{"image_url":null,"type":"rich","blog_url":"https://kerneltyu.hateblo.jp/","description":"\u3053\u3093\u306b\u3061\u306f\u3001\u3054\u7121\u6c99\u6c70\u3067\u3059\u3002\u4eca\u56de\u306f\u8aad\u3093\u3060\u8ad6\u6587\u306e\u5185\u5bb9\u306e\u307e\u3068\u3081\u3092\u3053\u3053\u306b\u8a18\u9332\u3057\u3088\u3046\u3068\u601d\u3044\u307e\u3059\u3002\u81ea\u5206\u306f\u5f37\u5316\u5b66\u7fd2\u306b\u5bfe\u3057\u3066\u4eba\u306e\u77e5\u8b58\u3092\u8ee2\u79fb\u3059\u308b\u3068\u3044\u3046\u3088\u3046\u306a\u7814\u7a76\u3092\u3057\u3066\u3044\u3066\u3001Human-friendly\u306a\u8ee2\u79fb\u65b9\u6cd5\u306f\u4f55\u304b\uff1f\u3068\u3044\u3046\u3053\u3068\u306b\u8208\u5473\u3092\u6301\u3063\u3066\u3044\u307e\u3059\u3002\u81ea\u5206\u7528\u306e\u30e1\u30e2\u306e\u3088\u3046\u306b\u8a18\u8ff0\u3057\u3066\u3044\u308b\u306e\u3067\u3001\u306a\u3093\u306e\u3053\u3063\u3061\u3083\u5206\u304b\u3089\u306a\u3044\u304b\u3082\u77e5\u308c\u307e\u305b\u3093\u304c\u3001\u3054\u5bb9\u8d66\u304f\u3060\u3055\u3044\u3002\u30b9\u30ad\u30e0\u3057\u305f\u7a0b\u5ea6\u3067\u3001\u5168\u4f53\u50cf\u3092\u307c\u3093\u3084\u308a\u63b4\u3093\u3060\u3068\u3044\u3046\u72b6\u614b\u3067\u66f8\u3044\u3066\u307e\u3059\u3002 \u8ad6\u6587\u60c5\u5831 \u30b8\u30e3\u30fc\u30ca\u30eb\u8ad6\u6587\u3067\u3059\u30022020\u5e74\u3001ACM Transactions on Autonomous and Adaptive Systems\u3067\u63b2\u8f09\u3055\u308c\u3066\u3044\u307e\u3059\u3002University of Technol\u2026","blog_title":"kerneltyu\u2019s tech blog","url":"https://kerneltyu.hateblo.jp/entry/2020/10/25/125326","provider_name":"Hatena Blog","author_url":"https://blog.hatena.ne.jp/kerneltyu/","categories":[],"published":"2020-10-25 12:53:26","width":"100%","version":"1.0","author_name":"kerneltyu","provider_url":"https://hatena.blog","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fkerneltyu.hateblo.jp%2Fentry%2F2020%2F10%2F25%2F125326\" title=\"\u3010\u8ad6\u6587\u3011Human Feedback as Action Assignment in Interactive Reinforcement Learning - kerneltyu\u2019s tech blog\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","height":"190","title":"\u3010\u8ad6\u6587\u3011Human Feedback as Action Assignment in Interactive Reinforcement Learning"}