\n\n \uac15\ud654\ud559\uc2b5( Reinforcement Learning, RL)\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uacfc \uc0c1\ud638\uc791\uc6a9\ud558\uba70 \ubcf4\uc0c1\uc744 \uadf9\ub300\ud654\ud558\ub294 \ud589\ub3d9\uc744 \ud559\uc2b5\ud558\ub294 \uae30\uacc4 \ud559\uc2b5 \ubd84\uc57c\uc785\ub2c8\ub2e4. \uadf8\ub7ec\ub098 \ubcf5\uc7a1\ud55c \ubb38\uc81c\ub97c \ud478\ub294 \ub370 \uc788\uc5b4 \ub2e8\uc21c\ud55c \uac15\ud654\ud559\uc2b5 \ubc29\ubc95\ub9cc\uc73c\ub85c\ub294 \ud55c\uacc4\uac00 \uc788\uc2b5\ub2c8\ub2e4. \uc774\ub7ec\ud55c \ud55c\uacc4\ub97c \uadf9\ubcf5\ud558\uae30 \uc704\ud574 \ub4f1\uc7a5\ud55c \uac1c\ub150\uc774 \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical Reinforcement Learning, HRL)<\/strong>\uc785\ub2c8\ub2e4. \uc774\ubc88 \uae00\uc5d0\uc11c\ub294 HRL\uc758 \uac1c\ub150, \uc7a5\uc810, \uc2e4\uc81c \uc0ac\ub840 \ubc0f \uc608\uc81c \ucf54\ub4dc\ub97c \ud1b5\ud574 \uc774 \uae30\ubc95\uc774 \uc5b4\ub5bb\uac8c \ubcf5\uc7a1\ud55c \ud589\ub3d9\uc744 \ud559\uc2b5\ud558\ub294 \ub370 \uc720\uc6a9\ud55c\uc9c0\ub97c \ud0d0\uad6c\ud574 \ubcf4\uaca0\uc2b5\ub2c8\ub2e4.\n <\/p>\n\uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(HRL)\uc758 \uac1c\ub150<\/h2>\n
\n \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5\uc740 \ubb38\uc81c\ub97c \uacc4\uce35\uc801\uc73c\ub85c \uad6c\ubd84\ud558\uc5ec \ud574\uacb0\ud558\ub294 \uc811\uadfc \ubc29\uc2dd\uc744 \uc81c\uacf5\ud569\ub2c8\ub2e4. \ubcf4\ud1b5 \uac15\ud654\ud559\uc2b5\uc5d0\uc11c\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uc5d0 \ub300\ud55c \ubcf4\uc0c1\uc744 \ucd5c\ub300\ud654\ud558\uae30 \uc704\ud574 \ubaa8\ub4e0 \ud589\ub3d9\uc744 \u091a\u092f\u0928\ud558\ub294 \ub370 \uc9d1\uc911\ud569\ub2c8\ub2e4. \uadf8\ub7ec\ub098 HRL\uc5d0\uc11c\ub294 \uba85\ud655\ud55c \ubaa9\ud45c\ub97c \ub2ec\uc131\ud558\uae30 \uc704\ud574 \ud589\ub3d9\uc744 \ud558\uc704 \ubaa9\ud45c\ub85c \ub098\ub204\uc5b4 \ucc98\ub9ac\ud569\ub2c8\ub2e4.\n <\/p>\n
\n HRL\uc740 \ud06c\uac8c \ub450 \uac00\uc9c0 \uad6c\uc131 \uc694\uc18c\ub85c \ub098\ub20c \uc218 \uc788\uc2b5\ub2c8\ub2e4:\n <\/p>\n
\n- \uc0c1\uc704 \uc815\ucc45(High-level Policy):<\/strong> \uc804\ubc18\uc801\uc778 \ubaa9\ud45c\ub97c \uba85\uc2dc\ud558\uace0 \uc774\ub97c \ub2ec\uc131\ud558\uae30 \uc704\ud55c \ud558\uc704 \uc791\uc5c5\uc744 \uc0dd\uc131\ud569\ub2c8\ub2e4.<\/li>\n
- \ud558\uc704 \uc815\ucc45(Low-level Policy):<\/strong> \uc0c1\uc704 \uc815\ucc45\uc5d0 \uc758\ud574 \uc0dd\uc131\ub41c \ud558\uc704 \uc791\uc5c5\uc744 \uc218\ud589\ud558\ub294 \ub370 \ud544\uc694\ud55c \uad6c\uccb4\uc801\uc778 \ud589\ub3d9\uc744 \uacb0\uc815\ud569\ub2c8\ub2e4.<\/li>\n<\/ul>\n
\uacc4\uce35\uc801 RL\uc758 \uc7a5\uc810<\/h2>\n
\n HRL\uc758 \uc8fc\uc694 \uc7a5\uc810\uc740 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4:\n <\/p>\n
\n- \ubcf5\uc7a1\ud55c \ubb38\uc81c \ud574\uacb0:<\/strong> \ubb38\uc81c\ub97c \ud558\uc704 \ubb38\uc81c\ub85c \ub098\ub204\uc5b4 \ub2e4\ub8f0 \uc218 \uc788\uc5b4 \ubcf5\uc7a1\ud55c \ubaa9\ud45c\ub97c \ubcf4\ub2e4 \uc27d\uac8c \ud574\uacb0\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n
- \ud559\uc2b5 \ud6a8\uc728\uc131:<\/strong> \ud558\uc704 \ubaa9\ud45c\ub97c \uc7ac\uc0ac\uc6a9\ud568\uc73c\ub85c\uc368 \ud559\uc2b5 \uacfc\uc815\uc5d0\uc11c \ub354 \ub098\uc740 \uc77c\ubc18\ud654 \uc131\ub2a5\uc744 \ubc1c\ud718\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n
- \ud0d0\ud5d8-\ud65c\uc6a9 \uade0\ud615:<\/strong> \uc0c1\uc704 \uc815\ucc45\uc774 \ubaa9\ud45c\ub97c \uc124\uc815\ud558\ubbc0\ub85c, \uc5d0\uc774\uc804\ud2b8\uac00 \ubcf4\ub2e4 \ud6a8\uacfc\uc801\uc73c\ub85c \ud0d0\ud5d8\ud558\uace0 \ud65c\uc6a9\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n
- \ubaa8\ub4c8\ud654:<\/strong> \ud558\uc704 \uc815\ucc45\uc744 \ub3c5\ub9bd\uc801\uc73c\ub85c \ud559\uc2b5\uc2dc\ud0a4\uace0 \uc7ac\uc0ac\uc6a9\ud560 \uc218 \uc788\uc5b4 \ucf54\ub4dc\uc758 \ubaa8\ub4c8\uc131\uacfc \uc720\uc9c0\ubcf4\uc218\uc131\uc774 \ud5a5\uc0c1\ub429\ub2c8\ub2e4.<\/li>\n<\/ul>\n
\uacc4\uce35\uc801 RL\uc758 \uad6c\uc870<\/h2>\n
HRL\uc740 \uc5ec\ub7ec \uc218\uc900\uc758 \uc815\ucc45\uc73c\ub85c \uc774\ub8e8\uc5b4\uc838 \uc788\uc73c\uba70, \uc774\ub4e4\uc740 \uc11c\ub85c \ub2e4\ub978 \uc5ed\ud560\uacfc \ucc45\uc784\uc744 \uac00\uc9c0\uace0 \uc788\uc2b5\ub2c8\ub2e4. HRL\uc758 \uae30\ubcf8 \uad6c\uc870\ub294 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4:<\/p>\n
\n- \uc0c1\uc704 \uc815\ucc45: \ubaa9\ud45c \uc120\uc815 \ubc0f \ud558\uc704 \uc791\uc5c5 \uc0dd\uc131<\/li>\n
- \ud558\uc704 \uc815\ucc45: \ud2b9\uc815 \ud558\uc704 \uc791\uc5c5 \uc218\ud589<\/li>\n<\/ul>\n
1. \uc0c1\uc704 \uc815\ucc45\uc758 \uc5ed\ud560<\/h3>\n
\n \uc0c1\uc704 \uc815\ucc45\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \ub2ec\uc131\ud558\uace0\uc790 \ud558\ub294 \ubaa9\ud45c\ub97c \uc815\ud558\uace0, \uc774\ub97c \uc704\ud574 \ud544\uc694\ud55c \ud558\uc704 \uc791\uc5c5\uc744 \uc815\uc758\ud569\ub2c8\ub2e4. \uc608\ub97c \ub4e4\uc5b4 \ub85c\ubd07\uc774 \uc8fc\uc5b4\uc9c4 \ubaa9\ud45c \uc9c0\uc810\uae4c\uc9c0 \uac00\ub294 \uac83\uc774 \ubaa9\ud45c\ub77c\uba74, \uadf8 \uacfc\uc815\uc5d0\uc11c \ub2e4\uc74c\uacfc \uac19\uc740 \ud558\uc704 \uc791\uc5c5\uc744 \uc815\uc758\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4:\n <\/p>\n
\n- \uc8fc\ubcc0 \ud658\uacbd \ud30c\uc545\ud558\uae30<\/li>\n
- \uc7a5\uc560\ubb3c \ud68c\ud53c\ud558\uae30<\/li>\n
- \ubaa9\ud45c \ubc29\ud5a5\uc73c\ub85c \uc774\ub3d9\ud558\uae30<\/li>\n<\/ul>\n
2. \ud558\uc704 \uc815\ucc45\uc758 \uc5ed\ud560<\/h3>\n
\n \ud558\uc704 \uc815\ucc45\uc740 \uc0c1\uc704 \uc815\ucc45\uc5d0\uc11c \uc0dd\uc131\ub41c \ud558\uc704 \uc791\uc5c5\uc744 \uc218\ud589\ud569\ub2c8\ub2e4. \ud558\uc704 \uc815\ucc45\uc740 \ub354 \uad6c\uccb4\uc801\uc778 \ud589\ub3d9\uc744 \uacb0\uc815\ud558\uc5ec \uc0c1\uc704 \uc815\ucc45\uc758 \ubaa9\ud45c \ub2ec\uc131\uc744 \uc9c0\uc6d0\ud569\ub2c8\ub2e4. \ud558\uc704 \uc815\ucc45\uc740 \uc2e0\uacbd\ub9dd \ub610\ub294 \ub2e4\ub978 \ud559\uc2b5 \uc54c\uace0\ub9ac\uc998\uc744 \ud1b5\ud574 \ud559\uc2b5\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.\n <\/p>\n
\uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5\uc758 \uc54c\uace0\ub9ac\uc998<\/h2>\n
HRL\uc758 \ub300\ud45c\uc801\uc778 \uc54c\uace0\ub9ac\uc998\uc740 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4:<\/p>\n
\n- MAXQ Framework<\/li>\n
- Option Framework<\/li>\n
- Hierarchical DQN<\/li>\n<\/ul>\n
MAXQ Framework<\/h3>\n
\n MAXQ\ub294 \uac15\ud654\ud559\uc2b5\uc758 \uacc4\uce35\uc801 \uc811\uadfc\uc744 \uc9c0\uc6d0\ud558\ub294 \ub300\ud45c\uc801\uc778 \ud504\ub808\uc784\uc6cc\ud06c\uc785\ub2c8\ub2e4. \uc774 \ud504\ub808\uc784\uc6cc\ud06c\uc5d0\uc11c\ub294 \uacc4\uce35\uc801 \uac00\uce58 \ud568\uc218\ub97c \uad6c\uc131\ud558\uc5ec \uc0c1\uc704 \uc815\ucc45\uc774 \ud558\uc704 \uc791\uc5c5\uc758 \uac00\uce58\ub97c \ud3c9\uac00\ud560 \uc218 \uc788\ub3c4\ub85d \ud569\ub2c8\ub2e4. \uc774\ub807\uac8c \ud558\uba74 \ud558\uc704 \uc791\uc5c5\uc758 \uc870\ud569\uc73c\ub85c\ubd80\ud130 \uc804\uccb4 \ubb38\uc81c\uc758 \uac00\uce58\ub97c \ud3c9\uac00\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.\n <\/p>\n
Option Framework<\/h3>\n
\n Option Framework\ub294 \ud558\uc704 \uc815\ucc45\uc744 “\uc635\uc158”\uc73c\ub85c \uc815\uc758\ud558\uc5ec \uadf8 \uc635\uc158 \ub0b4\uc5d0\uc11c\uc758 \ud589\ub3d9\uc744 \ud559\uc2b5\ud558\ub294 \ubc29\ubc95\ub860\uc785\ub2c8\ub2e4. \uac01 \uc635\uc158\uc740 \uc2dc\uc791 \uc0c1\ud0dc\uc640 \uc885\ub8cc \uc0c1\ud0dc, \ud574\ub2f9 \uc635\uc158\uc758 \uc815\ucc45\uc73c\ub85c \uad6c\uc131\ub429\ub2c8\ub2e4. \uc774\ub7ec\ud55c \uc811\uadfc\uc740 \ubcf5\uc7a1\ud55c \ud589\ub3d9\uc744 \ucc98\ub9ac\ud558\ub294 \ub370 \uc720\uc6a9\ud558\uba70, \ud6a8\uc728\uc801\uc778 \ud559\uc2b5\uc744 \ub3c4\uc640\uc90d\ub2c8\ub2e4.\n <\/p>\n
Hierarchical DQN<\/h3>\n
\n \ud558\uc774\ub7ec\ud0a4\uceec DQN(Hierarchical DQN)\uc740 \uc804\ud1b5\uc801\uc778 DQN \uc54c\uace0\ub9ac\uc998\uc5d0 \uacc4\uce35\uc801 \uad6c\uc870\ub97c \ub3c4\uc785\ud55c \uac83\uc785\ub2c8\ub2e4. DQN\uc740 \uc0c1\ud0dc-\ud589\ub3d9 \uac12\uc744 \uc0ac\uc6a9\ud558\uc5ec \ucd5c\uc801\uc758 \uc815\ucc45\uc744 \ud559\uc2b5\ud558\ub294 \ubc29\uc2dd\uc778\ub370, HRL\uc744 \ud1b5\ud574 \uc5ec\ub7ec \ub808\ubca8\uc758 \uc815\ucc45\uc744 \ub3d9\uc2dc\uc5d0 \ud559\uc2b5\ud558\ub3c4\ub85d \uad6c\uc131\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc774\ub97c \ud1b5\ud574 \ubcf5\uc7a1\ud55c \ud658\uacbd\uc5d0\uc11c\uc758 \uc548\uc815\uc131\uacfc \uc131\ub2a5\uc744 \ud5a5\uc0c1\uc2dc\ud0b5\ub2c8\ub2e4.\n <\/p>\n
\uacc4\uce35\uc801 RL\uc758 \uc801\uc6a9 \uc0ac\ub840<\/h2>\n
\n HRL\uc740 \ub2e4\uc591\ud55c \ubd84\uc57c\uc5d0\uc11c \ud65c\uc6a9\ub418\uace0 \uc788\uc2b5\ub2c8\ub2e4. \uadf8 \uc911 \uba87 \uac00\uc9c0\ub294 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4:\n <\/p>\n
\n- \ub85c\ubd07 \uc81c\uc5b4: \ubcf5\uc7a1\ud55c \uc6c0\uc9c1\uc784\uacfc \uc791\uc5c5\uc744 \uc218\ud589\ud560 \uc218 \uc788\ub3c4\ub85d \ub85c\ubd07\uc774 \ud558\uc704 \ubaa9\ud45c\ub97c \uc124\uc815\ud558\uace0 \uc774\ub97c \uc2e4\ud589\ud558\ub294 \ub370 \uc0ac\uc6a9\ub429\ub2c8\ub2e4.<\/li>\n
- \uac8c\uc784 AI: \ube44\ub514\uc624 \uac8c\uc784\uc5d0\uc11c \ub300\ub9bd\ud558\ub294 \uce90\ub9ad\ud130\uac00 \ubcf5\uc7a1\ud55c \uc804\ud22c \uc804\ub7b5\uc744 \uc218\ub9bd\ud558\uace0 \uc774\ub97c \uc2e4\ud589\ud558\ub294 \ub370 \uc801\uc6a9\ub420 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n
- \uc790\uc728\uc8fc\ud589\ucc28: \uc8fc\ud589 \uacbd\ub85c\uc758 \uacc4\ud68d \ubc0f \ubcf4\uc870 \uc791\uc5c5\uc744 \ucc98\ub9ac\ud558\uae30 \uc704\ud574 \uacc4\uce35\uc801 \uc815\ucc45\uc744 \uc0ac\uc6a9\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n<\/ul>\n
HRL\uc758 \uc608\uc81c \ucf54\ub4dc<\/h2>\n
\ub2e4\uc74c\uc740 Python\uc744 \uc0ac\uc6a9\ud558\uc5ec \uac04\ub2e8\ud55c \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5\uc744 \uad6c\ud604\ud55c \uc608\uc81c \ucf54\ub4dc\uc785\ub2c8\ub2e4. \uc774 \uc608\uc81c\ub294 OpenAI\uc758 Gym \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \ud65c\uc6a9\ud558\uc5ec \uac04\ub2e8\ud55c \ud658\uacbd\uc744 \uc124\uc815\ud569\ub2c8\ub2e4.<\/p>\n
\n \nimport gym\nimport numpy as np\n\nclass HighLevelPolicy:\n def __init__(self):\n self.subgoals = [0.3, 0.6, 0.8] # \ud558\uc704 \ubaa9\ud45c \uc608\uc2dc\n\n def get_subgoal(self, state):\n if state < self.subgoals[0]:\n return self.subgoals[0]\n elif state < self.subgoals[1]:\n return self.subgoals[1]\n elif state < self.subgoals[2]:\n return self.subgoals[2]\n else:\n return None\n\nclass LowLevelPolicy:\n def __init__(self, env):\n self.env = env\n\n def perform_action(self, subgoal):\n # \ud558\uc704 \ubaa9\ud45c\uc5d0 \ub3c4\ub2ec\ud558\uae30 \uc704\ud55c \ud589\ub3d9 \uc218\ud589\n state = self.env.reset()\n done = False\n while not done:\n action = self.env.action_space.sample() # \ub79c\ub364 \ud589\ub3d9\n state, reward, done, info = self.env.step(action)\n if state >= subgoal:\n break\n return state\n\n# \ud658\uacbd \uc124\uc815\nenv = gym.make('CartPole-v1')\nhigh_level_policy = HighLevelPolicy()\nlow_level_policy = LowLevelPolicy(env)\n\n# \uc5d0\ud53c\uc18c\ub4dc \uc2e4\ud589\nfor episode in range(100):\n state = env.reset()\n while True:\n subgoal = high_level_policy.get_subgoal(state)\n if subgoal is not None:\n final_state = low_level_policy.perform_action(subgoal)\n print(f\"\uc5d0\ud53c\uc18c\ub4dc {episode}, \ucd5c\uc885 \uc0c1\ud0dc: {final_state}\")\n else:\n break\n state = final_state\n if state >= 1.0: # \ubaa9\ud45c \ub3c4\ub2ec\n break\n env.render()\n\nenv.close()\n <\/code>\n <\/pre>\n\uacb0\ub860<\/h2>\n
\n \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \ubcf5\uc7a1\ud55c \ud589\ub3d9\uc744 \ub354 \ud6a8\uacfc\uc801\uc73c\ub85c \ud559\uc2b5\ud560 \uc218 \uc788\ub3c4\ub85d \ud558\ub294 \uac15\ub825\ud55c \ud328\ub7ec\ub2e4\uc784\uc785\ub2c8\ub2e4. \uae30\uc874\uc758 \uac15\ud654\ud559\uc2b5 \uc811\uadfc \ubc29\uc2dd\uc758 \ud55c\uacc4\ub97c \uadf9\ubcf5\ud558\uace0, \ubaa8\ub4c8\ud654\ub41c \uc815\ucc45 \uad6c\uc870\ub97c \ud1b5\ud574 \ubcf4\ub2e4 \ud6a8\uc728\uc801\uc778 \ud559\uc2b5\uc744 \uac00\ub2a5\ud558\uac8c \ud569\ub2c8\ub2e4. \uc2e4\uc81c \uc801\uc6a9 \uc0ac\ub840\ub97c \ud1b5\ud574 \uc774\uc810\uacfc \uac00\ub2a5\uc131\uc744 \ud655\uc778\ud560 \uc218 \uc788\uc73c\uba70, \ubbf8\ub798\uc758 \ub2e4\uc591\ud55c \ud658\uacbd\uc5d0\uc11c\ub3c4 HRL\uc774 \uc911\uc694\ud55c \uc5ed\ud560\uc744 \ud560 \uac83\uc73c\ub85c \uae30\ub300\ub429\ub2c8\ub2e4. \uad50\uc721, \uc758\ub8cc, \uc790\uc728 \ub85c\ubd07 \ubc0f \uac8c\uc784 \ub4f1 \ub2e4\uc591\ud55c \ubd84\uc57c\uc5d0\uc11c HRL\uc758 \uc801\uc6a9\uc774 \ub354\uc6b1 \ud655\ub300\ub418\uace0 \uc788\uc2b5\ub2c8\ub2e4.\n <\/p>\n
\uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5\uc5d0 \ub300\ud55c \uc774\ud574\ub97c \ud1b5\ud574 AI \uae30\uc220\uc744 \ubcf4\ub2e4 \uae4a\uac8c \ud1b5\ucc30\ud560 \uc218 \uc788\uae30\ub97c \ubc14\ub78d\ub2c8\ub2e4. \uc55e\uc73c\ub85c\uc758 \uc5f0\uad6c\uc640 \uc751\uc6a9\uc774 \uae30\ub300\ub418\ub294 \ubd84\uc57c \uc911 \ud558\ub098\uc778 \ub9cc\ud07c, HRL\uc5d0 \ub300\ud55c \uc5f0\uad6c\uc640 \ud559\uc2b5\uc740 \uc9c0\uc18d\uc801\uc73c\ub85c \ud544\uc694\ud560 \uac83\uc785\ub2c8\ub2e4.<\/p>\n<\/article>\n
<\/body><\/p>\n","protected":false},"excerpt":{"rendered":"
\uac15\ud654\ud559\uc2b5( Reinforcement Learning, RL)\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uacfc \uc0c1\ud638\uc791\uc6a9\ud558\uba70 \ubcf4\uc0c1\uc744 \uadf9\ub300\ud654\ud558\ub294 \ud589\ub3d9\uc744 \ud559\uc2b5\ud558\ub294 \uae30\uacc4 \ud559\uc2b5 \ubd84\uc57c\uc785\ub2c8\ub2e4. \uadf8\ub7ec\ub098 \ubcf5\uc7a1\ud55c \ubb38\uc81c\ub97c \ud478\ub294 \ub370 \uc788\uc5b4 \ub2e8\uc21c\ud55c \uac15\ud654\ud559\uc2b5 \ubc29\ubc95\ub9cc\uc73c\ub85c\ub294 \ud55c\uacc4\uac00 \uc788\uc2b5\ub2c8\ub2e4. \uc774\ub7ec\ud55c \ud55c\uacc4\ub97c \uadf9\ubcf5\ud558\uae30 \uc704\ud574 \ub4f1\uc7a5\ud55c \uac1c\ub150\uc774 \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical Reinforcement Learning, HRL)\uc785\ub2c8\ub2e4. \uc774\ubc88 \uae00\uc5d0\uc11c\ub294 HRL\uc758 \uac1c\ub150, \uc7a5\uc810, \uc2e4\uc81c \uc0ac\ub840 \ubc0f \uc608\uc81c \ucf54\ub4dc\ub97c \ud1b5\ud574 \uc774 \uae30\ubc95\uc774 \uc5b4\ub5bb\uac8c \ubcf5\uc7a1\ud55c \ud589\ub3d9\uc744 \ud559\uc2b5\ud558\ub294 \ub370 \uc720\uc6a9\ud55c\uc9c0\ub97c … \ub354 \ubcf4\uae30 “19. \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical RL)\uc73c\ub85c \ubcf5\uc7a1\ud55c \ud589\ub3d9 \ud559\uc2b5\ud558\uae30, \uacc4\uce35\uc801 RL\uc758 \uac1c\ub150\uacfc \uc7a5\uc810”<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[213],"tags":[],"class_list":["post-40482","post","type-post","status-publish","format-standard","hentry","category-213"],"yoast_head":"\n19. \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical RL)\uc73c\ub85c \ubcf5\uc7a1\ud55c \ud589\ub3d9 \ud559\uc2b5\ud558\uae30, \uacc4\uce35\uc801 RL\uc758 \uac1c\ub150\uacfc \uc7a5\uc810 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/atmokpo.com\/w\/40482\/\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"19. \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical RL)\uc73c\ub85c \ubcf5\uc7a1\ud55c \ud589\ub3d9 \ud559\uc2b5\ud558\uae30, \uacc4\uce35\uc801 RL\uc758 \uac1c\ub150\uacfc \uc7a5\uc810 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"og:description\" content=\"\uac15\ud654\ud559\uc2b5( Reinforcement Learning, RL)\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uacfc \uc0c1\ud638\uc791\uc6a9\ud558\uba70 \ubcf4\uc0c1\uc744 \uadf9\ub300\ud654\ud558\ub294 \ud589\ub3d9\uc744 \ud559\uc2b5\ud558\ub294 \uae30\uacc4 \ud559\uc2b5 \ubd84\uc57c\uc785\ub2c8\ub2e4. \uadf8\ub7ec\ub098 \ubcf5\uc7a1\ud55c \ubb38\uc81c\ub97c \ud478\ub294 \ub370 \uc788\uc5b4 \ub2e8\uc21c\ud55c \uac15\ud654\ud559\uc2b5 \ubc29\ubc95\ub9cc\uc73c\ub85c\ub294 \ud55c\uacc4\uac00 \uc788\uc2b5\ub2c8\ub2e4. \uc774\ub7ec\ud55c \ud55c\uacc4\ub97c \uadf9\ubcf5\ud558\uae30 \uc704\ud574 \ub4f1\uc7a5\ud55c \uac1c\ub150\uc774 \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical Reinforcement Learning, HRL)\uc785\ub2c8\ub2e4. \uc774\ubc88 \uae00\uc5d0\uc11c\ub294 HRL\uc758 \uac1c\ub150, \uc7a5\uc810, \uc2e4\uc81c \uc0ac\ub840 \ubc0f \uc608\uc81c \ucf54\ub4dc\ub97c \ud1b5\ud574 \uc774 \uae30\ubc95\uc774 \uc5b4\ub5bb\uac8c \ubcf5\uc7a1\ud55c \ud589\ub3d9\uc744 \ud559\uc2b5\ud558\ub294 \ub370 \uc720\uc6a9\ud55c\uc9c0\ub97c … \ub354 \ubcf4\uae30 "19. \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical RL)\uc73c\ub85c \ubcf5\uc7a1\ud55c \ud589\ub3d9 \ud559\uc2b5\ud558\uae30, \uacc4\uce35\uc801 RL\uc758 \uac1c\ub150\uacfc \uc7a5\uc810"\" \/>\n<meta property=\"og:url\" content=\"https:\/\/atmokpo.com\/w\/40482\/\" \/>\n<meta property=\"og:site_name\" content=\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"article:published_time\" content=\"2024-11-04T01:52:07+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-11-26T06:39:04+00:00\" \/>\n<meta name=\"author\" content=\"root\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@bebubo4\" \/>\n<meta name=\"twitter:site\" content=\"@bebubo4\" \/>\n<meta name=\"twitter:label1\" content=\"\uae00\uc4f4\uc774\" \/>\n\t<meta name=\"twitter:data1\" content=\"root\" \/>\n\t<meta name=\"twitter:label2\" content=\"\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04\" \/>\n\t<meta name=\"twitter:data2\" content=\"1\ubd84\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/atmokpo.com\/w\/40482\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/40482\/\"},\"author\":{\"name\":\"root\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\"},\"headline\":\"19. \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical RL)\uc73c\ub85c \ubcf5\uc7a1\ud55c \ud589\ub3d9 \ud559\uc2b5\ud558\uae30, \uacc4\uce35\uc801 RL\uc758 \uac1c\ub150\uacfc \uc7a5\uc810\",\"datePublished\":\"2024-11-04T01:52:07+00:00\",\"dateModified\":\"2024-11-26T06:39:04+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/atmokpo.com\/w\/40482\/\"},\"wordCount\":58,\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"articleSection\":[\"\uac15\ud654\ud559\uc2b5\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/atmokpo.com\/w\/40482\/\",\"url\":\"https:\/\/atmokpo.com\/w\/40482\/\",\"name\":\"19. \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical RL)\uc73c\ub85c \ubcf5\uc7a1\ud55c \ud589\ub3d9 \ud559\uc2b5\ud558\uae30, \uacc4\uce35\uc801 RL\uc758 \uac1c\ub150\uacfc \uc7a5\uc810 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#website\"},\"datePublished\":\"2024-11-04T01:52:07+00:00\",\"dateModified\":\"2024-11-26T06:39:04+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/atmokpo.com\/w\/40482\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/atmokpo.com\/w\/40482\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/atmokpo.com\/w\/40482\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\ud648\",\"item\":\"https:\/\/atmokpo.com\/w\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"19. \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical RL)\uc73c\ub85c \ubcf5\uc7a1\ud55c \ud589\ub3d9 \ud559\uc2b5\ud558\uae30, \uacc4\uce35\uc801 RL\uc758 \uac1c\ub150\uacfc \uc7a5\uc810\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/atmokpo.com\/w\/#website\",\"url\":\"https:\/\/atmokpo.com\/w\/\",\"name\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/atmokpo.com\/w\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ko-KR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\",\"name\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"url\":\"https:\/\/atmokpo.com\/w\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png\",\"contentUrl\":\"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png\",\"width\":400,\"height\":400,\"caption\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\"},\"image\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/x.com\/bebubo4\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\",\"name\":\"root\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g\",\"caption\":\"root\"},\"sameAs\":[\"http:\/\/atmokpo.com\/w\"],\"url\":\"https:\/\/atmokpo.com\/w\/author\/root\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"19. \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical RL)\uc73c\ub85c \ubcf5\uc7a1\ud55c \ud589\ub3d9 \ud559\uc2b5\ud558\uae30, \uacc4\uce35\uc801 RL\uc758 \uac1c\ub150\uacfc \uc7a5\uc810 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/atmokpo.com\/w\/40482\/","og_locale":"ko_KR","og_type":"article","og_title":"19. \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical RL)\uc73c\ub85c \ubcf5\uc7a1\ud55c \ud589\ub3d9 \ud559\uc2b5\ud558\uae30, \uacc4\uce35\uc801 RL\uc758 \uac1c\ub150\uacfc \uc7a5\uc810 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","og_description":"\uac15\ud654\ud559\uc2b5( Reinforcement Learning, RL)\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uacfc \uc0c1\ud638\uc791\uc6a9\ud558\uba70 \ubcf4\uc0c1\uc744 \uadf9\ub300\ud654\ud558\ub294 \ud589\ub3d9\uc744 \ud559\uc2b5\ud558\ub294 \uae30\uacc4 \ud559\uc2b5 \ubd84\uc57c\uc785\ub2c8\ub2e4. \uadf8\ub7ec\ub098 \ubcf5\uc7a1\ud55c \ubb38\uc81c\ub97c \ud478\ub294 \ub370 \uc788\uc5b4 \ub2e8\uc21c\ud55c \uac15\ud654\ud559\uc2b5 \ubc29\ubc95\ub9cc\uc73c\ub85c\ub294 \ud55c\uacc4\uac00 \uc788\uc2b5\ub2c8\ub2e4. \uc774\ub7ec\ud55c \ud55c\uacc4\ub97c \uadf9\ubcf5\ud558\uae30 \uc704\ud574 \ub4f1\uc7a5\ud55c \uac1c\ub150\uc774 \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical Reinforcement Learning, HRL)\uc785\ub2c8\ub2e4. \uc774\ubc88 \uae00\uc5d0\uc11c\ub294 HRL\uc758 \uac1c\ub150, \uc7a5\uc810, \uc2e4\uc81c \uc0ac\ub840 \ubc0f \uc608\uc81c \ucf54\ub4dc\ub97c \ud1b5\ud574 \uc774 \uae30\ubc95\uc774 \uc5b4\ub5bb\uac8c \ubcf5\uc7a1\ud55c \ud589\ub3d9\uc744 \ud559\uc2b5\ud558\ub294 \ub370 \uc720\uc6a9\ud55c\uc9c0\ub97c … \ub354 \ubcf4\uae30 \"19. \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical RL)\uc73c\ub85c \ubcf5\uc7a1\ud55c \ud589\ub3d9 \ud559\uc2b5\ud558\uae30, \uacc4\uce35\uc801 RL\uc758 \uac1c\ub150\uacfc \uc7a5\uc810\"","og_url":"https:\/\/atmokpo.com\/w\/40482\/","og_site_name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","article_published_time":"2024-11-04T01:52:07+00:00","article_modified_time":"2024-11-26T06:39:04+00:00","author":"root","twitter_card":"summary_large_image","twitter_creator":"@bebubo4","twitter_site":"@bebubo4","twitter_misc":{"\uae00\uc4f4\uc774":"root","\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04":"1\ubd84"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/atmokpo.com\/w\/40482\/#article","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/40482\/"},"author":{"name":"root","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7"},"headline":"19. \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical RL)\uc73c\ub85c \ubcf5\uc7a1\ud55c \ud589\ub3d9 \ud559\uc2b5\ud558\uae30, \uacc4\uce35\uc801 RL\uc758 \uac1c\ub150\uacfc \uc7a5\uc810","datePublished":"2024-11-04T01:52:07+00:00","dateModified":"2024-11-26T06:39:04+00:00","mainEntityOfPage":{"@id":"https:\/\/atmokpo.com\/w\/40482\/"},"wordCount":58,"publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"articleSection":["\uac15\ud654\ud559\uc2b5"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/atmokpo.com\/w\/40482\/","url":"https:\/\/atmokpo.com\/w\/40482\/","name":"19. \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical RL)\uc73c\ub85c \ubcf5\uc7a1\ud55c \ud589\ub3d9 \ud559\uc2b5\ud558\uae30, \uacc4\uce35\uc801 RL\uc758 \uac1c\ub150\uacfc \uc7a5\uc810 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/#website"},"datePublished":"2024-11-04T01:52:07+00:00","dateModified":"2024-11-26T06:39:04+00:00","breadcrumb":{"@id":"https:\/\/atmokpo.com\/w\/40482\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/atmokpo.com\/w\/40482\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/atmokpo.com\/w\/40482\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\ud648","item":"https:\/\/atmokpo.com\/w\/en\/"},{"@type":"ListItem","position":2,"name":"19. \uacc4\uce35\uc801 \uac15\ud654\ud559\uc2b5(Hierarchical RL)\uc73c\ub85c \ubcf5\uc7a1\ud55c \ud589\ub3d9 \ud559\uc2b5\ud558\uae30, \uacc4\uce35\uc801 RL\uc758 \uac1c\ub150\uacfc \uc7a5\uc810"}]},{"@type":"WebSite","@id":"https:\/\/atmokpo.com\/w\/#website","url":"https:\/\/atmokpo.com\/w\/","name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","description":"","publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/atmokpo.com\/w\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ko-KR"},{"@type":"Organization","@id":"https:\/\/atmokpo.com\/w\/#organization","name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","url":"https:\/\/atmokpo.com\/w\/","logo":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/","url":"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png","contentUrl":"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png","width":400,"height":400,"caption":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8"},"image":{"@id":"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/bebubo4"]},{"@type":"Person","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7","name":"root","image":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g","caption":"root"},"sameAs":["http:\/\/atmokpo.com\/w"],"url":"https:\/\/atmokpo.com\/w\/author\/root\/"}]}},"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack-related-posts":[{"id":40514,"url":"https:\/\/atmokpo.com\/w\/40514\/","url_meta":{"origin":40482,"position":0},"title":"57. \uac15\ud654\ud559\uc2b5 \ud559\uc2b5 \uc790\ub8cc \ubc0f \ucee4\ubba4\ub2c8\ud2f0 \ub9ac\uc18c\uc2a4, \ucd94\ucc9c \ub3c4\uc11c, \uc628\ub77c\uc778 \uac15\uc758, \ud29c\ud1a0\ub9ac\uc5bc","author":"root","date":"2024\ub144 11\uc6d4 04\uc77c","format":false,"excerpt":"\uc791\uc131\uc77c: 2023\ub144 10\uc6d4 \uc800\uc790: \uc870\uad11\ud615 1. \uac15\ud654\ud559\uc2b5\uc758 \uc774\ud574 \uac15\ud654\ud559\uc2b5(Reinforcement Learning, RL)\uc740 \uc778\uacf5\uc9c0\ub2a5\uc758 \ud55c \ubd84\uc57c\ub85c, \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uacfc \uc0c1\ud638\uc791\uc6a9 \ud558\uba70 \ucd5c\uc801\uc758 \ud589\ub3d9\uc744 \ud559\uc2b5\ud558\ub294 \uc54c\uace0\ub9ac\uc998\uc785\ub2c8\ub2e4. \uc774 \uacfc\uc815\uc5d0\uc11c \uc5d0\uc774\uc804\ud2b8\ub294 \ubcf4\uc0c1\uc744 \uc5bb\uae30 \uc704\ud574 \uc5ec\ub7ec \uac00\uc9c0 \ud589\ub3d9\uc744 \uc2dc\ub3c4\ud558\uace0 \uacb0\uacfc\ub97c \ubc14\ud0d5\uc73c\ub85c \ud559\uc2b5\ud569\ub2c8\ub2e4. \uac15\ud654\ud559\uc2b5\uc758 \ub300\ud45c\uc801\uc778 \ud2b9\uc9d5\uc740 \uc2dc\ud5d8\uacfc \uc624\ub958(trial and error) \ud559\uc2b5 \ubc29\uc2dd\uacfc \uc7a5\uae30\uc801\uc778 \ubcf4\uc0c1(long-term reward) \ucd5c\uc801\ud654\uc785\ub2c8\ub2e4. 2. \uac15\ud654\ud559\uc2b5\uc758\u2026","rel":"","context":""\uac15\ud654\ud559\uc2b5"\uc5d0\uc11c","block_context":{"text":"\uac15\ud654\ud559\uc2b5","link":"https:\/\/atmokpo.com\/w\/category\/%ea%b0%95%ed%99%94%ed%95%99%ec%8a%b5\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":40452,"url":"https:\/\/atmokpo.com\/w\/40452\/","url_meta":{"origin":40482,"position":1},"title":"4. \uac15\ud654\ud559\uc2b5\uacfc \ub2e4\ub978 \uba38\uc2e0\ub7ec\ub2dd \uae30\ubc95\uc758 \ube44\uad50, \uac15\ud654\ud559\uc2b5\uc758 \uc7a5\uc810\uacfc \ub2e8\uc810","author":"root","date":"2024\ub144 11\uc6d4 04\uc77c","format":false,"excerpt":"\uc791\uc131\uc77c: 2023\ub144 10\uc6d4 \uc791\uc131\uc790: \uc870\uad11\ud615 1. \uc11c\ub860 \uba38\uc2e0\ub7ec\ub2dd\uc740 \ub2e4\uc591\ud55c \uae30\ubc95\uc744 \ud1b5\ud574 \ub370\uc774\ud130\ub97c \ud559\uc2b5\ud558\uace0 \uc774\ub97c \uae30\ubc18\uc73c\ub85c \uc608\uce21 \ud639\uc740 \uacb0\uc815\uc744 \ub0b4\ub9ac\ub294 \uae30\uc220\uc774\ub2e4. \uadf8 \uc911\uc5d0\uc11c\ub3c4 \uac15\ud654\ud559\uc2b5\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uacfc \uc0c1\ud638\uc791\uc6a9\ud558\uba70 \ubcf4\uc0c1 \uc2e0\ud638\ub97c \ud1b5\ud574 \ud559\uc2b5\ud558\ub294 \ubc29\uc2dd\uc73c\ub85c, \ub2e4\ub978 \uba38\uc2e0\ub7ec\ub2dd \uae30\ubc95\ub4e4\uacfc\ub294 \ud655\uc5f0\ud788 \ub2e4\ub978 \ud2b9\uc9d5\uc744 \uac00\uc9c4\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \uac15\ud654\ud559\uc2b5\uacfc \ub2e4\ub978 \uba38\uc2e0\ub7ec\ub2dd \uae30\ubc95\ub4e4\uc744 \ube44\uad50\ud558\uace0, \uac15\ud654\ud559\uc2b5\uc758 \uc7a5\uc810\uacfc \ub2e8\uc810\uc744 \uc2ec\ub3c4 \uc788\uac8c\u2026","rel":"","context":""\uac15\ud654\ud559\uc2b5"\uc5d0\uc11c","block_context":{"text":"\uac15\ud654\ud559\uc2b5","link":"https:\/\/atmokpo.com\/w\/category\/%ea%b0%95%ed%99%94%ed%95%99%ec%8a%b5\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":40484,"url":"https:\/\/atmokpo.com\/w\/40484\/","url_meta":{"origin":40482,"position":2},"title":"33. \ucee4\ub9ac\ud058\ub7fc \ud559\uc2b5(Curriculum Learning)\uc73c\ub85c \ub2e8\uacc4\uc801 \ud559\uc2b5 \uad6c\ud604\ud558\uae30, \ucee4\ub9ac\ud058\ub7fc \ud559\uc2b5\uc758 \uc6d0\ub9ac\uc640 \uc7a5\uc810","author":"root","date":"2024\ub144 11\uc6d4 04\uc77c","format":false,"excerpt":"\uc791\uc131\uc790: \uc870\uad11\ud615 \ub0a0\uc9dc: 2024\ub144 11\uc6d4 26\uc77c 1. \uc11c\ub860 \uac15\ud654\ud559\uc2b5(Deep Reinforcement Learning, DRL)\uc740 \ubcf5\uc7a1\ud55c \ud658\uacbd\uc5d0\uc11c \ucd5c\uc801\uc758 \ud589\ub3d9\uc744 \ud559\uc2b5\ud558\uae30 \uc704\ud55c \uac15\ub825\ud55c \ub3c4\uad6c\uc785\ub2c8\ub2e4. \uadf8\ub7ec\ub098 \uc774\ub7ec\ud55c \ud559\uc2b5 \uacfc\uc815\uc740 \ub9e4\uc6b0 \ube44\ud6a8\uc728\uc801\uc77c \uc218 \uc788\uc73c\uba70, \ud2b9\ud788 \ud559\uc2b5\ud558\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \ucc98\uc74c\ubd80\ud130 \ubcf5\uc7a1\ud55c \uc791\uc5c5\uc744 \ucc98\ub9ac\ud574\uc57c \ud560 \uacbd\uc6b0 \ub354\uc6b1 \uadf8\ub7ec\ud569\ub2c8\ub2e4. \uc774\ub97c \ud574\uacb0\ud558\uae30 \uc704\ud55c \uc811\uadfc \ubc29\ubc95 \uc911 \ud558\ub098\uac00 \ubc14\ub85c \ucee4\ub9ac\ud058\ub7fc \ud559\uc2b5(Curriculum Learning)\uc785\ub2c8\ub2e4.\u2026","rel":"","context":""\uac15\ud654\ud559\uc2b5"\uc5d0\uc11c","block_context":{"text":"\uac15\ud654\ud559\uc2b5","link":"https:\/\/atmokpo.com\/w\/category\/%ea%b0%95%ed%99%94%ed%95%99%ec%8a%b5\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":40512,"url":"https:\/\/atmokpo.com\/w\/40512\/","url_meta":{"origin":40482,"position":3},"title":"54. \ubbf8\ub798\uc758 \uac15\ud654\ud559\uc2b5 \ucd5c\uc2e0 \uc5f0\uad6c \ub3d9\ud5a5\uacfc \ud5a5\ud6c4 \uc804\ub9dd, \uac15\ud654\ud559\uc2b5\uc758 \ubbf8\ub798 \uac00\ub2a5\uc131\uacfc \uc751\uc6a9 \ubd84\uc57c","author":"root","date":"2024\ub144 11\uc6d4 04\uc77c","format":false,"excerpt":"\uac15\ud654\ud559\uc2b5\uc740 \uc778\uacf5\uc9c0\ub2a5 \ubd84\uc57c\uc5d0\uc11c \uac00\uc7a5 \ud765\ubbf8\ub85c\uc6b4 \uc601\uc5ed \uc911 \ud558\ub098\ub85c, \uae30\uacc4 \ud559\uc2b5\uc758 \ud55c \ubd84\uc57c\ub85c\uc368, \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uacfc \uc0c1\ud638\uc791\uc6a9\ud558\uba70 \ucd5c\uc801\uc758 \ud589\ub3d9\uc744 \ubc30\uc6b0\ub294 \uacfc\uc815\uc744 \uc758\ubbf8\ud569\ub2c8\ub2e4. \ubcf8 \uae00\uc5d0\uc11c\ub294 \uac15\ud654\ud559\uc2b5\uc758 \ucd5c\uc2e0 \uc5f0\uad6c \ub3d9\ud5a5\uacfc \uc804\ub9dd, \uadf8\ub9ac\uace0 \uc774 \uae30\uc220\uc774 \uc801\uc6a9\ub420 \uc218 \uc788\ub294 \ub2e4\uc591\ud55c \ubd84\uc57c\ub97c \uc2ec\uce35\uc801\uc73c\ub85c \ud0d0\uad6c\ud574\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \uac15\ud654\ud559\uc2b5\uc758 \uac1c\uc694 \uac15\ud654\ud559\uc2b5\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uc5d0\uc11c\uc758 \uacbd\ud5d8\uc744 \ud1b5\ud574 \ubcf4\uc0c1\uc744 \ucd5c\ub300\ud654\ud558\ub294 \ubc29\ud5a5\uc73c\ub85c \ud589\ub3d9\uc744 \ud559\uc2b5\ud558\ub294 \uacfc\uc815\uc785\ub2c8\ub2e4.\u2026","rel":"","context":""\uac15\ud654\ud559\uc2b5"\uc5d0\uc11c","block_context":{"text":"\uac15\ud654\ud559\uc2b5","link":"https:\/\/atmokpo.com\/w\/category\/%ea%b0%95%ed%99%94%ed%95%99%ec%8a%b5\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":29369,"url":"https:\/\/atmokpo.com\/w\/29369\/","url_meta":{"origin":40482,"position":4},"title":"\uba38\uc2e0\ub7ec\ub2dd \ubc0f \ub525\ub7ec\ub2dd \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529, \ud150\uc11c\ubcf4\ub4dc\ub97c \uc0ac\uc6a9\ud574 \uc784\ubca0\ub529 \uc2dc\uac01\ud654","author":"root","date":"2024\ub144 10\uc6d4 27\uc77c","format":false,"excerpt":"2023\ub144 X\uc6d4 X\uc77c | \uc791\uc131\uc790: \uc870\uad11\ud615 \uc11c\ub860 \uae08\uc735 \uc2dc\uc7a5\uc5d0\uc11c\uc758 \uc790\ub3d9\ud654\ub41c \ud2b8\ub808\uc774\ub529\uc740 \uba38\uc2e0\ub7ec\ub2dd \ubc0f \ub525\ub7ec\ub2dd \uae30\uc220\uc758 \ubc1c\uc804\uacfc \ud568\uaed8 \uadf8 \uc758\ubbf8\uac00 \ub354\uc6b1 \uac15\uc870\ub418\uace0 \uc788\uc2b5\ub2c8\ub2e4. \ub370\uc774\ud130\uc758 \uc591\uacfc \ubcf5\uc7a1\uc131\uc774 \uc99d\uac00\ud558\uba74\uc11c \uc804\ud1b5\uc801\uc778 \ubc29\ubc95\uc73c\ub85c\ub294 \uc5bb\uae30 \ud798\ub4e0 \uc778\uc0ac\uc774\ud2b8\ub97c \uc81c\uacf5\ud560 \uc218 \uc788\ub294 \uae30\uacc4\ud559\uc2b5 \uae30\ubc18\uc758 \ud2b8\ub808\uc774\ub529 \uc54c\uace0\ub9ac\uc998\uc774 \ub300\ub450\ub418\uace0 \uc788\uc2b5\ub2c8\ub2e4. \ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \uba38\uc2e0\ub7ec\ub2dd\uacfc \ub525\ub7ec\ub2dd \uc54c\uace0\ub9ac\uc998\uc744 \uc0ac\uc6a9\ud55c \ud2b8\ub808\uc774\ub529 \uc804\ub7b5\uc5d0 \ub300\ud574 \uc54c\uc544\ubcf4\uace0,\u2026","rel":"","context":""\ub525\ub7ec\ub2dd \uba38\uc2e0\ub7ec\ub2dd \uc790\ub3d9 \ud2b8\ub808\uc774\ub529"\uc5d0\uc11c","block_context":{"text":"\ub525\ub7ec\ub2dd \uba38\uc2e0\ub7ec\ub2dd \uc790\ub3d9 \ud2b8\ub808\uc774\ub529","link":"https:\/\/atmokpo.com\/w\/category\/%eb%94%a5%eb%9f%ac%eb%8b%9d-%eb%a8%b8%ec%8b%a0%eb%9f%ac%eb%8b%9d-%ec%9e%90%eb%8f%99-%ed%8a%b8%eb%a0%88%ec%9d%b4%eb%94%a9\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":29401,"url":"https:\/\/atmokpo.com\/w\/29401\/","url_meta":{"origin":40482,"position":5},"title":"\uba38\uc2e0\ub7ec\ub2dd \ubc0f \ub525\ub7ec\ub2dd \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529, \ud2b8\ub808\uc774\ub529\uc744 \uc704\ud55c \ubca0\uc774\uc9c0\uc548 \uba38\uc2e0\ub7ec\ub2dd","author":"root","date":"2024\ub144 10\uc6d4 27\uc77c","format":false,"excerpt":"\uc778\uacf5\uc9c0\ub2a5\uc758 \ubc1c\uc804\uacfc \ud568\uaed8 \uae08\uc735\uc2dc\uc7a5\uc5d0\uc11c\uc758 \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc740 \uc810\ucc28 \uc911\uc694\ud574\uc9c0\uace0 \uc788\uc2b5\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \uba38\uc2e0\ub7ec\ub2dd\uacfc \ub525\ub7ec\ub2dd\uc744 \ube44\ub86f\ud55c \ub2e4\uc591\ud55c \uc54c\uace0\ub9ac\uc998\uc774 \uc5b4\ub5bb\uac8c \ud2b8\ub808\uc774\ub529\uc5d0 \uc751\uc6a9\ub420 \uc218 \uc788\ub294\uc9c0, \uadf8\ub9ac\uace0 \uadf8 \uc911\uc5d0\uc11c\ub3c4 \ubca0\uc774\uc9c0\uc548 \uba38\uc2e0\ub7ec\ub2dd\uc758 \uc5ed\ud560\uacfc \uc911\uc694\uc131\uc744 \uc0c1\uc138\ud788 \uc124\uba85\ud558\uaca0\uc2b5\ub2c8\ub2e4. 1. \uba38\uc2e0\ub7ec\ub2dd \ubc0f \ub525\ub7ec\ub2dd \uac1c\uc694 \uba38\uc2e0\ub7ec\ub2dd\uc740 \ub370\uc774\ud130\uc5d0\uc11c \ud328\ud134\uc744 \ud559\uc2b5\ud558\uc5ec \uc608\uce21\ud558\ub294 \uc54c\uace0\ub9ac\uc998\uc744 \uad6c\ud604\ud558\ub294 \uae30\uc220\uc785\ub2c8\ub2e4. \uc77c\ubc18\uc801\uc73c\ub85c \uba38\uc2e0\ub7ec\ub2dd\uc740 \uc8fc\uc5b4\uc9c4 \ub370\uc774\ud130\ub97c \uae30\ubc18\uc73c\ub85c \ubaa8\ub378\uc744 \ud559\uc2b5\uc2dc\ud0a4\uace0,\u2026","rel":"","context":""\ub525\ub7ec\ub2dd \uba38\uc2e0\ub7ec\ub2dd \uc790\ub3d9 \ud2b8\ub808\uc774\ub529"\uc5d0\uc11c","block_context":{"text":"\ub525\ub7ec\ub2dd \uba38\uc2e0\ub7ec\ub2dd \uc790\ub3d9 \ud2b8\ub808\uc774\ub529","link":"https:\/\/atmokpo.com\/w\/category\/%eb%94%a5%eb%9f%ac%eb%8b%9d-%eb%a8%b8%ec%8b%a0%eb%9f%ac%eb%8b%9d-%ec%9e%90%eb%8f%99-%ed%8a%b8%eb%a0%88%ec%9d%b4%eb%94%a9\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]}],"_links":{"self":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/40482","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/comments?post=40482"}],"version-history":[{"count":1,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/40482\/revisions"}],"predecessor-version":[{"id":40483,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/40482\/revisions\/40483"}],"wp:attachment":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/media?parent=40482"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/categories?post=40482"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/tags?post=40482"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}