{"categories":["\u5f8c\u3067\u8aad\u3080"],"blog_url":"https://gasyou.hatenablog.jp/","url":"https://gasyou.hatenablog.jp/entry/20170701/1498906118","author_url":"https://blog.hatena.ne.jp/Gasyou/","provider_url":"https://hatena.blog","published":"2017-07-01 19:48:38","author_name":"Gasyou","version":"1.0","title":"Count-Based Exploration in Feature Space for Reinforcement Learning","height":"190","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fgasyou.hatenablog.jp%2Fentry%2F20170701%2F1498906118\" title=\"Count-Based Exploration in Feature Space for Reinforcement Learning - GA\u5c06\uff1f\u958b\u767a\u65e5\u8a18\uff5e\u738b\u7406\u306e\u305d\u306e\u5148\u3078\uff5e\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","image_url":null,"width":"100%","type":"rich","blog_title":"GA\u5c06\uff1f\u958b\u767a\u65e5\u8a18\uff5e\u738b\u7406\u306e\u305d\u306e\u5148\u3078\uff5e","provider_name":"Hatena Blog","description":"https://arxiv.org/pdf/1706.08090.pdf \u5f37\u5316\u5b66\u7fd2\u3068\u95a2\u6570\u8fd1\u4f3c\u3092\u7d44\u307f\u5408\u308f\u305b\u305f\u5834\u5408\u306b\u3001 \u03c6-pseudocount\u3068\u547c\u3076\u6307\u6a19\u3092\u5143\u306b\u63a2\u67fb\u3092\u884c\u3046\u624b\u6cd5\u3089\u3057\u3044\u3002 \u5927\u304d\u306a\u72b6\u614b\u884c\u52d5\u7a7a\u9593\u3067\u3082\u52b9\u7387\u7684\u306b\u5b66\u7fd2\u53ef\u80fd\u3068\u3042\u308b\u306e\u3067\u3001\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u5c06\u68cb\u3078\u306e\u5fdc\u7528\u3082\u671f\u5f85\u51fa\u6765\u305d\u3046\u3002"}