ããè±ç²é£ãã§ããããã§ãããæ¯æ¸ã§ãã æ¨å¹´éããICML2013èªã¿ä¼ã«ç¶ããNIPS2013ã®è«æãç´¹ä»ããä¼ãéãã¾ãããå¹³æ¥å¤ã«ãé¢ããã60å以ä¸ã®ç³ãè¾¼ã¿ã50å以ä¸ã®åå ããããæ¹ãã¦æ©æ¢°å¦ç¿ã¸ã®èå³ã®é«ããè£ä»ãããã®ã¨ãªãã¾ãããä¼å ´æä¾ã«ãååé ããæ±å¤§ã®æ¦ç°æåå çãä¸å·è£å¿å çãããã³çºè¡¨è ã®çãããããã¨ããããã¾ããã ããã§ç¹çãããã®ãã@mooopanãããé¸ãã âPlaying Atari with Deep Reinforcement Learningâã§ãã 話é¡ã®Deep Neural Networkã¨å¼·åå¦ç¿ãçµã¿åããã¦ããã¬ãã²ã¼ã ã§äººéã«ãåã£ãã¨ããããã®æ¥å¯ä¸ã®ã¯ã¼ã¯ã·ã§ããè«æç´¹ä»ã ã£ãã®ã§ããããªãã¨èè ã®æå±ããDeepMind TechnologiesãGoogleã«500åå以ä¸ã§è²·åãããã¨ãããã¥ã¼ã¹ã3æ¥åé£ã³è¾¼ãã§ã
ã©ã³ãã³ã°
ã©ã³ãã³ã°
ã©ã³ãã³ã°
ãªãªã¼ã¹ãé害æ å ±ãªã©ã®ãµã¼ãã¹ã®ãç¥ãã
ææ°ã®äººæ°ã¨ã³ããªã¼ã®é ä¿¡
å¦çãå®è¡ä¸ã§ã
j次ã®ããã¯ãã¼ã¯
kåã®ããã¯ãã¼ã¯
lãã¨ã§èªã
eã³ã¡ã³ãä¸è¦§ãéã
oãã¼ã¸ãéã
{{#tags}}- {{label}}
{{/tags}}