{"id":40418,"date":"2024-11-04T01:51:35","date_gmt":"2024-11-04T01:51:35","guid":{"rendered":"https:\/\/atmokpo.com\/w\/?p=40418"},"modified":"2024-11-26T06:39:13","modified_gmt":"2024-11-26T06:39:13","slug":"58-%ea%b0%95%ed%99%94%ed%95%99%ec%8a%b5-%ed%95%99%ec%8a%b5-%ec%9e%90%eb%a3%8c-%eb%b0%8f-%ec%bb%a4%eb%ae%a4%eb%8b%88%ed%8b%b0-%eb%a6%ac%ec%86%8c%ec%8a%a4-%ec%a3%bc%ec%9a%94-%ea%b0%95%ed%99%94","status":"publish","type":"post","link":"https:\/\/atmokpo.com\/w\/40418\/","title":{"rendered":"58. \uac15\ud654\ud559\uc2b5 \ud559\uc2b5 \uc790\ub8cc \ubc0f \ucee4\ubba4\ub2c8\ud2f0 \ub9ac\uc18c\uc2a4, \uc8fc\uc694 \uac15\ud654\ud559\uc2b5 \ucee4\ubba4\ub2c8\ud2f0\uc640 \ud3ec\ub7fc \uc18c\uac1c"},"content":{"rendered":"

<\/p>\n

\uac15\ud654\ud559\uc2b5(Reinforcement Learning, RL)\uc740 \uc778\uacf5\uc9c0\ub2a5(AI) \ubd84\uc57c\uc5d0\uc11c \ucd5c\uadfc \uba87 \ub144 \ub3d9\uc548 \uac00\uc7a5 \ube60\ub974\uac8c \ubc1c\uc804\ud558\ub294 \uc601\uc5ed \uc911 \ud558\ub098\uc785\ub2c8\ub2e4. \uc774 \uae30\uc220\uc740 \ubcf5\uc7a1\ud55c \ubb38\uc81c\ub97c \ud574\uacb0\ud558\uae30 \uc704\ud55c \uc758\uc0ac\uacb0\uc815 \ubc29\uc2dd\uc73c\ub85c \uc8fc\ubaa9\ubc1b\uace0 \uc788\uc2b5\ub2c8\ub2e4. \uadf8\ub7ec\ub098 \uac15\ud654\ud559\uc2b5\uc758 \uc9c0\uc2dd\uc744 \uc313\ub294 \uac83\uc740 \uc27d\uc9c0 \uc54a\uc740 \uc77c\uc774\ubbc0\ub85c, \ud6a8\uacfc\uc801\uc778 \ud559\uc2b5 \uc790\ub8cc\uc640 \ucee4\ubba4\ub2c8\ud2f0\uc758 \ub9ac\uc18c\uc2a4\uac00 \ub9e4\uc6b0 \uc911\uc694\ud569\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \uac15\ud654\ud559\uc2b5\uc744 \ubc30\uc6b0\ub294\ub370 \ub3c4\uc6c0\uc774 \ub418\ub294 \ub2e4\uc591\ud55c \uc790\ub8cc\uc640 \ucee4\ubba4\ub2c8\ud2f0\ub97c \uc18c\uac1c\ud558\uace0, \uc774\ub4e4\uc774 \uac15\ud654\ud559\uc2b5\uc744 \ud559\uc2b5\ud558\ub294 \ub370 \uc5b4\ub5a4 \ubc29\uc2dd\uc73c\ub85c \uae30\uc5ec\ud560 \uc218 \uc788\ub294\uc9c0\uc5d0 \ub300\ud574 \ub17c\uc758\ud558\uaca0\uc2b5\ub2c8\ub2e4.<\/p>\n

1. \uac15\ud654\ud559\uc2b5\uc758 \uae30\ubcf8 \uac1c\ub150 \uc774\ud574\ud558\uae30<\/h2>\n

\uac15\ud654\ud559\uc2b5\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uacfc \uc0c1\ud638\uc791\uc6a9\ud558\uba70 \ucd5c\uc801\uc758 \ud589\ub3d9\uc744 \ud559\uc2b5\ud558\ub294 \ubc29\uc2dd\uc785\ub2c8\ub2e4. \uc5d0\uc774\uc804\ud2b8\ub294 \uc0c1\ud0dc(state)\ub97c \uad00\ucc30\ud558\uace0, \ud589\ub3d9(action)\uc744 \ucde8\ud558\uba70, \ubcf4\uc0c1(reward)\uc744 \ud1b5\ud574 \ud559\uc2b5\ud569\ub2c8\ub2e4. \uc774 \uacfc\uc815\uc740 \ubcf4\ud1b5 \ub2e4\uc74c\uacfc \uac19\uc740 \uad6c\uc131 \uc694\uc18c\ub85c \uc124\uba85\ub429\ub2c8\ub2e4:<\/p>\n