,"what":47,"said":60,"maker_in_thread":128,"shape":139,"grid":144,"attempts":301,"same_week":309,"maker_shows":339,"maker_hidden":340,"reader_version":341,"card":342},"20531307","jokenpo","Play rock paper and scissors against a untrained neural network","title","Show HN: Play rock paper and scissors against a untrained neural network","https:\u002F\u002Fgithub.com\u002Fvictorqribeiro\u002Fjokenpo","github.com","atum47",1564101828,2019,101,63,482,2195,22,"notable","ai","game playing neural network","web_app",[24,25,26,27],"rock paper scissors","neural network","browser game","machine learning","roasted",-0.367,{"positive":31,"neutral":32,"mixed":33,"critical":34},1,11,0,13,25,{"execution":37,"performance":39,"idea":41},{"positive":31,"critical":38},7,{"positive":33,"critical":40},4,{"positive":33,"critical":42},2,[33,31,33,31,31,31,31,33,33,33,31,31,33,33,33,33,33,33,33,33,33,33,33,33,44,44,44,44,31,31,44,31,33,31,44,33,45,33,31,44],3,5,null,{"problem":46,"audience":46,"pricing":46,"motivation":46,"time_to_build":46,"stack":48,"openness":57,"stage":58,"team_size":59},[49],{"value":50,"source":51,"evidence":52},"JavaScript","inferred",[53],{"id":54,"by":55,"text":56},"20532207","kojackst","This runs it randomly 1000 times (well not reaaally randomly, but it gets close), just paste it into the browser console: const times = 1000; function sleep(ms) { return new…","open_source","launched","unknown",{"praise":61,"objections":70,"requests":104,"questions":111,"alternatives":120},[62],{"value":63,"source":64,"evidence":65},"Surprisingly good opponent","commenter",[66],{"id":67,"by":68,"text":69},"20531492","thirdmeow","Wow it's surprisingly good",[71,85,97],{"value":72,"source":64,"evidence":73},"Training includes the player's current move before prediction, so it cheats",[74,78,82],{"id":75,"by":76,"text":77},"20531819","QuadmasterXLII","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…",{"id":79,"by":80,"text":81},"20532295","akovaski","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…",{"id":83,"by":76,"text":84},"20531744","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.",{"value":86,"source":64,"evidence":87},"Beats random play more often than chance allows",[88,89,93],{"id":83,"by":76,"text":84},{"id":90,"by":91,"text":92},"20531837","mbrumlow","Yeah, 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:\u002F\u002Fyoutu.be\u002Fg9Zo771HYpM…",{"id":94,"by":95,"text":96},"20532538","camjohnson26","I 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…",{"value":98,"source":64,"evidence":99},"Description says untrained but it trains on player moves",[100],{"id":101,"by":102,"text":103},"20533510","dTal","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!",[105],{"value":106,"source":64,"evidence":107},"Fix the prediction to train only after the move",[108],{"id":109,"by":95,"text":110},"20532638","I took a stab at fixing this: https:\u002F\u002Fgithub.com\u002Fvictorqribeiro\u002Fjokenpo\u002Fpull\u002F3",[112],{"value":113,"source":64,"evidence":114},"Why does the network win against random play?",[115,119],{"id":116,"by":117,"text":118},"20531509","thdxr","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\u002F50 Not enough trials or is there something else…",{"id":90,"by":91,"text":92},[121],{"value":122,"source":64,"evidence":123},"rpscontest.com bots",[124],{"id":125,"by":126,"text":127},"20535948","timfoden","There's a site where AIs play RPS on an ongoing basis http:\u002F\u002Fwww.rpscontest.com\u002F. Source code of the entrants is available. My best bot (called paper6)…",{"comments":38,"answered":33,"key":129},[130,133,136],{"id":131,"text":132},"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…",{"id":134,"text":135},"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",{"id":137,"text":138},"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…",{"commenters":140,"max_depth":141,"maker_replies":38,"first_comment_mins":142,"lifespan_hours":143},37,8,34,66,[145,147,149,151,153,156,157,160,163,164,166,170,174,177,180,182,183,187,190,193,196,198,200,202,205,207,209,212,214,217,219,222,224,227,230,233,235,238,240,244,246,248,249,251,253,254,257,259,262,265,268,271,274,275,278,280,283,285,287,290,292,294,297],[83,33,33,146,76,33],"commenter\u002Fcritical\u002Fexecution",[75,33,31,148,76,33],"project\u002Fcritical\u002Fexecution",[131,33,33,150,11,31],"maker\u002Fneutral\u002Fexecution",[134,33,33,152,11,31],"maker\u002Fneutral\u002Fidea",[154,33,31,148,155,33],"20532780","j-pb",[79,33,31,148,80,33],[158,33,31,148,159,33],"20532448","klenwell",[161,33,31,148,162,33],"20534557","GrumpyNl",[137,33,33,150,11,31],[109,33,44,165,95,33],"project\u002Fneutral\u002Fexecution",[167,33,31,168,169,33],"20533464","project\u002Fcritical\u002Fperformance","seventytwo",[171,33,33,172,173,33],"20533967","other\u002Fneutral\u002Fnone","scottlocklin",[175,33,33,172,176,33],"20534716","jerf",[178,33,33,172,179,33],"20534864","6gvONxR4sf7o",[181,33,33,172,176,33],"20535922",[101,33,31,148,102,33],[184,33,44,185,186,33],"20531833","project\u002Fneutral\u002Fidea","jchw",[188,33,31,189,91,33],"20531857","project\u002Fcritical\u002Fidea",[191,33,33,172,192,33],"20532417","vinceguidry",[194,33,33,195,91,33],"20532631","commenter\u002Fneutral\u002Fnone",[197,33,33,195,192,33],"20532766",[199,33,33,195,91,33],"20533408",[201,33,33,195,192,33],"20533491",[203,33,33,195,204,33],"20532637","kqr",[206,33,33,195,192,33],"20532773",[208,33,33,146,91,33],"20533402",[210,33,33,172,211,33],"20532933","seanhunter",[213,33,33,195,192,33],"20532961",[215,33,33,172,216,33],"20533421","ps101",[218,33,33,146,91,33],"20533504",[220,33,33,195,221,33],"20531865","EGreg",[223,33,33,195,186,33],"20531988",[225,33,33,195,226,33],"20532108","misterman101",[228,33,33,195,229,33],"20532245","p1necone",[231,33,33,195,232,33],"20535221","brokensegue",[234,33,33,195,211,33],"20532409",[236,33,33,195,237,33],"20534035","wongarsu",[90,33,44,239,91,33],"project\u002Fneutral\u002Fperformance",[241,33,44,242,243,33],"20532153","project\u002Fneutral\u002Fnone","albertshin",[245,33,44,242,91,33],"20532204",[247,33,33,195,243,33],"20546341",[54,33,44,242,55,33],[250,33,44,242,91,33],"20532259",[252,33,33,195,55,33],"20532283",[94,33,31,168,95,33],[255,31,31,168,256,33],"20532652","veselin",[258,42,33,150,11,31],"20534687",[260,42,44,239,261,33],"20535299","sambroner",[263,44,31,168,264,33],"20532209","resist_futility",[266,40,33,172,267,33],"20532150","sagebird",[269,40,33,195,270,33],"20532288","make3",[272,40,33,172,273,33],"20535156","mikeash",[125,40,31,189,126,33],[276,45,33,277,11,31],"20542565","maker\u002Fneutral\u002Fperformance",[116,279,44,239,117,33],6,[281,279,33,195,282,33],"20531568","quickthrower2",[284,279,44,239,91,33],"20531751",[67,38,45,286,68,33],"project\u002Fpositive\u002Fexecution",[288,38,33,172,289,33],"20531693","r-w",[291,38,31,148,95,33],"20532516",[293,38,33,195,11,31],"20535661",[295,141,33,296,11,31],"20538279","maker\u002Fpositive\u002Fdesign",[298,299,44,242,300,33],"20531733",9,"bobblywobbles",[302,305,308],{"id":303,"t":304,"points":44,"comments":40},"19408401",1552751692,{"id":306,"t":307,"points":40,"comments":44},"19536560",1554050911,{"id":4,"t":12,"points":14,"comments":15},[310,315,320,325,329,334],{"id":311,"name":312,"points":313,"category":314},"20533318","Sauron-native",255,"languages",{"id":316,"name":317,"points":318,"category":319},"20546356","TLDR This",235,"productivity",{"id":321,"name":322,"points":323,"category":324},"20550167","Memorize Terminal Commands",166,"learning_science",{"id":326,"name":327,"points":328,"category":314},"20563970","Bild",138,{"id":330,"name":331,"points":332,"category":333},"20524779","usbrip",136,"security_privacy",{"id":335,"name":336,"points":337,"category":338},"20569337","Builder.io",109,"web_saas",53,false,"v2",{"id":343,"name":5,"line":6,"ai":340,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":344,"top":18,"kw":345,"maker":11,"domain":10,"tier":19,"attempts":44,"strip":346,"url":9,"mix":347,"praise":63,"objection":72,"sub":21},20531307,-0.37,[24,25,26,27],"0101111000110000000000003333113101305013",[31,32,33,34],1794036579386]