{
  "@context":[
    "https://www.w3.org/ns/activitystreams",
    {"Hashtag":"as:Hashtag"}
  ],
  "published":"2021-03-12T02:06:03.960Z",
  "attributedTo":"https://epiktistes.com/actors/toddsundsted",
  "to":["https://www.w3.org/ns/activitystreams#Public"],
  "cc":["https://epiktistes.com/actors/toddsundsted/followers"],
  "content":"<p>I've been thinking about the impact of starting player order on winning strategy games. It seems like the kind of thing you'd want to design out of a game (or otherwise counterbalance). I came across <a href=\"https://maxcandocia.com/article/2017/Jul/22/using-neural-networks-to-play-board-games/\">an article</a> that modeled the dice and card game <a href=\"https://en.wikipedia.org/wiki/Machi_Koro\">Machi Koro</a> and then used a DNN to play 10,000 games. In the process the author found that there was a significant bias in favor of the first two players (vs. the last two players).<br></p><figure><img src=\"https://epiktistes.com/uploads/42eff704/d955/4ffd/1.png\" width=\"667\" height=\"667\"><figcaption>probably of winning vs. turn order</figcaption></figure><p>I'm going to see if I can replicate the results using <a href=\"https://github.com/toddsundsted/mxnet.cr\">MXNet.cr</a>.</p><p><a href=\"https://epiktistes.com/tags/boardgame\" class=\"hashtag\" rel=\"tag\">#boardgame</a> <a href=\"https://epiktistes.com/tags/neuralnetwork\" class=\"hashtag\" rel=\"tag\">#neuralnetwork</a></p>",
  "mediaType":"text/html",
  "attachment":[{"url":"https://epiktistes.com/uploads/42eff704/d955/4ffd/1.png","mediaType":"image/png"}],
  "tag":[
      {"type":"Hashtag","name":"#boardgame","href":"https://epiktistes.com/tags/boardgame"},
      {"type":"Hashtag","name":"#neuralnetwork","href":"https://epiktistes.com/tags/neuralnetwork"}
  ],
  "type":"Note",
  "id":"https://epiktistes.com/objects/OaSxGoiAYWA"
}