{"published":"2020-05-19 09:32:55","categories":["Agent57"],"width":"100%","provider_name":"Hatena Blog","image_url":"https://chart.apis.google.com/chart?cht=tx&chl=k%5Cin%5Cmathbb%7BN%7D","url":"https://tadaoyamaoka.hatenablog.com/entry/2020/05/19/093255","description":"\u4ed8\u9332D. \u30de\u30eb\u30c1\u30a2\u30fc\u30e0\u30d0\u30f3\u30c7\u30a3\u30c3\u30c8\u5f62\u5f0f \u3053\u306e\u7bc0\u3067\u306f\u3001\u30de\u30eb\u30c1\u30a2\u30fc\u30e0\u30d0\u30f3\u30c7\u30a3\u30c3\u30c8\uff08MAB\uff09\u30d1\u30e9\u30c0\u30a4\u30e0\u3001\u4e0a\u9650\u4fe1\u983c\u9650\u754c\uff08UCB\uff09\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3001\u304a\u3088\u3073\u30b9\u30e9\u30a4\u30c7\u30a3\u30f3\u30b0\u30a6\u30a3\u30f3\u30c9\u30a6UCB\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306b\u3064\u3044\u3066\u7c21\u6f54\u306b\u8aac\u660e\u3059\u308b\u3002 \u3088\u308a\u5b8c\u5168\u306a\u8aac\u660e\u3068\u5206\u6790\u306b\u3064\u3044\u3066\u306f\u3001Garivier & Moulines (2008)\u3092\u53c2\u7167\u3057\u3066\u307b\u3057\u3044\u3002 \u5404\u6642\u9593\u3067\u3001MAB\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306f\u3001\u524d\u306e\u884c\u52d5\u3068\u5831\u916c\u306e\u30b7\u30fc\u30b1\u30f3\u30b9\u3092\u6761\u4ef6\u3068\u3059\u308b\u65b9\u7b56\u306b\u5f93\u3063\u3066\u3001\u53ef\u80fd\u306a\u30a2\u30fc\u30e0\u304b\u3089\u30a2\u30fc\u30e0\u3092\u9078\u629e\u3059\u308b\u3002 \u305d\u3046\u3059\u308b\u3053\u3068\u3067\u3001\u5831\u916c\u3092\u53d7\u3051\u53d6\u308b\u3002 \u5b9a\u5e38\u306e\u5834\u5408\u3001\u4e0e\u3048\u3089\u308c\u305f\u30a2\u30fc\u30e0\u306e\u5831\u916c\u306f\u3001 i.i.d.\u78ba\u7387\u5909\u6570\u306e\u30b7\u30fc\u30b1\u30f3\u30b9\u306b\u3088\u3063\u3066\u30e2\u30c7\u30eb\u5316\u3055\u308c\u308b\u3002 \u975e\u5b9a\u5e38\u306e\u5834\u5408\u3001\u5831\u916c\u306f\u3001\u4e00\u9023\u306e\u72ec\u7acb\u78ba\u7387\u2026","type":"rich","height":"190","title":"Agent57: Outperforming the Atari Human Benchmark\u3092\u8aad\u3080 \u305d\u306e\uff11\uff11","provider_url":"https://hatena.blog","blog_title":"TadaoYamaoka\u306e\u958b\u767a\u65e5\u8a18","author_url":"https://blog.hatena.ne.jp/TadaoYamaoka/","blog_url":"https://tadaoyamaoka.hatenablog.com/","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Ftadaoyamaoka.hatenablog.com%2Fentry%2F2020%2F05%2F19%2F093255\" title=\"Agent57: Outperforming the Atari Human Benchmark\u3092\u8aad\u3080 \u305d\u306e\uff11\uff11 - TadaoYamaoka\u306e\u958b\u767a\u65e5\u8a18\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","version":"1.0","author_name":"TadaoYamaoka"}