2017-08-01ãã1ã¶æéã®è¨äºä¸è¦§
çæ§ç¥ã£ã¦ã®éããç¾½çä¸å ã¯ã¨ã¦ãå¼·ãã§ããå°æ£é£çã®ãã¼ã ãã¼ã¸ã«ããã¨ãã®è¨äºã®å·çæç¹ã§éç®æ績ã¯1379-552ã ããã§ããé·ãç¾å½¹ãç¶ãããã¤ãã¿ã¤ãã«ã«è¿ã¥ãã»ã©ç¸æãå¼·ããªãä¸ã§ãã®æ績ããã¼ãããã«ã¯ä¸¦ã ãªãã¬åªåãç¶ãã¦ãããã¨â¦
注ï¼ä»åã®è¨äºã¯å®å ¨ã«ããã°ã©ãåãã®è§£èª¬è¨äºã§ãã½ã¼ã¹ã³ã¼ãã®é²è¦§ããã¦ã³ãã¼ãã¯æ¤æ¹ããã©ãã GitHub - qhapaq-49/chainerrl_test: chainerrlã使ã£ãã¹ã¿ã³ãã¢ãã³ãªå¼·åå¦ç¿ã®ãµã³ãã«ã§ããååã®è¨äºï¼tensorflowçï¼ã ã¼ãããåµã tensorâ¦
注ï¼ä»åã®è¨äºã¯å®å ¨ã«ããã°ã©ãåãã®è§£èª¬è¨äºã§ãã½ã¼ã¹ã³ã¼ãã®é²è¦§ããã¦ã³ãã¼ãã¯æ¤æ¹ããã©ãã GitHub - qhapaq-49/tf_reinforcement: tensorflowã使ã£ãç°¡å(300è¡å¼±)ãªreinforcement learningãä»åä½ããããã®ã å²ç¢ããã¼ã«ã¼ã®AIã§åº¦ã 注â¦