{"author_name":"higepon","width":"100%","url":"https://higepon.hatenablog.com/entry/2020/07/27/195452","provider_name":"Hatena Blog","blog_title":"higepon blog","image_url":null,"published":"2020-07-27 19:54:52","version":"1.0","provider_url":"https://hatena.blog","height":"190","categories":[],"description":"\u5f37\u5316\u5b66\u7fd2\u306e self play \u306b\u3064\u3044\u3066\u77e5\u308a\u305f\u3044\u3053\u3068\u304c\u3042\u308b\u306e\u3067\u3001\u3056\u3063\u304f\u308a\u3068\u6709\u540d\u306a\u8ad6\u6587\u3092\u8aad\u3093\u3067\u3044\u304f\u3002\u719f\u8aad\u306f\u3057\u306a\u3044\u3002 \u77e5\u308a\u305f\u3044\u3053\u3068 self play \u306f\u540c\u4e00\u30a4\u30f3\u30b9\u30bf\u30f3\u30b9\u3001\u5225\u30a4\u30f3\u30b9\u30bf\u30f3\u30b9\u3069\u3061\u3089\u304b\uff1f \u76f4\u611f\u7684\u306b\u306f\u3069\u3053\u304b\u3067 stuck \u3057\u305d\u3046\u306a\u611f\u3058\u304c\u3059\u308b\u3051\u3069\uff1f \u5b66\u7fd2\u304c\u9032\u3093\u3067\u3044\u308b\u3053\u3068\u3092\u3069\u306e\u3088\u3046\u306b\u8a55\u4fa1\u3059\u308b\u304b\uff1f \u8ad6\u6587 Mastering the game of Go without human knowledge + AlphaGo Zero\u306e\u8ad6\u6587\u3092\u8aad\u3080 \u305d\u306e4(\u81ea\u5df1\u5bfe\u5c40) - TadaoYamaoka\u306e\u65e5\u8a18 \u6027\u80fd\u6307\u6a19 Elo rating for each Training time \u6700\u826f\u306e model \u30a4\u2026","blog_url":"https://higepon.hatenablog.com/","author_url":"https://blog.hatena.ne.jp/higepon/","type":"rich","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fhigepon.hatenablog.com%2Fentry%2F2020%2F07%2F27%2F195452\" title=\"Reinforcement Learning \u306e self play \u306b\u3064\u3044\u3066\u306e\u307e\u3068\u3081 - higepon blog\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","title":"Reinforcement Learning \u306e self play \u306b\u3064\u3044\u3066\u306e\u307e\u3068\u3081"}