ãã®è¨äºã«ã¤ã㦠éã¬ãå¢(ãã¤ãªã¤ã³ãã©ã¾ã)ã«ããAlphaGoã®ãµãã£ã¨ãã解説ã§ãã ç§ã¯å²ç¢æ段è ï¼æ©æ¢°å¦ç¿ããµãã£ã¨ç解ãã¦ãã¾ãã(å®è£ ã¯ããªãããã±ã¼ã¸ã¦ã¼ã¶ã¼) è«æèªãããªãã° Mastering the game of Go with deep nerural networks and tree search Human-level control through deep reinforcement learning ãèªããã æ¦è¦ -- AlphaGo = ããã£ã¼ãã©ã¼ãã³ã°ã«ãããããããªæã®é¸å®ã + ãã¢ã³ãã«ã«ãæ¨æ¢ç´¢(æç§å¦ç¿ã»æ¨æ¢ç´¢)ã«ããèªã¿ã -- ã¢ã³ãã«ã«ãæ¨æ¢ç´¢ã£ã¦ä½? -- ãã£ã¼ãã©ã¼ãã³ã°ã£ã¦ä½? -- ãã£ã¼ãã©ã¼ãã³ã°ã«ã¤ãã¦å¦ã³ããå ´å -- ãã£ã¼ãã©ã¼ãã³ã°ã®åé¡ç¹ã¨ãããã ã®4ã¤ã AlphaGoã®ã¢ã«ã´ãªãºã ãä¸è¨ã§
{{#tags}}- {{label}}
{{/tags}}