{"blog_url":"https://tech.morikatron.ai/","height":"190","provider_name":"Hatena Blog","type":"rich","categories":["\u6a5f\u68b0\u5b66\u7fd2","\u5f37\u5316\u5b66\u7fd2","GAIL","Python"],"description":"\u3053\u3093\u306b\u3061\u306f\u3001\u30a8\u30f3\u30b8\u30cb\u30a2\u306e\u7af9\u5185\u3067\u3059\u3002\u4ee5\u524d\u306e\u8a18\u4e8b\u3067DQN\u306b\u6a21\u5023\u5b66\u7fd2\u306e\u4ed5\u7d44\u307f\u3092\u53d6\u308a\u5165\u308c\u305fDeep Q-Learning from Demonstrations\u3068\u3044\u3046\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u7d39\u4ecb\u3057\u307e\u3057\u305f\u304c\u3001\u6a21\u5023\u5b66\u7fd2\u306b\u306f\u4ed6\u306b\u3082\u3044\u308d\u3044\u308d\u306a\u30a2\u30d7\u30ed\u30fc\u30c1\u304c\u5b58\u5728\u3057\u307e\u3059\u3002 \u7279\u306b\u30a8\u30ad\u30b9\u30d1\u30fc\u30c8\u306e\u884c\u52d5\u8ecc\u8de1\u304b\u3089\u74b0\u5883\u306e\u5831\u916c\u95a2\u6570\u3092\u63a8\u5b9a\u3059\u308b\u9006\u5f37\u5316\u5b66\u7fd2(Inverse Reinforcement Learning)\u3068\u3044\u3046\u624b\u6cd5\u3092\u5229\u7528\u3057\u305f\u3082\u306e\u306f\u6a21\u5023\u5b66\u7fd2\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306e\u4e2d\u3067\u3082\u4ee3\u8868\u7684\u306a\u624b\u6cd5\u306e1\u3064\u3067\u3042\u308a\u3001\u74b0\u5883\u304b\u3089\u306e\u5831\u916c\u304c\u5f97\u3089\u308c\u306a\u3044\u5834\u5408\u3067\u3082\u6a21\u5023\u5b66\u7fd2\u3092\u884c\u3046\u4e8b\u304c\u3067\u304d\u307e\u3059\u3002 \u305d\u3053\u3067\u4eca\u56de\u306f\u9006\u5f37\u5316\u5b66\u7fd2\u3092\u7528\u3044\u305f\u6a21\u5023\u5b66\u7fd2\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306e\u4e2d\u3067\u3082\u7279\u306b\u6709\u7528\u306a\u624b\u6cd5\u3067\u3042\u308b\u3001\u6575\u5bfe\u7684\u2026","provider_url":"https://hatena.blog","author_name":"morika-takeuchi","image_url":"https://cdn-ak.f.st-hatena.com/images/fotolife/m/morika-takeuchi/20200925/20200925162630.png","width":"100%","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Ftech.morikatron.ai%2Fentry%2F2020%2F10%2F12%2F100000\" title=\"\u3010GAIL\u3011\u9006\u5f37\u5316\u5b66\u7fd2\u3068GAN\u3092\u7d44\u307f\u5408\u308f\u305b\u305f\u6a21\u5023\u5b66\u7fd2\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u5b9f\u88c5\u3057\u3066\u307f\u308b\u3010CartPole\u3011 - Morikatron Engineer Blog\" 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","url":"https://tech.morikatron.ai/entry/2020/10/12/100000","title":"\u3010GAIL\u3011\u9006\u5f37\u5316\u5b66\u7fd2\u3068GAN\u3092\u7d44\u307f\u5408\u308f\u305b\u305f\u6a21\u5023\u5b66\u7fd2\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u5b9f\u88c5\u3057\u3066\u307f\u308b\u3010CartPole\u3011","author_url":"https://blog.hatena.ne.jp/morika-takeuchi/","blog_title":"Morikatron Engineer Blog","published":"2020-10-12 10:00:00"}