Deep Reinforcement Learningã§Atariã®ã²ã¼ã Montezuma's Revengeãæ»ç¥ããçµæãOpenAI Gymã«ã¢ãããããã¨ã ååè¨äºã§æ¸ãã¾ãããããã®æã®å¹³åã¹ã³ã¢(448ç¹)ã«å¯¾ããåãè¨å®ã§æ´ã«é«ãå¹³åç¹(1127ç¹)ãå¾ããã¾ããã®ã§ãå度ãOpenAI Gymã«ã¢ãããã¾ãããä»åã¯ãæåã®é¨å±ã®å·¦å´ã«é²åºãã¦ãã¾ã*1ã gym.openai.com ä»åãDeepMindã®è«æã§å°éãã¦ããªãã£ãé¨å±ã«å°éããDeepMindãè¶ ãã¾ãã*2ãä¸è¨ãããã®ãã³ã¯ã«å¡ãããé¨åããä»åå°éããé¨å±ã§ãã ãã³ã¯ã®é¨å±ã®ãã¡ãå³å´ã®ï¼ã¤ã¯åç»ãæ®ãã¾ããã®ã§ãä¸è¨ã«è¼ãã¦ããã¾ã(10/17 11:15 æ´æ°)ã youtu.be ã¡ãªã¿ã«ãä¸è¨ã¯ãã¹ã¿ã¼ãããé¨å±ã®å·¦å´ã®é¨å±ã«ããå®ç®±ãåã£ãåç»ã§ã(10/17 11:15 æ´æ°)ã
{{#tags}}- {{label}}
{{/tags}}