{"blog_url":"https://mabonki0725.hatenablog.com/","type":"rich","width":"100%","provider_url":"https://hatena.blog","height":"190","author_name":"mabonki0725","blog_title":"mabonki0725\u306e\u65e5\u8a18","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fmabonki0725.hatenablog.com%2Fentry%2F2017%2F10%2F13%2F235933\" title=\"\u4e00\u822c\u5316\u5831\u916c\u306b\u3088\u308b\u9ad8\u6b21\u5143\u306e\u5f37\u5316\u5b66\u7fd2\u306e\u8ad6\u6587\u3092\u8aad\u3080 - mabonki0725\u306e\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>","published":"2017-10-13 23:59:33","categories":["\u30ed\u30dc\u30c6\u30c3\u30af\u30b9","\u78ba\u7387\u30fb\u7d71\u8a08"],"author_url":"https://blog.hatena.ne.jp/mabonki0725/","image_url":"http://chart.apis.google.com/chart?cht=tx&chl=%5Cpi","provider_name":"Hatena Blog","version":"1.0","url":"https://mabonki0725.hatenablog.com/entry/2017/10/13/235933","description":"\u30e9\u30f3\u30cb\u30f3\u30b0\u3067\u304d\u305a \u82f1\u8a9e\u3067\u304d\u305a (1) \u4e00\u822c\u5316\u5831\u916c\u306b\u3088\u308b\u9ad8\u6b21\u5143\u306e\u5f37\u5316\u5b66\u7fd2\u306e\u8ad6\u6587\u3092\u8aad\u3080 \u300cHigh - Dimensional Continuous Control using Generated Advantage Estimation\u300d https://arxiv.org/abs/1506.02438 \u30b2\u30fc\u30e0\u306e\u5f37\u5316\u5b66\u7fd2\u3067\u306fQ-learning\u304c\u4e00\u822c\u7684\u3067\u3059\u304c\u3001\u4eba\u9593\u578b\u306e\u30d2\u30e6\u30fc\u30de\u30ed\u30a4\u30c9\u578b\u30ed\u30dc\u30c3\u30c8\u3067\u306f\u8907\u96d1\u3067\u9ad8\u6b21\u5143\u306e\u5236\u5fa1\u304c\u5fc5\u8981\u306a\u305f\u3081\u3001\u3053\u306e\u5f37\u5316\u5b66\u7fd2\u3067\u306f\u65b9\u7b56\u304c\u9069\u6b63\u62d8\u675f\u6761\u4ef6\u4e0b\u306e\u6700\u9069\u5316\u3067\u884c\u3046\u3053\u3068\u304c\u591a\u3044\u3067\u3059\u3002 https://youtu.be/Pvw28wPEWEo \u3053\u306e\u30e2\u30c7\u30eb\u3068\u3057\u3066\u306fUC Berkely\u306eAbb\u2026","title":"\u4e00\u822c\u5316\u5831\u916c\u306b\u3088\u308b\u9ad8\u6b21\u5143\u306e\u5f37\u5316\u5b66\u7fd2\u306e\u8ad6\u6587\u3092\u8aad\u3080"}