By PhOtOnQuAnTiQuE 人éã®è³ãå¦ç¿ããä»çµã¿ãåç¾ãããã£ã¼ãã©ã¼ãã³ã°ã®ç 究ãé²ãã ãã¨ã§ãã³ã³ãã¥ã¼ã¿ã¼ã«ãã人工ç¥è½(AI)ã®æè¡ãé£èºçãªé²åãéãã¦ãã¾ããGoogleã500ååã§è²·åããã¨ãããã¦ããã¤ã®ãªã¹ã®ãã³ãã£ã¼ä¼æ¥ãDeepMindããéçºããã¨ã¼ã¸ã§ã³ãããã°ã©ã ãDQN(Deep Q-Network)ãã¯ä¸åº¦ããã°ã©ã ãèµ·åãããã¨ãã¨ã¯äººéãæãå ããªãã¦ããã¹ãã¼ã¹ã¤ã³ãã¼ãã¼ããããããã¯å´©ããã¨ãã£ãã²ã¼ã ãä¸äººã§åæã«ç·´ç¿ãããã¤ã¹ã³ã¢ããããåºãæ¹æ³ãå¦ç¿ã§ããã¬ãã«ã«éãã¦ãããä»å¾ã®AIéçºãããã«å éããããã¬ã¼ã¯ã¹ã«ã¼ã«ãªãã¨èãããã¦ãã¾ãã Google DeepMind http://deepmind.com/ Human-level control through deep reinforcement learnin
{{#tags}}- {{label}}
{{/tags}}