{"id":29978,"date":"2024-10-28T03:18:58","date_gmt":"2024-10-28T03:18:58","guid":{"rendered":"http:\/\/atmokpo.com\/w\/?p=29978"},"modified":"2024-11-26T06:50:36","modified_gmt":"2024-11-26T06:50:36","slug":"%eb%94%a5%eb%9f%ac%eb%8b%9d-%ed%8c%8c%ec%9d%b4%ed%86%a0%ec%b9%98-%ea%b0%95%ec%a2%8c-%eb%b2%a8%eb%a7%8c-%ea%b8%b0%eb%8c%80-%eb%b0%a9%ec%a0%95%ec%8b%9d","status":"publish","type":"post","link":"https:\/\/atmokpo.com\/w\/29978\/","title":{"rendered":"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c,  \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd"},"content":{"rendered":"<p><body><\/p>\n<p>\n        \ub525\ub7ec\ub2dd\uacfc \uac15\ud654\ud559\uc2b5\uc758 \ubc1c\uc804\uc740 \ub9ce\uc740 \ubd84\uc57c\uc5d0 \ud601\uc2e0\uc801\uc778 \ubcc0\ud654\ub97c \uac00\uc838\uc654\uc2b5\ub2c8\ub2e4. \uadf8 \uc911\uc5d0\uc11c\ub3c4 \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd(Bellman Expectation Equation)\uc740 \uac15\ud654\ud559\uc2b5\uc758 \uc911\uc694\ud55c \uc694\uc18c\ub85c \uc790\ub9ac \uc7a1\uace0 \uc788\uc2b5\ub2c8\ub2e4. \uc774 \uacfc\uc815\uc5d0\uc11c\ub294 \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc758 \uac1c\ub150, \uc218\ud559\uc801 \ubc30\uacbd, \uadf8\ub9ac\uace0 \uc774\ub97c \ud30c\uc774\ud1a0\uce58(Pytorch)\ub97c \uc774\uc6a9\ud558\uc5ec \uad6c\ud604\ud558\ub294 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4.\n    <\/p>\n<h2>1. \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc774\ub780?<\/h2>\n<p>\n        \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc740 \ub3d9\uc801 \ud504\ub85c\uadf8\ub798\ubc0d\uc5d0\uc11c \uc0ac\uc6a9\ud558\ub294 \uc218\uc2dd\uc73c\ub85c, \uc5b4\ub5a4 \uc0c1\ud0dc\uc5d0\uc11c\uc758 \uac00\uce58\ub97c \ub2e4\uc74c\uacfc \uac19\uc774 \uc815\uc758\ud569\ub2c8\ub2e4. \uc8fc\uc5b4\uc9c4 \uc815\ucc45(\ud589\ub3d9\uc744 \uc120\ud0dd\ud558\ub294 \uaddc\uce59)\uc5d0 \ub530\ub77c \uc5d0\uc774\uc804\ud2b8\ub97c \uc6c0\uc9c1\uc77c \ub54c\uc758 \uae30\ub300 \ubcf4\uc0c1\uc744 \ub098\ud0c0\ub0c5\ub2c8\ub2e4.\n    <\/p>\n<p class=\"highlight\">\n        \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc740 \ub2e4\uc74c\uacfc \uac19\uc774 \ud45c\ud604\ub429\ub2c8\ub2e4:\n    <\/p>\n<p><code><br \/>\n        V^\\pi(s) = \\mathbb{E}_\\pi \\left[ r_t + \\gamma V^\\pi(s_{t+1}) | s_t = s \\right]<br \/>\n    <\/code><\/p>\n<p>\n        \uc5ec\uae30\uc11c <code>V^\\pi(s)<\/code>\ub294 \uc0c1\ud0dc <code>s<\/code>\uc5d0\uc11c \uc815\ucc45 <code>\\pi<\/code>\uc5d0 \ub530\ub978 \uae30\ub300 \uac12, <code>r_t<\/code>\ub294 \uc2dc\uac04 <code>t<\/code>\uc5d0\uc11c\uc758 \ubcf4\uc0c1, <code>\\gamma<\/code>\ub294 \ud560\uc778 \uc778\uc790, <code>s_{t+1}<\/code>\ub294 \ub2e4\uc74c \uc0c1\ud0dc\uc785\ub2c8\ub2e4.<br \/>\n        \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc744 \uc774\uc6a9\ud558\uba74 \ubaa8\ub4e0 \uac00\ub2a5\ud55c \uc815\ucc45\uc744 \ud3c9\uac00\ud558\uace0 \ucd5c\uc801\uc758 \uc815\ucc45\uc744 \ucc3e\ub294 \ub370 \ub9e4\uc6b0 \uc720\uc6a9\ud569\ub2c8\ub2e4.\n    <\/p>\n<h2>2. \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc758 \ud575\uc2ec \uac1c\ub150<\/h2>\n<p>\n        \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc744 \uc774\ud574\ud558\uae30 \uc704\ud574\uc11c\ub294 \ub2e4\uc74c\uacfc \uac19\uc740 \uae30\ubcf8 \uac1c\ub150\uc774 \ud544\uc694\ud569\ub2c8\ub2e4:\n    <\/p>\n<h3>2.1 \uc0c1\ud0dc\uc640 \ud589\ub3d9<\/h3>\n<p>\n        \uac15\ud654\ud559\uc2b5\uc5d0\uc11c \uc0c1\ud0dc(State)\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \ud604\uc7ac \ucc98\ud574 \uc788\ub294 \uc0c1\ud669\uc744 \ub098\ud0c0\ub0b4\uba70, \ud589\ub3d9(Action)\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \uc774 \uc0c1\ud0dc\uc5d0\uc11c \uc120\ud0dd\ud560 \uc218 \uc788\ub294 \ud589\ub3d9\uc758 \uc9d1\ud569\uc785\ub2c8\ub2e4. \uc774 \ub450 \uc694\uc18c\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uacfc \uc0c1\ud638\uc791\uc6a9\ud558\ub294 \ub370 \ud544\uc218\uc801\uc785\ub2c8\ub2e4.\n    <\/p>\n<h3>2.2 \uc815\ucc45<\/h3>\n<p>\n        \uc815\ucc45(Policy)\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \ud2b9\uc815 \uc0c1\ud0dc\uc5d0\uc11c \uc5b4\ub5a4 \ud589\ub3d9\uc744 \uc120\ud0dd\ud560\uc9c0\ub97c \uacb0\uc815\ud558\ub294 \uaddc\uce59\uc785\ub2c8\ub2e4. \uc815\ucc45\uc740 \ud655\ub960\uc801\uc73c\ub85c \uc815\uc758\ub420 \uc218 \uc788\uc73c\uba70, \ucd5c\uc801 \uc815\ucc45\uc740 \uc8fc\uc5b4\uc9c4 \uc0c1\ud0dc\uc5d0\uc11c \ucd5c\ub300\uc758 \uae30\ub300 \ubcf4\uc0c1\uc744 \uc5bb\ub294 \ud589\ub3d9\uc744 \uc120\ud0dd\ud569\ub2c8\ub2e4.\n    <\/p>\n<h3>2.3 \ubcf4\uc0c1<\/h3>\n<p>\n        \ubcf4\uc0c1(Reward)\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \ud2b9\uc815 \ud589\ub3d9\uc744 \uc120\ud0dd\ud588\uc744 \ub54c \ud658\uacbd\uc73c\ub85c\ubd80\ud130 \ubc1b\ub294 \ud53c\ub4dc\ubc31\uc785\ub2c8\ub2e4. \ubcf4\uc0c1\uc740 \uc5d0\uc774\uc804\ud2b8\uac00 \ubaa9\ud45c\ub97c \ub2ec\uc131\ud558\ub294 \ub370 \uc5bc\ub9c8\ub098 \uc798\ud558\uace0 \uc788\ub294\uc9c0\ub97c \ud3c9\uac00\ud558\ub294 \uae30\uc900\uc774 \ub429\ub2c8\ub2e4.\n    <\/p>\n<h2>3. \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc758 \uae30\ud558\ud559\uc801 \ud574\uc11d<\/h2>\n<p>\n        \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc744 \uae30\ud558\ud559\uc801\uc73c\ub85c \ud574\uc11d\ud558\uba74, \uac01 \uc0c1\ud0dc\uc758 \uac00\uce58\ub294 \ud574\ub2f9 \ud589\ub3d9\uc744 \ud1b5\ud574 \ub3c4\ub2ec\ud560 \uc218 \uc788\ub294 \ubbf8\ub798\uc758 \uae30\ub300 \ubcf4\uc0c1\uc758 \ud3c9\uade0\uc73c\ub85c \ubcfc \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc774 \uc758\ubbf8\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \uc5b4\ub5a4 \uc0c1\ud0dc\uc5d0\uc11c \ud589\ub3d9\uc744 \ucde8\ud588\uc744 \ub54c, \uadf8 \ud589\ub3d9\uc73c\ub85c \uc778\ud574 \uc5bb\uc744 \uc218 \uc788\ub294 \ubcf4\uc0c1\uc758 \uae30\ub300\uce58\ub97c \uacc4\uc0b0\ud558\ub294 \uac83\uc774\ub77c \ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.\n    <\/p>\n<h2>4. \ud30c\uc774\ud1a0\uce58\uc5d0\uc11c \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd \uad6c\ud604\ud558\uae30<\/h2>\n<p>\n        \uc774\uc81c \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc744 \ud30c\uc774\ud1a0\uce58\ub97c \uc774\uc6a9\ud558\uc5ec \uad6c\ud604\ud558\ub294 \ubc29\ubc95\uc744 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \uac04\ub2e8\ud55c \uc608\uc81c\ub85c\ub294 OpenAI\uc758 Gym \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc0ac\uc6a9\ud558\uc5ec \uc5d0\uc774\uc804\ud2b8\ub97c \ud6c8\ub828\uc2dc\ud0a4\uace0, \uc774\ub97c \ud1b5\ud574 \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc744 \uc801\uc6a9\ud574 \ubcf4\uaca0\uc2b5\ub2c8\ub2e4.\n    <\/p>\n<h3>4.1. \ud658\uacbd \uc124\uc815<\/h3>\n<p>\n        \uba3c\uc800 \ud544\uc694\ud55c \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc124\uce58\ud558\uace0 \ud658\uacbd\uc744 \uc124\uc815\ud569\ub2c8\ub2e4. OpenAI Gym\uc740 \ub2e4\uc591\ud55c \uac15\ud654\ud559\uc2b5 \ud658\uacbd\uc744 \uc81c\uacf5\ud558\ub294 \ub77c\uc774\ube0c\ub7ec\ub9ac\uc785\ub2c8\ub2e4.\n    <\/p>\n<p><code><br \/>\n        !pip install gym<br \/>\n        !pip install torch<br \/>\n        !pip install matplotlib<br \/>\n    <\/code><\/p>\n<h3>4.2. \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd \uad6c\ud604<\/h3>\n<p>\n        \uc544\ub798 \uc608\uc81c\uc5d0\uc11c\ub294 \uac04\ub2e8\ud55c \ud14c\uc774\ube14 \uc0c1\ud0dc \uacf5\uac04\uc744 \uac00\uc9c4 MDP(Markov Decision Process) \ud658\uacbd\uc744 \uad6c\ud604\ud558\uc5ec \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc744 \uc801\uc6a9\ud569\ub2c8\ub2e4.\n    <\/p>\n<p><code><br \/>\n    import numpy as np<br \/>\n    import torch<\/p>\n<p>    class SimpleMDP:<br \/>\n        def __init__(self):<br \/>\n            self.states = [0, 1, 2]<br \/>\n            self.actions = [0, 1]  # 0: \uc67c\ucabd, 1: \uc624\ub978\ucabd<br \/>\n            self.transition_probs = {<br \/>\n                0: {0: (0, 0.8), 1: (1, 0.2)},<br \/>\n                1: {0: (0, 0.3), 1: (2, 0.7)},<br \/>\n                2: {0: (2, 1.0), 1: (2, 1.0)},<br \/>\n            }<br \/>\n            self.rewards = [0, 1, 10]  # \uac01 \uc0c1\ud0dc\uc5d0 \ub300\ud55c \ubcf4\uc0c1<br \/>\n            self.gamma = 0.9  # \ud560\uc778 \uc778\uc790<\/p>\n<p>        def get_next_state(self, state, action):<br \/>\n            next_state, prob = self.transition_probs[state][action]<br \/>\n            return next_state, prob<\/p>\n<p>        def get_reward(self, state):<br \/>\n            return self.rewards[state]<\/p>\n<p>        def value_iteration(self, theta=1e-6):<br \/>\n            V = np.zeros(len(self.states))  # \uc0c1\ud0dc \uac12 \ucd08\uae30\ud654<br \/>\n            while True:<br \/>\n                delta = 0<br \/>\n                for s in self.states:<br \/>\n                    v = V[s]<br \/>\n                    V[s] = max(sum(prob * (self.get_reward(next_state) + self.gamma * V[next_state])<br \/>\n                                   for next_state, prob in [self.get_next_state(s, a) for a in self.actions])<br \/>\n                               for a in self.actions)<br \/>\n                    delta = max(delta, abs(v - V[s]))<br \/>\n                if delta &lt; theta:<br \/>\n                    break<br \/>\n            return V<\/p>\n<p>    # MDP \ud658\uacbd \ucd08\uae30\ud654 \ubc0f \uac00\uce58 \ubc18\ubcf5 \uc218\ud589<br \/>\n    mdp_environment = SimpleMDP()<br \/>\n    values = mdp_environment.value_iteration()<br \/>\n    print(\"\uc0c1\ud0dc \uac12:\", values)<br \/>\n    <\/code><\/p>\n<h3>4.3. \ucf54\ub4dc \uc124\uba85<\/h3>\n<p>\n        \uc704 \ucf54\ub4dc\uc5d0\uc11c <code>SimpleMDP<\/code> \ud074\ub798\uc2a4\ub294 \uac04\ub2e8\ud55c \ub9c8\ub974\ucf54\ud504 \uacb0\uc815 \uacfc\uc815\uc758 \uc0c1\ud0dc, \ud589\ub3d9, \uc804\uc774 \ud655\ub960\uc744 \uc815\uc758\ud569\ub2c8\ub2e4. \uac00\uce58 \ubc18\ubcf5(Value Iteration) \uc54c\uace0\ub9ac\uc998\uc744 \uc0ac\uc6a9\ud558\uc5ec \uac01 \uc0c1\ud0dc\uc758 \uac00\uce58\ub97c \uc5c5\ub370\uc774\ud2b8\ud569\ub2c8\ub2e4. \uc54c\uace0\ub9ac\uc998\uc740 \uc0c1\ud0dc\ub9c8\ub2e4 \uac00\ub2a5\ud55c \ubaa8\ub4e0 \ud589\ub3d9\uc5d0 \ub300\ud574 \ub2e4\uc74c \uc0c1\ud0dc\uc5d0 \ub300\ud55c \uc608\uc0c1 \ubcf4\uc0c1\uc744 \uacc4\uc0b0\ud558\uace0 \uadf8 \uc911 \ucd5c\ub300 \uac12\uc744 \uc120\ud0dd\ud569\ub2c8\ub2e4.\n    <\/p>\n<h2>5. \uc2e4\ud5d8 \ubc0f \uacb0\uacfc<\/h2>\n<p>\n        \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc744 \uc801\uc6a9\ud55c \ud6c4, \uc5bb\uc5b4\uc9c4 \uc0c1\ud0dc \uac12\uc740 \ub2e4\uc74c\uacfc \uac19\uc740 \uacb0\uacfc\ub85c \ucd9c\ub825\ub429\ub2c8\ub2e4.<br \/>\n        <br \/>\n<code><br \/>\n        \uc0c1\ud0dc \uac12: [0.0, 9.0, 10.0]<br \/>\n        <\/code>\n<\/p>\n<p>\n        \uc774\ub7ec\ud55c \uacb0\uacfc\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \uac01 \uc0c1\ud0dc\uc5d0\uc11c \uc5bb\uc744 \uc218 \uc788\ub294 \uae30\ub300 \ubcf4\uc0c1\uc744 \ub098\ud0c0\ub0c5\ub2c8\ub2e4. \uc0c1\ud0dc 2\uc5d0\uc11c\uc758 \uac00\uce58\uac00 10\uc778 \uac83\uc740 \uc774 \uc0c1\ud0dc\uc5d0\uc11c\uc758 \ubcf4\uc0c1\uc774 \uac00\uc7a5 \ud06c\ub2e4\ub294 \uac83\uc744 \uc758\ubbf8\ud569\ub2c8\ub2e4.\n    <\/p>\n<h2>6. \uacb0\ub860<\/h2>\n<p>\n        \ubcf8 \uac15\uc88c\uc5d0\uc11c\ub294 \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc758 \uc774\ub860\uc801 \ubc30\uacbd\uacfc \uc774\ub97c \ud30c\uc774\ud1a0\uce58\ub97c \uc774\uc6a9\ud55c \ud504\ub85c\uadf8\ub798\ubc0d\uc744 \ud1b5\ud574 \uc2e4\uc81c\ub85c \uad6c\ud604\ud558\ub294 \ubc29\ubc95\uc744 \ub2e4\ub8e8\uc5c8\uc2b5\ub2c8\ub2e4. \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc740 \uac15\ud654\ud559\uc2b5\uc758 \uae30\ubcf8\uc774 \ub418\ub294 \uc218\uc2dd\uc73c\ub85c, \ub2e4\uc591\ud55c \ud658\uacbd\uc5d0\uc11c \uc5d0\uc774\uc804\ud2b8\uc758 \ud589\ub3d9\uc744 \ucd5c\uc801\ud654\ud558\ub294 \ub370 \ud544\uc218\uc801\uc778 \uc694\uc18c\uc785\ub2c8\ub2e4.\n    <\/p>\n<p>\n        \uc55e\uc73c\ub85c\ub3c4 \uac15\ud654\ud559\uc2b5\uc758 \ub2e4\uc591\ud55c \uae30\ubc95\ub4e4\uacfc \uc774\ub860\ub4e4\uc744 \uc9c0\uc18d\uc801\uc73c\ub85c \ud0d0\uad6c\ud558\uba70 \uc2e4\uc2b5\ud558\uae38 \ubc14\ub78d\ub2c8\ub2e4. \ub525\ub7ec\ub2dd\uacfc \uac15\ud654\ud559\uc2b5\uc758 \uc138\uacc4\uc5d0 \ubc1c\uc744 \ub4e4\uc5ec\ub193\uc740 \ubaa8\ub4e0 \uc774\ub4e4\uc774 \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc744 \ud1b5\ud574 \ub9ce\uc740 \uc131\uacfc\ub97c \uc774\ub8e8\uae38 \ubc14\ub78d\ub2c8\ub2e4.\n    <\/p>\n<p><\/body><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\ub525\ub7ec\ub2dd\uacfc \uac15\ud654\ud559\uc2b5\uc758 \ubc1c\uc804\uc740 \ub9ce\uc740 \ubd84\uc57c\uc5d0 \ud601\uc2e0\uc801\uc778 \ubcc0\ud654\ub97c \uac00\uc838\uc654\uc2b5\ub2c8\ub2e4. \uadf8 \uc911\uc5d0\uc11c\ub3c4 \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd(Bellman Expectation Equation)\uc740 \uac15\ud654\ud559\uc2b5\uc758 \uc911\uc694\ud55c \uc694\uc18c\ub85c \uc790\ub9ac \uc7a1\uace0 \uc788\uc2b5\ub2c8\ub2e4. \uc774 \uacfc\uc815\uc5d0\uc11c\ub294 \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc758 \uac1c\ub150, \uc218\ud559\uc801 \ubc30\uacbd, \uadf8\ub9ac\uace0 \uc774\ub97c \ud30c\uc774\ud1a0\uce58(Pytorch)\ub97c \uc774\uc6a9\ud558\uc5ec \uad6c\ud604\ud558\ub294 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc774\ub780? \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc740 \ub3d9\uc801 \ud504\ub85c\uadf8\ub798\ubc0d\uc5d0\uc11c \uc0ac\uc6a9\ud558\ub294 \uc218\uc2dd\uc73c\ub85c, \uc5b4\ub5a4 \uc0c1\ud0dc\uc5d0\uc11c\uc758 \uac00\uce58\ub97c \ub2e4\uc74c\uacfc \uac19\uc774 \uc815\uc758\ud569\ub2c8\ub2e4. &hellip; <a href=\"https:\/\/atmokpo.com\/w\/29978\/\" class=\"more-link\">\ub354 \ubcf4\uae30<span class=\"screen-reader-text\"> &#8220;\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c,  \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd&#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":[33],"tags":[],"class_list":["post-29978","post","type-post","status-publish","format-standard","hentry","category-33"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.2 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd - \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\/29978\/\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"og:description\" content=\"\ub525\ub7ec\ub2dd\uacfc \uac15\ud654\ud559\uc2b5\uc758 \ubc1c\uc804\uc740 \ub9ce\uc740 \ubd84\uc57c\uc5d0 \ud601\uc2e0\uc801\uc778 \ubcc0\ud654\ub97c \uac00\uc838\uc654\uc2b5\ub2c8\ub2e4. \uadf8 \uc911\uc5d0\uc11c\ub3c4 \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd(Bellman Expectation Equation)\uc740 \uac15\ud654\ud559\uc2b5\uc758 \uc911\uc694\ud55c \uc694\uc18c\ub85c \uc790\ub9ac \uc7a1\uace0 \uc788\uc2b5\ub2c8\ub2e4. \uc774 \uacfc\uc815\uc5d0\uc11c\ub294 \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc758 \uac1c\ub150, \uc218\ud559\uc801 \ubc30\uacbd, \uadf8\ub9ac\uace0 \uc774\ub97c \ud30c\uc774\ud1a0\uce58(Pytorch)\ub97c \uc774\uc6a9\ud558\uc5ec \uad6c\ud604\ud558\ub294 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc774\ub780? \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc740 \ub3d9\uc801 \ud504\ub85c\uadf8\ub798\ubc0d\uc5d0\uc11c \uc0ac\uc6a9\ud558\ub294 \uc218\uc2dd\uc73c\ub85c, \uc5b4\ub5a4 \uc0c1\ud0dc\uc5d0\uc11c\uc758 \uac00\uce58\ub97c \ub2e4\uc74c\uacfc \uac19\uc774 \uc815\uc758\ud569\ub2c8\ub2e4. &hellip; \ub354 \ubcf4\uae30 &quot;\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/atmokpo.com\/w\/29978\/\" \/>\n<meta property=\"og:site_name\" content=\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"article:published_time\" content=\"2024-10-28T03:18:58+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-11-26T06:50:36+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\/29978\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/29978\/\"},\"author\":{\"name\":\"root\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\"},\"headline\":\"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\",\"datePublished\":\"2024-10-28T03:18:58+00:00\",\"dateModified\":\"2024-11-26T06:50:36+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/atmokpo.com\/w\/29978\/\"},\"wordCount\":18,\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"articleSection\":[\"\ud30c\uc774\ud1a0\uce58 \uac15\uc88c\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/atmokpo.com\/w\/29978\/\",\"url\":\"https:\/\/atmokpo.com\/w\/29978\/\",\"name\":\"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#website\"},\"datePublished\":\"2024-10-28T03:18:58+00:00\",\"dateModified\":\"2024-11-26T06:50:36+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/atmokpo.com\/w\/29978\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/atmokpo.com\/w\/29978\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/atmokpo.com\/w\/29978\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\ud648\",\"item\":\"https:\/\/atmokpo.com\/w\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\"}]},{\"@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":"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd - \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\/29978\/","og_locale":"ko_KR","og_type":"article","og_title":"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","og_description":"\ub525\ub7ec\ub2dd\uacfc \uac15\ud654\ud559\uc2b5\uc758 \ubc1c\uc804\uc740 \ub9ce\uc740 \ubd84\uc57c\uc5d0 \ud601\uc2e0\uc801\uc778 \ubcc0\ud654\ub97c \uac00\uc838\uc654\uc2b5\ub2c8\ub2e4. \uadf8 \uc911\uc5d0\uc11c\ub3c4 \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd(Bellman Expectation Equation)\uc740 \uac15\ud654\ud559\uc2b5\uc758 \uc911\uc694\ud55c \uc694\uc18c\ub85c \uc790\ub9ac \uc7a1\uace0 \uc788\uc2b5\ub2c8\ub2e4. \uc774 \uacfc\uc815\uc5d0\uc11c\ub294 \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc758 \uac1c\ub150, \uc218\ud559\uc801 \ubc30\uacbd, \uadf8\ub9ac\uace0 \uc774\ub97c \ud30c\uc774\ud1a0\uce58(Pytorch)\ub97c \uc774\uc6a9\ud558\uc5ec \uad6c\ud604\ud558\ub294 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc774\ub780? \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\uc740 \ub3d9\uc801 \ud504\ub85c\uadf8\ub798\ubc0d\uc5d0\uc11c \uc0ac\uc6a9\ud558\ub294 \uc218\uc2dd\uc73c\ub85c, \uc5b4\ub5a4 \uc0c1\ud0dc\uc5d0\uc11c\uc758 \uac00\uce58\ub97c \ub2e4\uc74c\uacfc \uac19\uc774 \uc815\uc758\ud569\ub2c8\ub2e4. &hellip; \ub354 \ubcf4\uae30 \"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd\"","og_url":"https:\/\/atmokpo.com\/w\/29978\/","og_site_name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","article_published_time":"2024-10-28T03:18:58+00:00","article_modified_time":"2024-11-26T06:50:36+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\/29978\/#article","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/29978\/"},"author":{"name":"root","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7"},"headline":"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd","datePublished":"2024-10-28T03:18:58+00:00","dateModified":"2024-11-26T06:50:36+00:00","mainEntityOfPage":{"@id":"https:\/\/atmokpo.com\/w\/29978\/"},"wordCount":18,"publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"articleSection":["\ud30c\uc774\ud1a0\uce58 \uac15\uc88c"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/atmokpo.com\/w\/29978\/","url":"https:\/\/atmokpo.com\/w\/29978\/","name":"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/#website"},"datePublished":"2024-10-28T03:18:58+00:00","dateModified":"2024-11-26T06:50:36+00:00","breadcrumb":{"@id":"https:\/\/atmokpo.com\/w\/29978\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/atmokpo.com\/w\/29978\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/atmokpo.com\/w\/29978\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\ud648","item":"https:\/\/atmokpo.com\/w\/en\/"},{"@type":"ListItem","position":2,"name":"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \ubca8\ub9cc \uae30\ub300 \ubc29\uc815\uc2dd"}]},{"@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":[],"_links":{"self":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/29978","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=29978"}],"version-history":[{"count":1,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/29978\/revisions"}],"predecessor-version":[{"id":29979,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/29978\/revisions\/29979"}],"wp:attachment":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/media?parent=29978"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/categories?post=29978"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/tags?post=29978"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}