\ud2b8\ub808\uc774\ub2dd \uc190\uc2e4(Training Loss)<\/strong>: \uc5d0\uc774\uc804\ud2b8\uc758 \ud559\uc2b5 \uacfc\uc815\uc5d0\uc11c \uc190\uc2e4 \ud568\uc218\uc758 \uac12\uc744 \ucd94\uc801\ud568\uc73c\ub85c\uc368, \ud559\uc2b5\uc774 \uc798 \uc9c4\ud589\ub418\uace0 \uc788\ub294\uc9c0\ub97c \ubd84\uc11d\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/li>\n<\/ul>\n3. \uac15\ud654\ud559\uc2b5 \uc5d0\uc774\uc804\ud2b8 \ud3c9\uac00 \ubc29\ubc95<\/h2>\n
RL \uc5d0\uc774\uc804\ud2b8\ub97c \ud3c9\uac00\ud558\ub294 \ubc29\ubc95\uc740 \uc5ec\ub7ec \uac00\uc9c0\uac00 \uc788\uc73c\uba70, \ub2e4\uc74c\uacfc \uac19\uc740 \ub2e8\uacc4\ub85c \uc9c4\ud589\ub429\ub2c8\ub2e4:<\/p>\n
3.1. \uc5d0\ud53c\uc18c\ub4dc \uc218\uc9d1<\/h3>\n
\uc5d0\uc774\uc804\ud2b8\uac00 \ud559\uc2b5\ud55c \uc815\ucc45\uc744 \ubc14\ud0d5\uc73c\ub85c \uc5ec\ub7ec \uc5d0\ud53c\uc18c\ub4dc\ub97c \uc2e4\ud589\ud558\uc5ec \ub370\uc774\ud130\ub97c \uc218\uc9d1\ud569\ub2c8\ub2e4. \uc774\ub54c, \uac01\uac01\uc758 \uc5d0\ud53c\uc18c\ub4dc\ub294 \uc0c1\ud0dc-\ud589\ub3d9-\ubcf4\uc0c1-\ub2e4\uc74c \uc0c1\ud0dc\uc758 \uc30d\uc73c\ub85c \uad6c\uc131\ub429\ub2c8\ub2e4.<\/p>\n
3.2. \uc131\ub2a5 \uc9c0\ud45c \uacc4\uc0b0<\/h3>\n
\uc218\uc9d1\ud55c \uc5d0\ud53c\uc18c\ub4dc\uc5d0\uc11c \uc815\uc758\ud55c \uc131\ub2a5 \uc9c0\ud45c\ub97c \uacc4\uc0b0\ud558\uc5ec \uc5d0\uc774\uc804\ud2b8\uc758 \uc131\ub2a5\uc744 \ud3c9\uac00\ud569\ub2c8\ub2e4. \uc608\ub97c \ub4e4\uc5b4, \ud3c9\uade0 \ubcf4\uc0c1, \uc5d0\ud53c\uc18c\ub4dc \uae38\uc774, \ubcf4\uc0c1\uc758 \ubd84\ud3ec\ub97c \uacc4\uc0b0\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n
3.3. \uc2dc\uac01\ud654 \ubc0f \ubd84\uc11d<\/h3>\n
\uc131\ub2a5 \uc9c0\ud45c\ub97c \uc2dc\uac01\ud654\ud558\uc5ec \ud559\uc2b5\uc758 \uacbd\uacfc\uc640 \ubc29\uc2dd\uc744 \uc774\ud574\ud569\ub2c8\ub2e4. \uadf8\ub798\ud504\ub97c \ud1b5\ud574 \uc5d0\uc774\uc804\ud2b8\uc758 \ud559\uc2b5\uc774 \uc798 \uc774\ub8e8\uc5b4\uc9c0\uace0 \uc788\ub294\uc9c0\ub97c \ube60\ub974\uac8c \ud30c\uc545\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n
4. RL \uc5d0\uc774\uc804\ud2b8 \ub514\ubc84\uae45<\/h2>\n
\uac15\ud654\ud559\uc2b5 \uc5d0\uc774\uc804\ud2b8\uc758 \ub514\ubc84\uae45\uc740 \ud2b9\ud788 \uc911\uc694\ud569\ub2c8\ub2e4. \ub2e4\uc74c\uc740 \ud6a8\uacfc\uc801\uc778 \ub514\ubc84\uae45 \ubc29\ubc95\ub4e4\uc785\ub2c8\ub2e4:<\/p>\n
4.1. \ub85c\uadf8 \ubd84\uc11d<\/h3>\n
\uc5d0\uc774\uc804\ud2b8\uc758 \ud589\ub3d9\uacfc \ubcf4\uc0c1\uc744 \uae30\ub85d\ud558\ub294 \ub85c\uadf8\ub97c \uc720\uc9c0\ud558\uace0 \ubd84\uc11d\ud558\uc5ec, \uc5b4\ub5a4 \ud589\ub3d9\uc774 \uc88b\uc558\uace0 \ub098\ube74\ub294\uc9c0\ub97c \ud310\ub2e8\ud569\ub2c8\ub2e4. \ub85c\uadf8 \ub370\uc774\ud130\ub97c \ubd84\uc11d\ud558\uba74 \uc5d0\uc774\uc804\ud2b8\uc758 \uc798\ubabb\ub41c \uc120\ud0dd\uc774\ub098 \uc815\ucc45\uc758 \ubb38\uc81c\uc810\uc744 \ubc1c\uacac\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n
4.2. \ud558\uc774\ud37c\ud30c\ub77c\ubbf8\ud130 \uc870\uc815<\/h3>\n
\ud558\uc774\ud37c\ud30c\ub77c\ubbf8\ud130\ub294 \ud559\uc2b5\ub960, \ud560\uc778 \uc778\uc790, \ub124\ud2b8\uc6cc\ud06c \ud06c\uae30\uc640 \uac19\uc740 \uc694\uc18c\ub4e4\ub85c \uad6c\uc131\ub429\ub2c8\ub2e4. \uc774\ub7ec\ud55c \ud30c\ub77c\ubbf8\ud130\ub97c \uc870\uc815\ud568\uc73c\ub85c\uc368 \uc5d0\uc774\uc804\ud2b8\uc758 \uc131\ub2a5\uc744 \ud5a5\uc0c1\uc2dc\ud0ac \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n
4.3. \ubaa8\ub378 \ud3c9\uac00<\/h3>\n
\ubaa8\ub378\uc774 \uacfc\uc801\ud569\uc5d0 \ube60\uc9c0\uc9c0 \uc54a\uc558\ub294\uc9c0 \ud655\uc778\ud558\uace0, \ud6c8\ub828 \ub370\uc774\ud130\uc640 \ud14c\uc2a4\ud2b8 \ub370\uc774\ud130\ub97c \ubd84\ub9ac\ud558\uc5ec \uc774\ub97c \ud3c9\uac00\ud569\ub2c8\ub2e4. \uad50\ucc28 \uac80\uc99d\uc744 \uc218\ud589\ud558\ub294 \uac83\ub3c4 \uc88b\uc740 \ubc29\ubc95\uc785\ub2c8\ub2e4.<\/p>\n
4.4. \ub2e4\uc591\ud55c \ud658\uacbd \ud14c\uc2a4\ud2b8<\/h3>\n
\uc5d0\uc774\uc804\ud2b8\ub97c \ub2e4\uc591\ud55c \ud658\uacbd\uc5d0 \ubc30\uce58\ud558\uc5ec \uadf8 \uc131\ub2a5\uc744 \uc2dc\ud5d8\ud574 \ubc14\ub85c\uc7a1\uc744 \ud544\uc694\uac00 \uc788\uc2b5\ub2c8\ub2e4. \uc774\ub54c \uc5d0\uc774\uc804\ud2b8\uac00 \ub2e4\ub978 \uc0c1\ud669\uc5d0\uc11c\ub3c4 \uc798 \uc791\ub3d9\ud558\ub294\uc9c0 \ud655\uc778\ud558\ub294 \uac83\uc774 \uc911\uc694\ud569\ub2c8\ub2e4.<\/p>\n
5. \uc608\uc81c \ucf54\ub4dc: RL \uc5d0\uc774\uc804\ud2b8 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45<\/h2>\n
\uc774\uc81c \uac04\ub2e8\ud55c \uc608\uc81c\ub97c \ud1b5\ud574 RL \uc5d0\uc774\uc804\ud2b8\ub97c \ud3c9\uac00\ud558\uace0 \ub514\ubc84\uae45\ud558\ub294 \ubc29\ubc95\uc744 \uc0b4\ud3b4\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \uc544\ub798\ub294 OpenAI\uc758 Gym \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc0ac\uc6a9\ud558\uc5ec Q-learning \uc5d0\uc774\uc804\ud2b8\ub97c \ud3c9\uac00\ud558\uace0 \uc131\ub2a5 \uc9c0\ud45c\ub97c \uae30\ub85d\ud558\ub294 \ucf54\ub4dc\uc785\ub2c8\ub2e4.<\/p>\n
import gym\nimport numpy as np\nimport matplotlib.pyplot as plt\n\n# \ud658\uacbd \uc0dd\uc131\nenv = gym.make('CartPole-v1')\n\n# Q-\ud14c\uc774\ube14 \ucd08\uae30\ud654\nQ = np.zeros((env.observation_space.n, env.action_space.n))\n\n# \ud558\uc774\ud37c\ud30c\ub77c\ubbf8\ud130 \uc124\uc815\nlearning_rate = 0.1\ndiscount_factor = 0.95\nnum_episodes = 1000\n\n# \uc131\ub2a5 \ud3c9\uac00 \ubcc0\uc218\nrewards_per_episode = []\n\nfor episode in range(num_episodes):\n state = env.reset()\n total_reward = 0\n done = False\n \n while not done:\n # Epsilon-greedy \uc815\ucc45\n if np.random.rand() < 0.1:\n action = env.action_space.sample()\n else:\n action = np.argmax(Q[state, :])\n \n next_state, reward, done, _ = env.step(action)\n \n # Q-\ud14c\uc774\ube14 \uc5c5\ub370\uc774\ud2b8\n Q[state, action] = Q[state, action] + learning_rate * (reward + discount_factor * np.max(Q[next_state, :]) - Q[state, action])\n \n total_reward += reward\n state = next_state\n \n rewards_per_episode.append(total_reward)\n\n# \ud3c9\uade0 \ubcf4\uc0c1 \uacc4\uc0b0\naverage_reward = np.mean(rewards_per_episode)\n\n# \uc131\ub2a5 \uacb0\uacfc \uc2dc\uac01\ud654\nplt.plot(rewards_per_episode)\nplt.xlabel('Episode')\nplt.ylabel('Reward')\nplt.title('Rewards per Episode')\nplt.show()\n\nprint(f\"Average Reward: {average_reward}\")\n<\/code><\/pre>\n\uc704 \ucf54\ub4dc\uc5d0\uc11c Q-learning \uc54c\uace0\ub9ac\uc998\uc744 \uc0ac\uc6a9\ud558\uc5ec CartPole \ud658\uacbd\uc5d0\uc11c \uc5d0\uc774\uc804\ud2b8\ub97c \ud559\uc2b5\uc2dc\ud0a4\uace0 \uac01 \uc5d0\ud53c\uc18c\ub4dc\uc5d0\uc11c \uc5bb\uc740 \ubcf4\uc0c1\uc744 \uae30\ub85d\ud569\ub2c8\ub2e4. \ucd5c\uc885\uc801\uc73c\ub85c \ud3c9\uade0 \ubcf4\uc0c1\uc744 \ucd9c\ub825\ud558\uace0, \uac01 \uc5d0\ud53c\uc18c\ub4dc\uc5d0\uc11c \ubcf4\uc0c1\uc744 \uc2dc\uac01\ud654\ud569\ub2c8\ub2e4.<\/p>\n
6. \uacb0\ub860<\/h2>\n
\uac15\ud654\ud559\uc2b5 \uc5d0\uc774\uc804\ud2b8\uc758 \uc131\ub2a5 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45\uc740 \ud6a8\uacfc\uc801\uc778 \ubaa8\ub378 \uac1c\ubc1c\uc5d0 \uc788\uc5b4\uc11c \ud544\uc218\uc801\uc778 \uacfc\uc815\uc785\ub2c8\ub2e4. \ub2e4\uc591\ud55c \ud3c9\uac00 \uc9c0\ud45c\ub97c \ud65c\uc6a9\ud558\uace0, \ubaa8\ub378\uc744 \uc9c0\uc18d\uc801\uc73c\ub85c \ubaa8\ub2c8\ud130\ub9c1\ud558\uc5ec \uc131\ub2a5\uc744 \ucd5c\uc801\ud654\ud568\uc73c\ub85c\uc368 \uc2e4\uc81c \uc0c1\ud669\uc5d0 \uc801\ud569\ud55c \uc5d0\uc774\uc804\ud2b8\ub97c \uad6c\ucd95\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4. \uc55e\uc73c\ub85c\ub3c4 \uac15\ud654\ud559\uc2b5 \ubd84\uc57c\uc5d0\uc11c \ucde8\uc57d\uc810\uc744 \ubcf4\uc644\ud558\uace0, \uc0c8\ub85c\uc6b4 \uae30\uc220\uc744 \uc801\uc6a9\ud558\uc5ec \ud6a8\uacfc\uc801\uc778 \uc5d0\uc774\uc804\ud2b8\ub97c \uac1c\ubc1c\ud574 \ub098\uac00\uae38 \ubc14\ub78d\ub2c8\ub2e4.<\/p>\n
\uac10\uc0ac\ud569\ub2c8\ub2e4.<\/p>\n
<\/body><\/p>\n","protected":false},"excerpt":{"rendered":"
\uac15\ud654\ud559\uc2b5( Reinforcement Learning, RL) \ubd84\uc57c\uc5d0\uc11c\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uacfc \uc0c1\ud638 \uc791\uc6a9\ud558\uba70 \ucd5c\uc801\uc758 \ud589\ub3d9 \uc815\ucc45\uc744 \ud559\uc2b5\ud558\ub294 \uac83\uc774 \ud575\uc2ec\uc785\ub2c8\ub2e4. \uadf8\ub7ec\ub098 \uc774 \uacfc\uc815\uc5d0\uc11c \uc5d0\uc774\uc804\ud2b8\uc758 \uc131\ub2a5\uc744 \ud3c9\uac00\ud558\uace0 \ud6a8\uc728\uc801\uc73c\ub85c \ub514\ubc84\uae45\ud558\ub294 \uac83\uc740 \ub9e4\uc6b0 \ub3c4\uc804\uc801\uc778 \uc791\uc5c5\uc785\ub2c8\ub2e4. \uc774\ubc88 \uae00\uc5d0\uc11c\ub294 RL \uc5d0\uc774\uc804\ud2b8\uc758 \uc131\ub2a5 \ud3c9\uac00 \uc9c0\ud45c\uc640 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc124\uba85\ud558\uace0, \uc774\ub97c \ud1b5\ud574 \ub354 \ub098\uc740 \uc5d0\uc774\uc804\ud2b8\ub97c \uac1c\ubc1c\ud558\ub294 \ub370 \ub3c4\uc6c0\uc774 \ub418\uace0\uc790 \ud569\ub2c8\ub2e4. 1. RL \uc5d0\uc774\uc804\ud2b8 \uc131\ub2a5 … \ub354 \ubcf4\uae30 “43. RL \uc5d0\uc774\uc804\ud2b8 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45 \ubc29\ubc95, \uc5d0\uc774\uc804\ud2b8 \uc131\ub2a5 \ud3c9\uac00 \uc9c0\ud45c”<\/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-40448","post","type-post","status-publish","format-standard","hentry","category-213"],"yoast_head":"\n43. RL \uc5d0\uc774\uc804\ud2b8 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45 \ubc29\ubc95, \uc5d0\uc774\uc804\ud2b8 \uc131\ub2a5 \ud3c9\uac00 \uc9c0\ud45c - \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\/40448\/\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"43. RL \uc5d0\uc774\uc804\ud2b8 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45 \ubc29\ubc95, \uc5d0\uc774\uc804\ud2b8 \uc131\ub2a5 \ud3c9\uac00 \uc9c0\ud45c - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"og:description\" content=\"\uac15\ud654\ud559\uc2b5( Reinforcement Learning, RL) \ubd84\uc57c\uc5d0\uc11c\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uacfc \uc0c1\ud638 \uc791\uc6a9\ud558\uba70 \ucd5c\uc801\uc758 \ud589\ub3d9 \uc815\ucc45\uc744 \ud559\uc2b5\ud558\ub294 \uac83\uc774 \ud575\uc2ec\uc785\ub2c8\ub2e4. \uadf8\ub7ec\ub098 \uc774 \uacfc\uc815\uc5d0\uc11c \uc5d0\uc774\uc804\ud2b8\uc758 \uc131\ub2a5\uc744 \ud3c9\uac00\ud558\uace0 \ud6a8\uc728\uc801\uc73c\ub85c \ub514\ubc84\uae45\ud558\ub294 \uac83\uc740 \ub9e4\uc6b0 \ub3c4\uc804\uc801\uc778 \uc791\uc5c5\uc785\ub2c8\ub2e4. \uc774\ubc88 \uae00\uc5d0\uc11c\ub294 RL \uc5d0\uc774\uc804\ud2b8\uc758 \uc131\ub2a5 \ud3c9\uac00 \uc9c0\ud45c\uc640 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc124\uba85\ud558\uace0, \uc774\ub97c \ud1b5\ud574 \ub354 \ub098\uc740 \uc5d0\uc774\uc804\ud2b8\ub97c \uac1c\ubc1c\ud558\ub294 \ub370 \ub3c4\uc6c0\uc774 \ub418\uace0\uc790 \ud569\ub2c8\ub2e4. 1. RL \uc5d0\uc774\uc804\ud2b8 \uc131\ub2a5 … \ub354 \ubcf4\uae30 "43. RL \uc5d0\uc774\uc804\ud2b8 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45 \ubc29\ubc95, \uc5d0\uc774\uc804\ud2b8 \uc131\ub2a5 \ud3c9\uac00 \uc9c0\ud45c"\" \/>\n<meta property=\"og:url\" content=\"https:\/\/atmokpo.com\/w\/40448\/\" \/>\n<meta property=\"og:site_name\" content=\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"article:published_time\" content=\"2024-11-04T01:51:49+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-11-26T06:39:09+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\/40448\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/40448\/\"},\"author\":{\"name\":\"root\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\"},\"headline\":\"43. RL \uc5d0\uc774\uc804\ud2b8 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45 \ubc29\ubc95, \uc5d0\uc774\uc804\ud2b8 \uc131\ub2a5 \ud3c9\uac00 \uc9c0\ud45c\",\"datePublished\":\"2024-11-04T01:51:49+00:00\",\"dateModified\":\"2024-11-26T06:39:09+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/atmokpo.com\/w\/40448\/\"},\"wordCount\":28,\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"articleSection\":[\"\uac15\ud654\ud559\uc2b5\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/atmokpo.com\/w\/40448\/\",\"url\":\"https:\/\/atmokpo.com\/w\/40448\/\",\"name\":\"43. RL \uc5d0\uc774\uc804\ud2b8 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45 \ubc29\ubc95, \uc5d0\uc774\uc804\ud2b8 \uc131\ub2a5 \ud3c9\uac00 \uc9c0\ud45c - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#website\"},\"datePublished\":\"2024-11-04T01:51:49+00:00\",\"dateModified\":\"2024-11-26T06:39:09+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/atmokpo.com\/w\/40448\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/atmokpo.com\/w\/40448\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/atmokpo.com\/w\/40448\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\ud648\",\"item\":\"https:\/\/atmokpo.com\/w\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"43. RL \uc5d0\uc774\uc804\ud2b8 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45 \ubc29\ubc95, \uc5d0\uc774\uc804\ud2b8 \uc131\ub2a5 \ud3c9\uac00 \uc9c0\ud45c\"}]},{\"@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":"43. RL \uc5d0\uc774\uc804\ud2b8 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45 \ubc29\ubc95, \uc5d0\uc774\uc804\ud2b8 \uc131\ub2a5 \ud3c9\uac00 \uc9c0\ud45c - \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\/40448\/","og_locale":"ko_KR","og_type":"article","og_title":"43. RL \uc5d0\uc774\uc804\ud2b8 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45 \ubc29\ubc95, \uc5d0\uc774\uc804\ud2b8 \uc131\ub2a5 \ud3c9\uac00 \uc9c0\ud45c - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","og_description":"\uac15\ud654\ud559\uc2b5( Reinforcement Learning, RL) \ubd84\uc57c\uc5d0\uc11c\ub294 \uc5d0\uc774\uc804\ud2b8\uac00 \ud658\uacbd\uacfc \uc0c1\ud638 \uc791\uc6a9\ud558\uba70 \ucd5c\uc801\uc758 \ud589\ub3d9 \uc815\ucc45\uc744 \ud559\uc2b5\ud558\ub294 \uac83\uc774 \ud575\uc2ec\uc785\ub2c8\ub2e4. \uadf8\ub7ec\ub098 \uc774 \uacfc\uc815\uc5d0\uc11c \uc5d0\uc774\uc804\ud2b8\uc758 \uc131\ub2a5\uc744 \ud3c9\uac00\ud558\uace0 \ud6a8\uc728\uc801\uc73c\ub85c \ub514\ubc84\uae45\ud558\ub294 \uac83\uc740 \ub9e4\uc6b0 \ub3c4\uc804\uc801\uc778 \uc791\uc5c5\uc785\ub2c8\ub2e4. \uc774\ubc88 \uae00\uc5d0\uc11c\ub294 RL \uc5d0\uc774\uc804\ud2b8\uc758 \uc131\ub2a5 \ud3c9\uac00 \uc9c0\ud45c\uc640 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45 \ubc29\ubc95\uc5d0 \ub300\ud574 \uc790\uc138\ud788 \uc124\uba85\ud558\uace0, \uc774\ub97c \ud1b5\ud574 \ub354 \ub098\uc740 \uc5d0\uc774\uc804\ud2b8\ub97c \uac1c\ubc1c\ud558\ub294 \ub370 \ub3c4\uc6c0\uc774 \ub418\uace0\uc790 \ud569\ub2c8\ub2e4. 1. RL \uc5d0\uc774\uc804\ud2b8 \uc131\ub2a5 … \ub354 \ubcf4\uae30 \"43. RL \uc5d0\uc774\uc804\ud2b8 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45 \ubc29\ubc95, \uc5d0\uc774\uc804\ud2b8 \uc131\ub2a5 \ud3c9\uac00 \uc9c0\ud45c\"","og_url":"https:\/\/atmokpo.com\/w\/40448\/","og_site_name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","article_published_time":"2024-11-04T01:51:49+00:00","article_modified_time":"2024-11-26T06:39:09+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\/40448\/#article","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/40448\/"},"author":{"name":"root","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7"},"headline":"43. RL \uc5d0\uc774\uc804\ud2b8 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45 \ubc29\ubc95, \uc5d0\uc774\uc804\ud2b8 \uc131\ub2a5 \ud3c9\uac00 \uc9c0\ud45c","datePublished":"2024-11-04T01:51:49+00:00","dateModified":"2024-11-26T06:39:09+00:00","mainEntityOfPage":{"@id":"https:\/\/atmokpo.com\/w\/40448\/"},"wordCount":28,"publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"articleSection":["\uac15\ud654\ud559\uc2b5"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/atmokpo.com\/w\/40448\/","url":"https:\/\/atmokpo.com\/w\/40448\/","name":"43. RL \uc5d0\uc774\uc804\ud2b8 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45 \ubc29\ubc95, \uc5d0\uc774\uc804\ud2b8 \uc131\ub2a5 \ud3c9\uac00 \uc9c0\ud45c - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/#website"},"datePublished":"2024-11-04T01:51:49+00:00","dateModified":"2024-11-26T06:39:09+00:00","breadcrumb":{"@id":"https:\/\/atmokpo.com\/w\/40448\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/atmokpo.com\/w\/40448\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/atmokpo.com\/w\/40448\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\ud648","item":"https:\/\/atmokpo.com\/w\/en\/"},{"@type":"ListItem","position":2,"name":"43. RL \uc5d0\uc774\uc804\ud2b8 \ud3c9\uac00 \ubc0f \ub514\ubc84\uae45 \ubc29\ubc95, \uc5d0\uc774\uc804\ud2b8 \uc131\ub2a5 \ud3c9\uac00 \uc9c0\ud45c"}]},{"@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\/40448","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=40448"}],"version-history":[{"count":1,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/40448\/revisions"}],"predecessor-version":[{"id":40449,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/40448\/revisions\/40449"}],"wp:attachment":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/media?parent=40448"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/categories?post=40448"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/tags?post=40448"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}