ã2020å¹´ã¢ãããã¼ãçã å¼·åå¦ç¿ã§ã¯ï¼ç°å¢ã§å¾ãããå ±é ¬ãã¹ãã¼ã¹ã§ããå ´åï¼ãã¾ãå¦ç¿ãããã¨ãã§ããªãï¼ãã®åé¡ã解決ããããã®ææ³ã¨ãã¦ï¼å¼·åå¦ç¿ã®ã¨ã¼ã¸ã§ã³ãã«ã好å¥å¿ããä¸ããç 究ã注ç®ããã¦ããï¼æ¬ã¹ã©ã¤ãã§ã¯ï¼æ·±å±¤å¼·åå¦ç¿ã®ç»å ´ä»¥éã«çºè¡¨ãããã好å¥å¿ããå©ç¨ããå¼·åå¦ç¿ã®ç 究ãã¾ã¨ããï¼ç¹ã«ä¸»è¦ãã³ããã¼ã¯ã§ããMontezuma's Revengeã§é«ãããã©ã¼ãã³ã¹ãçºæ®ããã¢ã«ã´ãªãºã ã«ã¤ãã¦è©³ãã解説ããï¼ã¾ãï¼ã好å¥å¿ãã«ããæ¢ç´¢ãå ±é ¬ãã¹ãã¼ã¹ãªå ´å以å¤ã®å¼·åå¦ç¿ã«é©ç¨ããå ´åã®ææ°ç 究ã«ã¤ãã¦ãç´¹ä»ããï¼ ç¾å¨ã¯ï¼æ¬è³æã®ä¿®æ£ã»ã¢ãããã¼ãçã以ä¸ã§å ¬éãã¦ãã¾ãï¼ ãå¼·åå¦ç¿ã«ããã好å¥å¿ã https://www.slideshare.net/ShotaImai3/curiosity-reinforcement-learning-238344056
{{#tags}}- {{label}}
{{/tags}}