{"id":40490,"date":"2024-11-04T01:52:09","date_gmt":"2024-11-04T01:52:09","guid":{"rendered":"https:\/\/atmokpo.com\/w\/?p=40490"},"modified":"2024-11-26T06:39:03","modified_gmt":"2024-11-26T06:39:03","slug":"12-%eb%b3%b4%ec%83%81-%ed%95%a8%ec%88%98reward-function-%ec%84%a4%ea%b3%84%ec%9d%98-%ec%a4%91%ec%9a%94%ec%84%b1-%eb%b3%b4%ec%83%81-%ec%84%a4%ea%b3%84-%ec%8b%9c-%ea%b3%a0%eb%a0%a4%ec%82%ac%ed%95%ad","status":"publish","type":"post","link":"https:\/\/atmokpo.com\/w\/40490\/","title":{"rendered":"12. \ubcf4\uc0c1 \ud568\uc218(Reward Function) \uc124\uacc4\uc758 \uc911\uc694\uc131, \ubcf4\uc0c1 \uc124\uacc4 \uc2dc \uace0\ub824\uc0ac\ud56d \ubc0f \uc608\uc2dc"},"content":{"rendered":"<p><body><\/p>\n<p>\uac15\ud654\ud559\uc2b5(Deep Reinforcement Learning) \ubd84\uc57c\uc5d0\uc11c \ubcf4\uc0c1 \ud568\uc218(reward function)\ub294 \uc5d0\uc774\uc804\ud2b8\uc758 \ud559\uc2b5\uacfc \uc131\ub2a5\uc744 \uacb0\uc815\uc9d3\ub294 \ud575\uc2ec \uc694\uc18c\ub85c, \uc774\ub97c \uc801\uc808\ud788 \uc124\uacc4\ud558\ub294 \uac83\uc774 \uc131\uacf5\uc801\uc778 \ubaa8\ub378 \uad6c\ucd95\uc758 \ud544\uc218 \uc870\uac74\uc785\ub2c8\ub2e4. \ubcf4\uc0c1 \ud568\uc218\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uc5d0\uc11c \ud2b9\uc815 \ud589\ub3d9\uc744 \ucde8\ud588\uc744 \ub54c \ubc1b\ub294 \ud53c\ub4dc\ubc31\uc73c\ub85c, \uc5d0\uc774\uc804\ud2b8\uac00 \ubaa9\ud45c\ub97c \ud5a5\ud574 \ub098\uc544\uac00\uac70\ub098 \ucd5c\uc801\uc758 \ud589\ub3d9\uc744 \uc120\ud0dd\ud558\ub3c4\ub85d \ub3d5\uc2b5\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \ubcf4\uc0c1 \ud568\uc218\uc758 \uc911\uc694\uc131\uacfc \uc774\ub97c \uc124\uacc4\ud560 \ub54c \uace0\ub824\ud574\uc57c \ud560 \uc0ac\ud56d, \uadf8\ub9ac\uace0 \uc2e4\uc81c \uc608\uc2dc\ub97c \ud1b5\ud574 \uadf8 \uc124\uacc4 \ubc29\uc548\uc744 \uc0b4\ud3b4\ubcf4\uaca0\uc2b5\ub2c8\ub2e4.<\/p>\n<h2>1. \ubcf4\uc0c1 \ud568\uc218\uc758 \uc911\uc694\uc131<\/h2>\n<p>\ubcf4\uc0c1 \ud568\uc218\ub294 \uac15\ud654\ud559\uc2b5\uc5d0\uc11c \uc5d0\uc774\uc804\ud2b8\uc5d0\uac8c \ub3d9\uae30\ub97c \ubd80\uc5ec\ud558\ub294 \uc911\uc694\ud55c \uc5ed\ud560\uc744 \ud569\ub2c8\ub2e4. \uc5d0\uc774\uc804\ud2b8\ub294 \uc790\uc2e0\uc758 \ud589\ub3d9\uc774 \ubcf4\uc0c1\uc5d0 \uc5b4\ub5a4 \uc601\ud5a5\uc744 \ubbf8\uce58\ub294\uc9c0\ub97c \ud559\uc2b5\ud558\uc5ec, \ud5a5\ud6c4 \ud589\ub3d9 \uacb0\uc815\uc744 \uac1c\uc120\ud569\ub2c8\ub2e4. \ub530\ub77c\uc11c \ubcf4\uc0c1 \ud568\uc218\uac00 \uc798 \uc124\uacc4\ub418\uc9c0 \uc54a\uc73c\uba74 \uc5d0\uc774\uc804\ud2b8\ub294 \uc758\ub3c4\ud558\uc9c0 \uc54a\uc740 \ubc29\ud5a5\uc73c\ub85c \ud559\uc2b5\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc5ec\ub7ec \uc5f0\uad6c\uc5d0 \ub530\ub974\uba74 \ubcf4\uc0c1 \ud568\uc218\ub294 \ub2e4\uc74c\uacfc \uac19\uc740 \uc774\uc720\ub85c \uc911\uc694\ud569\ub2c8\ub2e4:<\/p>\n<ul>\n<li><strong>\ud589\ub3d9 \uc720\ub3c4:<\/strong> \ubcf4\uc0c1 \ud568\uc218\ub294 \uc5d0\uc774\uc804\ud2b8\uc5d0\uac8c \uc5b4\ub5a4 \ud589\ub3d9\uc774 \uc720\ub9ac\ud55c\uc9c0\ub97c \uc54c\ub824\uc8fc\uba70, \uc774\ub97c \ud1b5\ud574 \uc5d0\uc774\uc804\ud2b8\ub294 \ucd5c\uc801\uc758 \ud589\ub3d9\uc744 \uc120\ud0dd\ud558\uac8c \ub429\ub2c8\ub2e4.<\/li>\n<li><strong>\ube60\ub978 \ud559\uc2b5:<\/strong> \uc801\uc808\ud55c \ubcf4\uc0c1 \ud568\uc218\ub97c \uc124\uacc4\ud558\uba74 \uc5d0\uc774\uc804\ud2b8\uac00 \ube60\ub974\uac8c \uc218\ub834\ud558\uace0 \ud6a8\uc728\uc801\uc73c\ub85c \ud559\uc2b5\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n<li><strong>\uc77c\ubc18\ud654 \ub2a5\ub825 \ud5a5\uc0c1:<\/strong> \uc798 \uc124\uacc4\ub41c \ubcf4\uc0c1 \ud568\uc218\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \uc0c8\ub85c\uc6b4 \uc0c1\ud669\uc5d0\uc11c\ub3c4 \uc774\uc804 \ud559\uc2b5\uc744 \ud6a8\uacfc\uc801\uc73c\ub85c \ud65c\uc6a9\ud558\ub3c4\ub85d \ub3d5\uc2b5\ub2c8\ub2e4.<\/li>\n<li><strong>\ud589\ub3d9 \uc774\ud574:<\/strong> \ubcf4\uc0c1 \ud568\uc218\ub294 \ud559\uc2b5 \uacfc\uc815\uc5d0\uc11c \uc5d0\uc774\uc804\ud2b8\uc758 \ud589\ub3d9\uc744 \uc774\ud574\ud558\uace0 \ub514\ubc84\uae45\ud558\ub294 \ub370 \uc788\uc5b4 \uc911\uc694\ud55c \uc815\ubcf4\ub97c \uc81c\uacf5\ud569\ub2c8\ub2e4.<\/li>\n<\/ul>\n<h2>2. \ubcf4\uc0c1 \uc124\uacc4 \uc2dc \uace0\ub824\uc0ac\ud56d<\/h2>\n<p>\ubcf4\uc0c1 \ud568\uc218\ub97c \uc124\uacc4\ud560 \ub54c\ub294 \uc5ec\ub7ec \uac00\uc9c0 \uc694\uc18c\ub97c \uace0\ub824\ud574\uc57c \ud569\ub2c8\ub2e4. \uac01 \uc694\uc18c\ub294 \uc5d0\uc774\uc804\ud2b8\uc758 \ud559\uc2b5\uacfc \uc131\ub2a5\uc5d0 \uc9c1\uc811\uc801\uc778 \uc601\ud5a5\uc744 \ubbf8\uce58\ubbc0\ub85c \uc2e0\uc911\ud55c \uc811\uadfc\uc774 \ud544\uc694\ud569\ub2c8\ub2e4. \ub2e4\uc74c\uc740 \ubcf4\uc0c1 \uc124\uacc4 \uc2dc \uace0\ub824\ud574\uc57c \ud560 \uc8fc\uc694 \uc0ac\ud56d\uc785\ub2c8\ub2e4:<\/p>\n<h3>2.1. \ubaa9\ud45c \uc815\uc758<\/h3>\n<p>\uc6b0\uc120, \ubcf4\uc0c1 \ud568\uc218\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \ub2ec\uc131\ud574\uc57c \ud560 \ubaa9\ud45c\ub97c \uba85\ud655\ud788 \uc815\uc758\ud574\uc57c \ud569\ub2c8\ub2e4. \ubaa9\ud45c\ub294 \uc77c\ubc18\uc801\uc73c\ub85c \ud2b9\uc815 \uc791\uc5c5\uc744 \uc218\ud589\ud558\ub294 \uac83\uacfc \uad00\ub828\uc774 \uc788\uc73c\uba70, \uc774\ub97c \uc704\ud574 \ubcf4\uc0c1\uc740 \uc544\ub798\uc640 \uac19\uc740 \ubc29\ubc95\uc73c\ub85c \uc124\uacc4\ub420 \uc218 \uc788\uc2b5\ub2c8\ub2e4:<\/p>\n<ul>\n<li>\uc131\uacf5\uc801\uc778 \uc791\uc5c5\uc5d0 \ub300\ud574\uc11c\ub294 \uae0d\uc815\uc801\uc778 \ubcf4\uc0c1(\uc608: +1)\uc744 \ubd80\uc5ec\ud558\uace0, \uc2e4\ud328\ud55c \uc791\uc5c5\uc5d0 \ub300\ud574\uc11c\ub294 \ubd80\uc815\uc801\uc778 \ubcf4\uc0c1(\uc608: -1)\uc744 \ubd80\uc5ec<\/li>\n<li>\uc791\uc5c5\uc758 \ubaa9\ud45c \uc9c0\uc810\uc5d0 \uac00\uae4c\uc6cc\uc9c8\uc218\ub85d \uc810\uc9c4\uc801\uc73c\ub85c \uc99d\uac00\ud558\ub294 \ubcf4\uc0c1 \uc124\uacc4<\/li>\n<\/ul>\n<h3>2.2. \uacfc\ub3c4\ud55c \ubcf4\uc0c1\uacfc \ubc8c\uc810 \ud53c\ud558\uae30<\/h3>\n<p>\uc5d0\uc774\uc804\ud2b8\uac00 \ud6a8\uacfc\uc801\uc73c\ub85c \ud559\uc2b5\ud558\uae30 \uc704\ud574\uc11c\ub294 \uc9c0\ub098\uce58\uac8c \ud070 \ubcf4\uc0c1\uc774\ub098 \ubc8c\uc810\uc744 \ud53c\ud558\ub294 \uac83\uc774 \uc88b\uc2b5\ub2c8\ub2e4. \uc774\ub7ec\ud55c \uc0c1\ud669\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \ud2b9\uc815 \ud589\ub3d9\uc5d0 \ub300\ud574 \uacfc\ub3c4\ud55c \uc758\uc874\uc131\uc744 \uac00\uc9c8 \uc218 \uc788\ub3c4\ub85d \ub9cc\ub4e4\uba70, \uc774\ub294 \ud559\uc2b5\uc744 \uc800\ud574\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n<h3>2.3. \uc9c0\uc5f0 \ubcf4\uc0c1 \ucc98\ub9ac<\/h3>\n<p>\ub300\ubd80\ubd84\uc758 \ud658\uacbd\uc5d0\uc11c\ub294 \uc989\uac01\uc801\uc778 \ubcf4\uc0c1\ubcf4\ub2e4\ub294 \uc9c0\uc5f0 \ubcf4\uc0c1\uc774 \uc801\uc808\ud55c \uacbd\uc6b0\uac00 \ub9ce\uc2b5\ub2c8\ub2e4. \uc774\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \uc5ec\ub7ec \ud589\ub3d9\uc744 \uc5f0\uc18d\uc801\uc73c\ub85c \ucde8\ud55c \ud6c4\uc5d0\uc57c \ubcf4\uc0c1\uc744 \ubc1b\ub294 \uad6c\uc870\ub97c \uc758\ubbf8\ud569\ub2c8\ub2e4. \uc774\ub7ec\ud55c \uacbd\uc6b0, \uc5d0\uc774\uc804\ud2b8\ub294 \ud589\ub3d9 \uac04\uc758 \uc5f0\uad00\uc131\uc744 \uba85\ud655\ud788 \uc774\ud574\ud560 \uc218 \uc788\ub3c4\ub85d \ubcf4\uc0c1\uc744 \uc124\uacc4\ud574\uc57c \ud569\ub2c8\ub2e4.<\/p>\n<h3>2.4. \ubcf4\uc0c1\uc758 \ubc00\ub3c4 \ubc0f \ubcc0\ub3d9\uc131 \uac10\uc18c<\/h3>\n<p>\uc5d0\uc774\uc804\ud2b8\uac00 \ud559\uc2b5\ud560 \uc218 \uc788\ub294 \ud765\ubbf8\ub85c\uc6b4 \ubcf4\uc0c1\uc744 \uc81c\uacf5\ud558\ub418, \uc774\uc758 \ubcc0\ub3d9\uc131\uc744 \ucd5c\uc18c\ud654\ud574\uc57c \ud569\ub2c8\ub2e4. \ubd88\ud544\uc694\ud558\uac8c \ubcc0\ud654\uac00 \uc2ec\ud55c \ubcf4\uc0c1\uc740 \uc5d0\uc774\uc804\ud2b8\ub85c \ud558\uc5ec\uae08 \ud63c\ub780\uc5d0 \ube60\uc9c0\uac8c \ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n<h3>2.5. \ubd80\uc218\uc801 \ud589\ub3d9 \uace0\ub824<\/h3>\n<p>\ubcf4\uc0c1 \ud568\uc218\ub97c \uc124\uacc4\ud560 \ub54c\ub294 \uc8fc \ubaa9\ud45c\ubfd0\ub9cc \uc544\ub2c8\ub77c \ubd80\uc218\uc801\uc778 \ud589\ub3d9\uc5d0 \ub300\ud574\uc11c\ub3c4 \ubcf4\uc0c1\uc744 \uace0\ub824\ud574\uc57c \ud569\ub2c8\ub2e4. \uc608\ub97c \ub4e4\uc5b4, \uc790\ub3d9\ucc28\ub97c \uc8fc\ud589\ud558\ub294 \uc5d0\uc774\uc804\ud2b8\ub77c\uba74, \uc8fc\ud589 \uacbd\ub85c\ub97c \ub530\ub974\ub294 \uac83\ubfd0\ub9cc \uc544\ub2c8\ub77c \uc2e0\ud638\ub97c \uc9c0\ud0a4\ub294 \uac83\uacfc \uac19\uc740 \ud589\ub3d9\uc5d0\ub3c4 \ubcf4\uc0c1\uc744 \ubd80\uc5ec\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n<h2>3. \ubcf4\uc0c1 \ud568\uc218 \uc124\uacc4 \uc608\uc2dc<\/h2>\n<p>\uc774\uc81c \ud2b9\uc815 \uc608\uc2dc\ub97c \ud1b5\ud574 \ubcf4\uc0c1 \ud568\uc218 \uc124\uacc4\ub97c \uad6c\uccb4\uc801\uc73c\ub85c \ub2e4\ub904\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \uc544\ub798\uc758 \uc608\uc2dc\ub294 \uac04\ub2e8\ud55c \uadf8\ub9ac\ub4dc \uc6d4\ub4dc(Grid World) \ud658\uacbd\uc5d0\uc11c \uc5d0\uc774\uc804\ud2b8\uac00 \ubaa9\ud45c \uc9c0\uc810\uc5d0 \ub3c4\ub2ec\ud558\ub294 \uac83\uc744 \ubaa9\ud45c\ub85c \ud558\ub294 \uacbd\uc6b0\uc785\ub2c8\ub2e4.<\/p>\n<h3>3.1. \uae30\ubcf8 \ud658\uacbd \uc124\uc815<\/h3>\n<p>\uba3c\uc800, \uadf8\ub9ac\ub4dc \uc6d4\ub4dc \ud658\uacbd\uc744 \uc124\uc815\ud558\uaca0\uc2b5\ub2c8\ub2e4. \uc5ec\uae30\uc11c\ub294 5&#215;5 \ud06c\uae30\uc758 \uaca9\uc790\uc5d0\uc11c \uc5d0\uc774\uc804\ud2b8\uac00 (0, 0) \uc704\uce58\uc5d0\uc11c \uc2dc\uc791\ud574 (4, 4) \uc704\uce58\ub85c \uc774\ub3d9\ud558\ub294 \uacbd\uc6b0\ub97c \uac00\uc815\ud569\ub2c8\ub2e4.<\/p>\n<pre><code>import numpy as np\n\nclass GridWorld:\n    def __init__(self):\n        self.grid_size = 5\n        self.state = (0, 0)   # \uc5d0\uc774\uc804\ud2b8 \uc2dc\uc791 \uc704\uce58\n        self.goal_state = (4, 4)  # \ubaa9\ud45c \uc704\uce58\n        self.action_space = [(0, 1), (1, 0), (0, -1), (-1, 0)]  # \uc624\ub978\ucabd, \uc544\ub798, \uc67c\ucabd, \uc704\n\n    def reset(self):\n        self.state = (0, 0)\n        return self.state\n\n    def step(self, action):\n        # \uc0c1\ud0dc \uc5c5\ub370\uc774\ud2b8\n        next_state = (self.state[0] + action[0], self.state[1] + action[1])\n        # \uacbd\uacc4 \uccb4\ud06c\n        if 0 &lt;= next_state[0] &lt; self.grid_size and 0 &lt;= next_state[1] &lt; self.grid_size:\n            self.state = next_state\n        \n        # \ubcf4\uc0c1 \ubc0f \uc885\ub8cc \ud655\uc778\n        if self.state == self.goal_state:\n            return self.state, 1, True  # \ubaa9\ud45c \ub3c4\ub2ec \uc2dc \ubcf4\uc0c1 1\n        else:\n            return self.state, -0.1, False  # \uc77c\ubc18 \uc774\ub3d9 \uc2dc \uc18c\ub7c9\uc758 \uc74c\uc758 \ubcf4\uc0c1\n<\/code><\/pre>\n<h3>3.2. \uc5d0\uc774\uc804\ud2b8 \ud559\uc2b5<\/h3>\n<p>\ub2e4\uc74c\uc73c\ub85c, \uc704\uc758 \ud658\uacbd\uc744 \uc774\uc6a9\ud574 \uac04\ub2e8\ud55c Q-\ub7ec\ub2dd \uc5d0\uc774\uc804\ud2b8\ub97c \uad6c\ud604\ud558\uaca0\uc2b5\ub2c8\ub2e4. \uc5d0\uc774\uc804\ud2b8\ub294 \ubcf4\uc0c1 \ud568\uc218\ub97c \ud1b5\ud574 \ud559\uc2b5\ud569\ub2c8\ub2e4.<\/p>\n<pre><code>class QLearningAgent:\n    def __init__(self, environment):\n        self.env = environment\n        self.q_table = np.zeros((environment.grid_size, environment.grid_size, len(environment.action_space)))\n        self.alpha = 0.1  # \ud559\uc2b5\ub960\n        self.gamma = 0.99  # \ud560\uc778 \uacc4\uc218\n        self.epsilon = 0.1  # \ud0d0\uc0c9 \ud655\ub960\n\n    def choose_action(self, state):\n        if np.random.rand() &lt; self.epsilon:  # \ud0d0\uc0c9\n            return np.random.choice(range(len(self.env.action_space)))\n        else:  # \uac1c\ubc1c\n            return np.argmax(self.q_table[state[0], state[1]])\n\n    def update_q_value(self, state, action, reward, next_state):\n        best_next_action = np.argmax(self.q_table[next_state[0], next_state[1]])\n        td_target = reward + self.gamma * self.q_table[next_state[0], next_state[1], best_next_action]\n        td_error = td_target - self.q_table[state[0], state[1], action]\n        self.q_table[state[0], state[1], action] += self.alpha * td_error\n\n    def train(self, episodes):\n        for episode in range(episodes):\n            state = self.env.reset()\n            done = False\n            while not done:\n                action = self.choose_action(state)\n                next_state, reward, done = self.env.step(self.env.action_space[action])\n                self.update_q_value(state, action, reward, next_state)\n                state = next_state\n<\/code><\/pre>\n<h3>3.3. \uacb0\uacfc \ud655\uc778<\/h3>\n<p>\ub9c8\uc9c0\ub9c9\uc73c\ub85c, \ud559\uc2b5\uc744 \uc218\ud589\ud558\uace0 \ucd5c\uc885 Q-\ud14c\uc774\ube14\uc744 \ucd9c\ub825\ud558\uc5ec \uc5d0\uc774\uc804\ud2b8\uac00 \uc5b4\ub5bb\uac8c \ud559\uc2b5\ud588\ub294\uc9c0\ub97c \ud655\uc778\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n<pre><code>if __name__ == \"__main__\":\n    env = GridWorld()\n    agent = QLearningAgent(env)\n    agent.train(1000)\n\n    # Q-\ud14c\uc774\ube14 \ucd9c\ub825\n    print(\"Final Q-Table:\")\n    print(agent.q_table)\n<\/code><\/pre>\n<h2>\uacb0\ub860<\/h2>\n<p>\uc774\uc0c1\uc73c\ub85c \uac15\ud654\ud559\uc2b5\uc5d0\uc11c \ubcf4\uc0c1 \ud568\uc218\uc758 \uc911\uc694\uc131\uacfc \uc124\uacc4 \uc2dc \uace0\ub824 \uc0ac\ud56d, \uadf8\ub9ac\uace0 \uc2e4\uc81c \ubcf4\uc0c1 \uc124\uacc4\ub97c \uc704\ud55c \uc608\uc2dc\ub97c \uc0b4\ud3b4\ubcf4\uc558\uc2b5\ub2c8\ub2e4. \ubcf4\uc0c1 \ud568\uc218\ub294 \uc5d0\uc774\uc804\ud2b8\uc758 \ud559\uc2b5 \ud6a8\uacfc\uc640 \ud589\ub3d9\uc744 \ubcf8\uc9c8\uc801\uc73c\ub85c \ud615\uc131\ud558\ub294 \uc694\uc18c\ub85c, \uc774\ub294 \uac15\ud654\ud559\uc2b5\uc758 \uc131\uacf5\uc5d0 \ub9e4\uc6b0 \uc911\uc694\ud55c \uc5ed\ud560\uc744 \ud569\ub2c8\ub2e4. \ud5a5\ud6c4 \ub2e4\uc591\ud55c \ud658\uacbd\uacfc \uc0ac\ub840\uc5d0 \ub300\ud574 \uc9c0\uc18d\uc801\uc73c\ub85c \uc5f0\uad6c\ud558\uc5ec, \ub354 \ud6a8\uc728\uc801\uc774\uace0 \ud6a8\uacfc\uc801\uc778 \ubcf4\uc0c1 \ud568\uc218\ub97c \uc124\uacc4\ud574 \ub098\uac00\ub294 \uac83\uc774 \uc911\uc694\ud569\ub2c8\ub2e4.<\/p>\n<p><\/body><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\uac15\ud654\ud559\uc2b5(Deep Reinforcement Learning) \ubd84\uc57c\uc5d0\uc11c \ubcf4\uc0c1 \ud568\uc218(reward function)\ub294 \uc5d0\uc774\uc804\ud2b8\uc758 \ud559\uc2b5\uacfc \uc131\ub2a5\uc744 \uacb0\uc815\uc9d3\ub294 \ud575\uc2ec \uc694\uc18c\ub85c, \uc774\ub97c \uc801\uc808\ud788 \uc124\uacc4\ud558\ub294 \uac83\uc774 \uc131\uacf5\uc801\uc778 \ubaa8\ub378 \uad6c\ucd95\uc758 \ud544\uc218 \uc870\uac74\uc785\ub2c8\ub2e4. \ubcf4\uc0c1 \ud568\uc218\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uc5d0\uc11c \ud2b9\uc815 \ud589\ub3d9\uc744 \ucde8\ud588\uc744 \ub54c \ubc1b\ub294 \ud53c\ub4dc\ubc31\uc73c\ub85c, \uc5d0\uc774\uc804\ud2b8\uac00 \ubaa9\ud45c\ub97c \ud5a5\ud574 \ub098\uc544\uac00\uac70\ub098 \ucd5c\uc801\uc758 \ud589\ub3d9\uc744 \uc120\ud0dd\ud558\ub3c4\ub85d \ub3d5\uc2b5\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \ubcf4\uc0c1 \ud568\uc218\uc758 \uc911\uc694\uc131\uacfc \uc774\ub97c \uc124\uacc4\ud560 \ub54c \uace0\ub824\ud574\uc57c \ud560 \uc0ac\ud56d, \uadf8\ub9ac\uace0 \uc2e4\uc81c \uc608\uc2dc\ub97c \ud1b5\ud574 &hellip; <a href=\"https:\/\/atmokpo.com\/w\/40490\/\" class=\"more-link\">\ub354 \ubcf4\uae30<span class=\"screen-reader-text\"> &#8220;12. \ubcf4\uc0c1 \ud568\uc218(Reward Function) \uc124\uacc4\uc758 \uc911\uc694\uc131, \ubcf4\uc0c1 \uc124\uacc4 \uc2dc \uace0\ub824\uc0ac\ud56d \ubc0f \uc608\uc2dc&#8221;<\/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-40490","post","type-post","status-publish","format-standard","hentry","category-213"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.2 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>12. \ubcf4\uc0c1 \ud568\uc218(Reward Function) \uc124\uacc4\uc758 \uc911\uc694\uc131, \ubcf4\uc0c1 \uc124\uacc4 \uc2dc \uace0\ub824\uc0ac\ud56d \ubc0f \uc608\uc2dc - \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\/40490\/\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"12. \ubcf4\uc0c1 \ud568\uc218(Reward Function) \uc124\uacc4\uc758 \uc911\uc694\uc131, \ubcf4\uc0c1 \uc124\uacc4 \uc2dc \uace0\ub824\uc0ac\ud56d \ubc0f \uc608\uc2dc - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"og:description\" content=\"\uac15\ud654\ud559\uc2b5(Deep Reinforcement Learning) \ubd84\uc57c\uc5d0\uc11c \ubcf4\uc0c1 \ud568\uc218(reward function)\ub294 \uc5d0\uc774\uc804\ud2b8\uc758 \ud559\uc2b5\uacfc \uc131\ub2a5\uc744 \uacb0\uc815\uc9d3\ub294 \ud575\uc2ec \uc694\uc18c\ub85c, \uc774\ub97c \uc801\uc808\ud788 \uc124\uacc4\ud558\ub294 \uac83\uc774 \uc131\uacf5\uc801\uc778 \ubaa8\ub378 \uad6c\ucd95\uc758 \ud544\uc218 \uc870\uac74\uc785\ub2c8\ub2e4. \ubcf4\uc0c1 \ud568\uc218\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uc5d0\uc11c \ud2b9\uc815 \ud589\ub3d9\uc744 \ucde8\ud588\uc744 \ub54c \ubc1b\ub294 \ud53c\ub4dc\ubc31\uc73c\ub85c, \uc5d0\uc774\uc804\ud2b8\uac00 \ubaa9\ud45c\ub97c \ud5a5\ud574 \ub098\uc544\uac00\uac70\ub098 \ucd5c\uc801\uc758 \ud589\ub3d9\uc744 \uc120\ud0dd\ud558\ub3c4\ub85d \ub3d5\uc2b5\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \ubcf4\uc0c1 \ud568\uc218\uc758 \uc911\uc694\uc131\uacfc \uc774\ub97c \uc124\uacc4\ud560 \ub54c \uace0\ub824\ud574\uc57c \ud560 \uc0ac\ud56d, \uadf8\ub9ac\uace0 \uc2e4\uc81c \uc608\uc2dc\ub97c \ud1b5\ud574 &hellip; \ub354 \ubcf4\uae30 &quot;12. \ubcf4\uc0c1 \ud568\uc218(Reward Function) \uc124\uacc4\uc758 \uc911\uc694\uc131, \ubcf4\uc0c1 \uc124\uacc4 \uc2dc \uace0\ub824\uc0ac\ud56d \ubc0f \uc608\uc2dc&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/atmokpo.com\/w\/40490\/\" \/>\n<meta property=\"og:site_name\" content=\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"article:published_time\" content=\"2024-11-04T01:52:09+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-11-26T06:39:03+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\/40490\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/40490\/\"},\"author\":{\"name\":\"root\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\"},\"headline\":\"12. \ubcf4\uc0c1 \ud568\uc218(Reward Function) \uc124\uacc4\uc758 \uc911\uc694\uc131, \ubcf4\uc0c1 \uc124\uacc4 \uc2dc \uace0\ub824\uc0ac\ud56d \ubc0f \uc608\uc2dc\",\"datePublished\":\"2024-11-04T01:52:09+00:00\",\"dateModified\":\"2024-11-26T06:39:03+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/atmokpo.com\/w\/40490\/\"},\"wordCount\":13,\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"articleSection\":[\"\uac15\ud654\ud559\uc2b5\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/atmokpo.com\/w\/40490\/\",\"url\":\"https:\/\/atmokpo.com\/w\/40490\/\",\"name\":\"12. \ubcf4\uc0c1 \ud568\uc218(Reward Function) \uc124\uacc4\uc758 \uc911\uc694\uc131, \ubcf4\uc0c1 \uc124\uacc4 \uc2dc \uace0\ub824\uc0ac\ud56d \ubc0f \uc608\uc2dc - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#website\"},\"datePublished\":\"2024-11-04T01:52:09+00:00\",\"dateModified\":\"2024-11-26T06:39:03+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/atmokpo.com\/w\/40490\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/atmokpo.com\/w\/40490\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/atmokpo.com\/w\/40490\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\ud648\",\"item\":\"https:\/\/atmokpo.com\/w\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"12. \ubcf4\uc0c1 \ud568\uc218(Reward Function) \uc124\uacc4\uc758 \uc911\uc694\uc131, \ubcf4\uc0c1 \uc124\uacc4 \uc2dc \uace0\ub824\uc0ac\ud56d \ubc0f \uc608\uc2dc\"}]},{\"@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":"12. \ubcf4\uc0c1 \ud568\uc218(Reward Function) \uc124\uacc4\uc758 \uc911\uc694\uc131, \ubcf4\uc0c1 \uc124\uacc4 \uc2dc \uace0\ub824\uc0ac\ud56d \ubc0f \uc608\uc2dc - \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\/40490\/","og_locale":"ko_KR","og_type":"article","og_title":"12. \ubcf4\uc0c1 \ud568\uc218(Reward Function) \uc124\uacc4\uc758 \uc911\uc694\uc131, \ubcf4\uc0c1 \uc124\uacc4 \uc2dc \uace0\ub824\uc0ac\ud56d \ubc0f \uc608\uc2dc - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","og_description":"\uac15\ud654\ud559\uc2b5(Deep Reinforcement Learning) \ubd84\uc57c\uc5d0\uc11c \ubcf4\uc0c1 \ud568\uc218(reward function)\ub294 \uc5d0\uc774\uc804\ud2b8\uc758 \ud559\uc2b5\uacfc \uc131\ub2a5\uc744 \uacb0\uc815\uc9d3\ub294 \ud575\uc2ec \uc694\uc18c\ub85c, \uc774\ub97c \uc801\uc808\ud788 \uc124\uacc4\ud558\ub294 \uac83\uc774 \uc131\uacf5\uc801\uc778 \ubaa8\ub378 \uad6c\ucd95\uc758 \ud544\uc218 \uc870\uac74\uc785\ub2c8\ub2e4. \ubcf4\uc0c1 \ud568\uc218\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uc5d0\uc11c \ud2b9\uc815 \ud589\ub3d9\uc744 \ucde8\ud588\uc744 \ub54c \ubc1b\ub294 \ud53c\ub4dc\ubc31\uc73c\ub85c, \uc5d0\uc774\uc804\ud2b8\uac00 \ubaa9\ud45c\ub97c \ud5a5\ud574 \ub098\uc544\uac00\uac70\ub098 \ucd5c\uc801\uc758 \ud589\ub3d9\uc744 \uc120\ud0dd\ud558\ub3c4\ub85d \ub3d5\uc2b5\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \ubcf4\uc0c1 \ud568\uc218\uc758 \uc911\uc694\uc131\uacfc \uc774\ub97c \uc124\uacc4\ud560 \ub54c \uace0\ub824\ud574\uc57c \ud560 \uc0ac\ud56d, \uadf8\ub9ac\uace0 \uc2e4\uc81c \uc608\uc2dc\ub97c \ud1b5\ud574 &hellip; \ub354 \ubcf4\uae30 \"12. \ubcf4\uc0c1 \ud568\uc218(Reward Function) \uc124\uacc4\uc758 \uc911\uc694\uc131, \ubcf4\uc0c1 \uc124\uacc4 \uc2dc \uace0\ub824\uc0ac\ud56d \ubc0f \uc608\uc2dc\"","og_url":"https:\/\/atmokpo.com\/w\/40490\/","og_site_name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","article_published_time":"2024-11-04T01:52:09+00:00","article_modified_time":"2024-11-26T06:39:03+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\/40490\/#article","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/40490\/"},"author":{"name":"root","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7"},"headline":"12. \ubcf4\uc0c1 \ud568\uc218(Reward Function) \uc124\uacc4\uc758 \uc911\uc694\uc131, \ubcf4\uc0c1 \uc124\uacc4 \uc2dc \uace0\ub824\uc0ac\ud56d \ubc0f \uc608\uc2dc","datePublished":"2024-11-04T01:52:09+00:00","dateModified":"2024-11-26T06:39:03+00:00","mainEntityOfPage":{"@id":"https:\/\/atmokpo.com\/w\/40490\/"},"wordCount":13,"publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"articleSection":["\uac15\ud654\ud559\uc2b5"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/atmokpo.com\/w\/40490\/","url":"https:\/\/atmokpo.com\/w\/40490\/","name":"12. \ubcf4\uc0c1 \ud568\uc218(Reward Function) \uc124\uacc4\uc758 \uc911\uc694\uc131, \ubcf4\uc0c1 \uc124\uacc4 \uc2dc \uace0\ub824\uc0ac\ud56d \ubc0f \uc608\uc2dc - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/#website"},"datePublished":"2024-11-04T01:52:09+00:00","dateModified":"2024-11-26T06:39:03+00:00","breadcrumb":{"@id":"https:\/\/atmokpo.com\/w\/40490\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/atmokpo.com\/w\/40490\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/atmokpo.com\/w\/40490\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\ud648","item":"https:\/\/atmokpo.com\/w\/en\/"},{"@type":"ListItem","position":2,"name":"12. \ubcf4\uc0c1 \ud568\uc218(Reward Function) \uc124\uacc4\uc758 \uc911\uc694\uc131, \ubcf4\uc0c1 \uc124\uacc4 \uc2dc \uace0\ub824\uc0ac\ud56d \ubc0f \uc608\uc2dc"}]},{"@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":40490,"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":"&quot;\uac15\ud654\ud559\uc2b5&quot;\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":40490,"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":"&quot;\uac15\ud654\ud559\uc2b5&quot;\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":40490,"position":2},"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":"&quot;\uac15\ud654\ud559\uc2b5&quot;\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":40460,"url":"https:\/\/atmokpo.com\/w\/40460\/","url_meta":{"origin":40490,"position":3},"title":"8. \uc0c1\ud0dc \uacf5\uac04(State Space) \uc124\uacc4\ud558\uae30, \uc0c1\ud0dc \uc778\ucf54\ub529 \uae30\ubc95 (\ubca1\ud130\ud654, \uc6d0-\ud56b \uc778\ucf54\ub529 \ub4f1)","author":"root","date":"2024\ub144 11\uc6d4 04\uc77c","format":false,"excerpt":"\uac15\ud654\ud559\uc2b5\uc5d0\uc11c \uac00\uc7a5 \uc911\uc694\ud55c \uac1c\ub150 \uc911 \ud558\ub098\ub294 \uc0c1\ud0dc \uacf5\uac04(State Space) \uc124\uacc4\uc785\ub2c8\ub2e4. \uc0c1\ud0dc\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uc5d0\uc11c \uc5b4\ub5a4 \uc0c1\ud669\uc5d0 \ucc98\ud574 \uc788\ub294\uc9c0\ub97c \ub098\ud0c0\ub0b4\uba70, \uc0c1\ud0dc \uacf5\uac04\uc740 \uac00\ub2a5\ud55c \ubaa8\ub4e0 \uc0c1\ud0dc\uc758 \uc9d1\ud569\uc785\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \uc0c1\ud0dc \uacf5\uac04 \uc124\uacc4\uc758 \uc911\uc694\uc131\uacfc \ud568\uaed8 \ub2e4\uc591\ud55c \uc0c1\ud0dc \uc778\ucf54\ub529 \uae30\ubc95, \ud2b9\ud788 \ubca1\ud130\ud654\uc640 \uc6d0-\ud56b \uc778\ucf54\ub529\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc124\uba85\ud558\uaca0\uc2b5\ub2c8\ub2e4. \uc0c1\ud0dc \uacf5\uac04 \uc124\uacc4\uc758 \uc911\uc694\uc131 \uc0c1\ud0dc \uacf5\uac04\uc740 \uac15\ud654\ud559\uc2b5 \uc5d0\uc774\uc804\ud2b8\uac00\u2026","rel":"","context":"&quot;\uac15\ud654\ud559\uc2b5&quot;\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":40490,"position":4},"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":"&quot;\uac15\ud654\ud559\uc2b5&quot;\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":29465,"url":"https:\/\/atmokpo.com\/w\/29465\/","url_meta":{"origin":40490,"position":5},"title":"\uba38\uc2e0\ub7ec\ub2dd \ubc0f \ub525\ub7ec\ub2dd \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529, \ud45c\ubcf8 \uc678 \uc218\uc775\ub960\ub85c \uc804\uc9c4 \ubd84\uc11d","author":"root","date":"2024\ub144 10\uc6d4 27\uc77c","format":false,"excerpt":"\ucd5c\uadfc \uba87 \ub144 \uac04 \uc778\uacf5\uc9c0\ub2a5 \uae30\uc220\uc740 \uae08\uc735 \uc2dc\uc7a5\uc5d0\uc11c\uc758 \ud2b8\ub808\uc774\ub529 \ubc29\uc2dd\uc5d0 \ud601\uc2e0\uc744 \uac00\uc838\uc654\uc2b5\ub2c8\ub2e4. \uba38\uc2e0\ub7ec\ub2dd\uacfc \ub525\ub7ec\ub2dd \uc54c\uace0\ub9ac\uc998\uc744 \ud65c\uc6a9\ud55c \uc790\ub3d9\ub9e4\ub9e4 \uc2dc\uc2a4\ud15c\uc740 \ub9ce\uc740 \ud22c\uc790\uc790\uc640 \ud000\ud2b8\ub4e4\uc774 \uc801\uc6a9\ud558\uace0 \uc788\uc73c\uba70, \uadf8 \uac00\ub2a5\uc131\uc740 \ubb34\uad81\ubb34\uc9c4\ud569\ub2c8\ub2e4. \ubcf8 \uae00\uc5d0\uc11c\ub294 \uba38\uc2e0\ub7ec\ub2dd \ubc0f \ub525\ub7ec\ub2dd\uc744 \ud65c\uc6a9\ud55c \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\uc758 \uae30\ucd08\ubd80\ud130 \uace0\uae09 \uc8fc\uc81c\uc778 \ud45c\ubcf8 \uc678 \uc218\uc775\ub960 \ubd84\uc11d(Out-of-Sample Return Analysis)\uae4c\uc9c0\ub97c \uc2ec\ub3c4 \uae4a\uac8c \ub2e4\ub8e8\uc5b4 \ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. \uc54c\uace0\ub9ac\uc998 \ud2b8\ub808\uc774\ub529\u2026","rel":"","context":"&quot;\ub525\ub7ec\ub2dd \uba38\uc2e0\ub7ec\ub2dd \uc790\ub3d9 \ud2b8\ub808\uc774\ub529&quot;\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\/40490","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=40490"}],"version-history":[{"count":1,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/40490\/revisions"}],"predecessor-version":[{"id":40491,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/40490\/revisions\/40491"}],"wp:attachment":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/media?parent=40490"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/categories?post=40490"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/tags?post=40490"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}