\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780 - \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\/29996\/\" \/>\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, \uac15\ud654 \ud559\uc2b5\uc774\ub780 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"og:description\" content=\"\uac15\ud654 \ud559\uc2b5(RL, Reinforcement Learning)\uc740 \uc778\uacf5\uc9c0\ub2a5 \ubd84\uc57c\uc5d0\uc11c \uc911\uc694\ud55c \ubd84\uc57c \uc911 \ud558\ub098\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 \ub370 \uc911\uc810\uc744 \ub461\ub2c8\ub2e4. \uc5d0\uc774\uc804\ud2b8\ub294 \ud2b9\uc815 \uc0c1\ud0dc\uc5d0\uc11c \ud589\ub3d9\uc744 \uc120\ud0dd\ud558\uace0, \uadf8 \ud589\ub3d9\uc5d0 \ub300\ud55c \ubcf4\uc0c1\uc744 \ubc1b\uc544 \uc774\ub97c \ud1b5\ud574 \ud559\uc2b5\uc744 \ud569\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \uac15\ud654 \ud559\uc2b5\uc758 \uae30\ubcf8 \uac1c\ub150, PyTorch\ub97c \uc774\uc6a9\ud55c \uad6c\ud604 \ubc29\ubc95, \uc608\uc81c \ucf54\ub4dc\ub97c \ud1b5\ud574 \uac15\ud654 \ud559\uc2b5\uc758 \uc791\ub3d9 \ubc29\uc2dd\uc744 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. \uac15\ud654 \ud559\uc2b5\uc758 \uae30\ubcf8 … \ub354 \ubcf4\uae30 "\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780"\" \/>\n<meta property=\"og:url\" content=\"https:\/\/atmokpo.com\/w\/29996\/\" \/>\n<meta property=\"og:site_name\" content=\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"article:published_time\" content=\"2024-10-28T03:19:03+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-11-26T06:50:29+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\/29996\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/29996\/\"},\"author\":{\"name\":\"root\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\"},\"headline\":\"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780\",\"datePublished\":\"2024-10-28T03:19:03+00:00\",\"dateModified\":\"2024-11-26T06:50:29+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/atmokpo.com\/w\/29996\/\"},\"wordCount\":56,\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"articleSection\":[\"\ud30c\uc774\ud1a0\uce58 \uac15\uc88c\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/atmokpo.com\/w\/29996\/\",\"url\":\"https:\/\/atmokpo.com\/w\/29996\/\",\"name\":\"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#website\"},\"datePublished\":\"2024-10-28T03:19:03+00:00\",\"dateModified\":\"2024-11-26T06:50:29+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/atmokpo.com\/w\/29996\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/atmokpo.com\/w\/29996\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/atmokpo.com\/w\/29996\/#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, \uac15\ud654 \ud559\uc2b5\uc774\ub780\"}]},{\"@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_head_json":{"title":"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780 - \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\/29996\/","og_locale":"ko_KR","og_type":"article","og_title":"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","og_description":"\uac15\ud654 \ud559\uc2b5(RL, Reinforcement Learning)\uc740 \uc778\uacf5\uc9c0\ub2a5 \ubd84\uc57c\uc5d0\uc11c \uc911\uc694\ud55c \ubd84\uc57c \uc911 \ud558\ub098\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 \ub370 \uc911\uc810\uc744 \ub461\ub2c8\ub2e4. \uc5d0\uc774\uc804\ud2b8\ub294 \ud2b9\uc815 \uc0c1\ud0dc\uc5d0\uc11c \ud589\ub3d9\uc744 \uc120\ud0dd\ud558\uace0, \uadf8 \ud589\ub3d9\uc5d0 \ub300\ud55c \ubcf4\uc0c1\uc744 \ubc1b\uc544 \uc774\ub97c \ud1b5\ud574 \ud559\uc2b5\uc744 \ud569\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \uac15\ud654 \ud559\uc2b5\uc758 \uae30\ubcf8 \uac1c\ub150, PyTorch\ub97c \uc774\uc6a9\ud55c \uad6c\ud604 \ubc29\ubc95, \uc608\uc81c \ucf54\ub4dc\ub97c \ud1b5\ud574 \uac15\ud654 \ud559\uc2b5\uc758 \uc791\ub3d9 \ubc29\uc2dd\uc744 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. \uac15\ud654 \ud559\uc2b5\uc758 \uae30\ubcf8 … \ub354 \ubcf4\uae30 \"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780\"","og_url":"https:\/\/atmokpo.com\/w\/29996\/","og_site_name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","article_published_time":"2024-10-28T03:19:03+00:00","article_modified_time":"2024-11-26T06:50:29+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\/29996\/#article","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/29996\/"},"author":{"name":"root","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7"},"headline":"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780","datePublished":"2024-10-28T03:19:03+00:00","dateModified":"2024-11-26T06:50:29+00:00","mainEntityOfPage":{"@id":"https:\/\/atmokpo.com\/w\/29996\/"},"wordCount":56,"publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"articleSection":["\ud30c\uc774\ud1a0\uce58 \uac15\uc88c"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/atmokpo.com\/w\/29996\/","url":"https:\/\/atmokpo.com\/w\/29996\/","name":"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/#website"},"datePublished":"2024-10-28T03:19:03+00:00","dateModified":"2024-11-26T06:50:29+00:00","breadcrumb":{"@id":"https:\/\/atmokpo.com\/w\/29996\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/atmokpo.com\/w\/29996\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/atmokpo.com\/w\/29996\/#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, \uac15\ud654 \ud559\uc2b5\uc774\ub780"}]},{"@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":40452,"url":"https:\/\/atmokpo.com\/w\/40452\/","url_meta":{"origin":29996,"position":0},"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":40514,"url":"https:\/\/atmokpo.com\/w\/40514\/","url_meta":{"origin":29996,"position":1},"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":40512,"url":"https:\/\/atmokpo.com\/w\/40512\/","url_meta":{"origin":29996,"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":""\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":29996,"position":3},"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":40460,"url":"https:\/\/atmokpo.com\/w\/40460\/","url_meta":{"origin":29996,"position":4},"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":""\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":29996,"position":5},"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":[]}],"_links":{"self":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/29996","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=29996"}],"version-history":[{"count":1,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/29996\/revisions"}],"predecessor-version":[{"id":29997,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/29996\/revisions\/29997"}],"wp:attachment":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/media?parent=29996"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/categories?post=29996"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/tags?post=29996"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}

{"id":29996,"date":"2024-10-28T03:19:03","date_gmt":"2024-10-28T03:19:03","guid":{"rendered":"http:\/\/atmokpo.com\/w\/?p=29996"},"modified":"2024-11-26T06:50:29","modified_gmt":"2024-11-26T06:50:29","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-%ea%b0%95%ed%99%94-%ed%95%99%ec%8a%b5%ec%9d%b4%eb%9e%80","status":"publish","type":"post","link":"https:\/\/atmokpo.com\/w\/29996\/","title":{"rendered":"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780"},"content":{"rendered":"

<\/p>\n

\uac15\ud654 \ud559\uc2b5(RL, Reinforcement Learning)\uc740 \uc778\uacf5\uc9c0\ub2a5 \ubd84\uc57c\uc5d0\uc11c \uc911\uc694\ud55c \ubd84\uc57c \uc911 \ud558\ub098\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 \ub370 \uc911\uc810\uc744 \ub461\ub2c8\ub2e4. \uc5d0\uc774\uc804\ud2b8\ub294 \ud2b9\uc815 \uc0c1\ud0dc\uc5d0\uc11c \ud589\ub3d9\uc744 \uc120\ud0dd\ud558\uace0, \uadf8 \ud589\ub3d9\uc5d0 \ub300\ud55c \ubcf4\uc0c1\uc744 \ubc1b\uc544 \uc774\ub97c \ud1b5\ud574 \ud559\uc2b5\uc744 \ud569\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \uac15\ud654 \ud559\uc2b5\uc758 \uae30\ubcf8 \uac1c\ub150, PyTorch\ub97c \uc774\uc6a9\ud55c \uad6c\ud604 \ubc29\ubc95, \uc608\uc81c \ucf54\ub4dc\ub97c \ud1b5\ud574 \uac15\ud654 \ud559\uc2b5\uc758 \uc791\ub3d9 \ubc29\uc2dd\uc744 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4.<\/p>\n

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

\uac15\ud654 \ud559\uc2b5\uc758 \ud575\uc2ec \uad6c\uc870\ub294 \ub2e4\uc74c\uacfc \uac19\uc774 \uc124\uba85\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4:<\/p>\n

\uc5d0\uc774\uc804\ud2b8(Agent)<\/strong>: \ud658\uacbd \ub0b4\uc5d0\uc11c \ud589\ub3d9\uc744 \ucde8\ud558\ub294 \uc8fc\uccb4\uc785\ub2c8\ub2e4.<\/li>\n
\ud658\uacbd(Environment)<\/strong>: \uc5d0\uc774\uc804\ud2b8\uc758 \ud589\ub3d9\uc5d0 \ub530\ub77c \ubcc0\ud654\ud558\ub294 \uc2dc\uc2a4\ud15c\uc774\ub098 \uc138\uacc4\uc785\ub2c8\ub2e4.<\/li>\n
\uc0c1\ud0dc(State)<\/strong>: \uc5d0\uc774\uc804\ud2b8\uac00 \ud604\uc7ac \ucc98\ud574 \uc788\ub294 \ud658\uacbd\uc758 \uc0c1\ud669\uc744 \ub098\ud0c0\ub0c5\ub2c8\ub2e4.<\/li>\n
\ud589\ub3d9(Action)<\/strong>: \uc5d0\uc774\uc804\ud2b8\uac00 \uc120\ud0dd\ud560 \uc218 \uc788\ub294 \ub2e4\uc591\ud55c \ud589\ub3d9\uc785\ub2c8\ub2e4.<\/li>\n
\ubcf4\uc0c1(Reward)<\/strong>: \uc5d0\uc774\uc804\ud2b8\uc758 \ud589\ub3d9\uc5d0 \ub300\ud574 \ud658\uacbd\uc774 \uc81c\uacf5\ud558\ub294 \ud53c\ub4dc\ubc31\uc785\ub2c8\ub2e4.<\/li>\n
\uc815\ucc45(Policy)<\/strong>: \uc5d0\uc774\uc804\ud2b8\uac00 \uc8fc\uc5b4\uc9c4 \uc0c1\ud0dc\uc5d0\uc11c \uc5b4\ub5a4 \ud589\ub3d9\uc744 \uc120\ud0dd\ud560\uc9c0 \uacb0\uc815\ud558\ub294 \uc804\ub7b5\uc785\ub2c8\ub2e4.<\/li>\n

\uac00\uce58 \ud568\uc218(Value Function)<\/strong>: \ud2b9\uc815 \uc0c1\ud0dc\uc5d0\uc11c\uc758 \uae30\ub300 \ubcf4\uc0c1\uc744 \ucd94\uc815\ud558\ub294 \ud568\uc218\uc785\ub2c8\ub2e4.<\/li>\n<\/ul>\n
2. \uac15\ud654 \ud559\uc2b5\uc758 \uacfc\uc815<\/h2>\n
\uac15\ud654 \ud559\uc2b5\uc758 \uae30\ubcf8 \uacfc\uc815\uc740 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4:<\/p>\n
\n
\uc5d0\uc774\uc804\ud2b8\ub294 \ucd08\uae30 \uc0c1\ud0dc\ub97c \uad00\ucc30\ud569\ub2c8\ub2e4.<\/li>\n
\uc815\ucc45\uc5d0 \ub530\ub77c \ud589\ub3d9\uc744 \uc120\ud0dd\ud569\ub2c8\ub2e4.<\/li>\n
\ud589\ub3d9\uc744 \ucde8\ud55c \ud6c4 \uc0c8\ub85c\uc6b4 \uc0c1\ud0dc\ub97c \uad00\ucc30\ud558\uace0 \ubcf4\uc0c1\uc744 \ubc1b\uc2b5\ub2c8\ub2e4.<\/li>\n
\ubcf4\uc0c1\uc744 \ubc14\ud0d5\uc73c\ub85c \uc815\ucc45\uc744 \uc5c5\ub370\uc774\ud2b8\ud569\ub2c8\ub2e4.<\/li>\n
\uc774 \uacfc\uc815\uc744 \ubc18\ubcf5\ud558\uc5ec \ucd5c\uc801\uc758 \uc815\ucc45\uc744 \ud559\uc2b5\ud569\ub2c8\ub2e4.<\/li>\n<\/ol>\n
3. \uac15\ud654 \ud559\uc2b5\uc758 \uc8fc\uc694 \uc54c\uace0\ub9ac\uc998<\/h2>\n
\uac15\ud654 \ud559\uc2b5\uc5d0\uc11c \uc0ac\uc6a9\ub418\ub294 \uc8fc\uc694 \uc54c\uace0\ub9ac\uc998\uc740 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4:<\/p>\n
\n
Q-learning<\/strong>: \uac00\uce58 \uae30\ubc18 \ud559\uc2b5 \ubc29\ubc95\uc73c\ub85c, \uc5d0\uc774\uc804\ud2b8\ub294 Q-\uac12\uc744 \uc5c5\ub370\uc774\ud2b8\ud558\uc5ec \ucd5c\uc801\uc758 \ud589\ub3d9\uc744 \ud559\uc2b5\ud569\ub2c8\ub2e4.<\/li>\n
\uc815\ucc45 \uacbd\ub7c9\ud654(Policy Gradient)<\/strong>: \uc815\ucc45\uc744 \uc9c1\uc811 \ud559\uc2b5\ud558\uba70, \ud655\ub960\uc801\uc778 \uc811\uadfc\ubc29\uc2dd\uc785\ub2c8\ub2e4.<\/li>\n
Actor-Critic<\/strong>: \uac00\uce58 \uae30\ubc18\uacfc \uc815\ucc45 \uae30\ubc18 \ubc29\ubc95\uc758 \uc870\ud569\uc73c\ub85c, \ub450 \uac00\uc9c0 \uc2e0\uacbd\ub9dd\uc744 \uc0ac\uc6a9\ud558\uc5ec \ud559\uc2b5\ud569\ub2c8\ub2e4.<\/li>\n<\/ul>\n
4. PyTorch\ub97c \uc774\uc6a9\ud55c \uac15\ud654 \ud559\uc2b5 \uad6c\ud604<\/h2>\n
\uc774\ubc88 \uc139\uc158\uc5d0\uc11c\ub294 PyTorch\ub97c \uc0ac\uc6a9\ud558\uc5ec \uac04\ub2e8\ud55c \uac15\ud654 \ud559\uc2b5 \uc608\uc81c\ub97c \uad6c\ud604\ud574 \ubcf4\uaca0\uc2b5\ub2c8\ub2e4. \uc544\ub798 \ucf54\ub4dc\ub294 OpenAI Gym\uc758 CartPole \ud658\uacbd\uc744 \uc0ac\uc6a9\ud558\uc5ec Q-learning \uc54c\uace0\ub9ac\uc998\uc744 \uad6c\ud604\ud55c \uc608\uc81c\uc785\ub2c8\ub2e4.<\/p>\n
4.1. \ud658\uacbd \uc124\uc815<\/h3>\n
\uba3c\uc800 \ud544\uc694\ud55c \ub77c\uc774\ube0c\ub7ec\ub9ac\ub97c \uc124\uce58\ud558\uace0, CartPole \ud658\uacbd\uc744 \uc124\uc815\ud569\ub2c8\ub2e4:<\/p>\n
!pip install gym torch numpy\nimport gym\nimport numpy as np<\/code><\/pre>\n4.2. Q-learning \uc54c\uace0\ub9ac\uc998 \uad6c\ud604<\/h3>\n\ub2e4\uc74c\uc73c\ub85c, Q-learning \uc54c\uace0\ub9ac\uc998\uc744 \uad6c\ud604\ud569\ub2c8\ub2e4. Q \ud14c\uc774\ube14\uc744 \uc0dd\uc131\ud558\uace0, \u03b5-greedy \uc815\ucc45\uc744 \uc0ac\uc6a9\ud558\uc5ec \ud559\uc2b5\ud569\ub2c8\ub2e4:<\/p>\n class QLearningAgent:\n def __init__(self, env):\n self.env = env\n self.q_table = np.zeros((env.observation_space.n, env.action_space.n))\n self.learning_rate = 0.1\n self.discount_factor = 0.95\n self.epsilon = 0.1\n\n def choose_action(self, state):\n if np.random.rand() < self.epsilon:\n return self.env.action_space.sample()\n else:\n return np.argmax(self.q_table[state])\n\n def learn(self, state, action, reward, next_state):\n best_next_action = np.argmax(self.q_table[next_state])\n td_target = reward + self.discount_factor * self.q_table[next_state][best_next_action]\n td_delta = td_target - self.q_table[state][action]\n self.q_table[state][action] += self.learning_rate * td_delta<\/code><\/pre>\n4.3. \ud559\uc2b5 \uacfc\uc815<\/h3>\n\uc774\uc81c \uc5d0\uc774\uc804\ud2b8\ub97c \ud559\uc2b5\uc2dc\ud0a4\ub294 \uba54\uc778 \ub8e8\ud504\ub97c \uc791\uc131\ud569\ub2c8\ub2e4:<\/p>\n env = gym.make('CartPole-v1')\nagent = QLearningAgent(env)\n\nepisodes = 1000\nfor episode in range(episodes):\n state = env.reset()\n done = False\n while not done:\n action = agent.choose_action(state)\n next_state, reward, done, _ = env.step(action)\n agent.learn(state, action, reward, next_state)\n state = next_state<\/code><\/pre>\n4.4. \ud559\uc2b5 \uacb0\uacfc \uc2dc\uac01\ud654<\/h3>\n\ud559\uc2b5\uc774 \uc644\ub8cc\ub41c \ud6c4, \uc5d0\uc774\uc804\ud2b8\uc758 \ud589\ub3d9\uc744 \uc2dc\uac01\ud654\ud558\uc5ec \uacb0\uacfc\ub97c \ud655\uc778\ud569\ub2c8\ub2e4:<\/p>\n total_reward = 0\nstate = env.reset()\ndone = False\nwhile not done:\n action = np.argmax(agent.q_table[state])\n state, reward, done, _ = env.step(action)\n total_reward += reward\n env.render()\n\nprint(f'Total Reward: {total_reward}')\nenv.close()<\/code><\/pre>\n5. \uacb0\ub860<\/h2>\n\uc774\ubc88 \uae00\uc5d0\uc11c\ub294 \uac15\ud654 \ud559\uc2b5\uc758 \uae30\ubcf8 \uac1c\ub150\uc744 \uc124\uba85\ud558\uace0, PyTorch\uc640 OpenAI Gym\uc744 \uc774\uc6a9\ud558\uc5ec \uac04\ub2e8\ud55c Q-learning \uc54c\uace0\ub9ac\uc998\uc744 \uad6c\ud604\ud574 \ubcf4\uc558\uc2b5\ub2c8\ub2e4. \uac15\ud654 \ud559\uc2b5\uc740 \ub2e4\uc591\ud55c \ubd84\uc57c\uc5d0 \uc801\uc6a9\ub420 \uc218 \uc788\ub294 \uac15\ub825\ud55c \uae30\uc220\uc774\uba70, \uc55e\uc73c\ub85c\ub3c4 \ub9ce\uc740 \ubc1c\uc804\uc774 \uae30\ub300\ub429\ub2c8\ub2e4. \ub2e4\uc74c \uae00\uc5d0\uc11c\ub294 \ub354\uc6b1 \uc2ec\ud654\ub41c \uc8fc\uc81c\ub97c \ub2e4\ub8e8\ub3c4\ub85d \ud558\uaca0\uc2b5\ub2c8\ub2e4.<\/p>\n 6. \ucc38\uace0 \uc790\ub8cc<\/h2>\n\nOpenAI Gym: https:\/\/gym.openai.com\/<\/a><\/li>\n PyTorch: https:\/\/pytorch.org\/<\/a><\/li>\n Reinforcement Learning: An Introduction (2nd Edition) by Richard S. Sutton and Andrew G. Barto<\/li>\n<\/ul>\n<\/body><\/p>\n","protected":false},"excerpt":{"rendered":"\uac15\ud654 \ud559\uc2b5(RL, Reinforcement Learning)\uc740 \uc778\uacf5\uc9c0\ub2a5 \ubd84\uc57c\uc5d0\uc11c \uc911\uc694\ud55c \ubd84\uc57c \uc911 \ud558\ub098\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 \ub370 \uc911\uc810\uc744 \ub461\ub2c8\ub2e4. \uc5d0\uc774\uc804\ud2b8\ub294 \ud2b9\uc815 \uc0c1\ud0dc\uc5d0\uc11c \ud589\ub3d9\uc744 \uc120\ud0dd\ud558\uace0, \uadf8 \ud589\ub3d9\uc5d0 \ub300\ud55c \ubcf4\uc0c1\uc744 \ubc1b\uc544 \uc774\ub97c \ud1b5\ud574 \ud559\uc2b5\uc744 \ud569\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \uac15\ud654 \ud559\uc2b5\uc758 \uae30\ubcf8 \uac1c\ub150, PyTorch\ub97c \uc774\uc6a9\ud55c \uad6c\ud604 \ubc29\ubc95, \uc608\uc81c \ucf54\ub4dc\ub97c \ud1b5\ud574 \uac15\ud654 \ud559\uc2b5\uc758 \uc791\ub3d9 \ubc29\uc2dd\uc744 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. \uac15\ud654 \ud559\uc2b5\uc758 \uae30\ubcf8 … \ub354 \ubcf4\uae30 “\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780”<\/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-29996","post","type-post","status-publish","format-standard","hentry","category-33"],"yoast_head":"\n\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780 - \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\/29996\/\" \/>\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, \uac15\ud654 \ud559\uc2b5\uc774\ub780 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"og:description\" content=\"\uac15\ud654 \ud559\uc2b5(RL, Reinforcement Learning)\uc740 \uc778\uacf5\uc9c0\ub2a5 \ubd84\uc57c\uc5d0\uc11c \uc911\uc694\ud55c \ubd84\uc57c \uc911 \ud558\ub098\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 \ub370 \uc911\uc810\uc744 \ub461\ub2c8\ub2e4. \uc5d0\uc774\uc804\ud2b8\ub294 \ud2b9\uc815 \uc0c1\ud0dc\uc5d0\uc11c \ud589\ub3d9\uc744 \uc120\ud0dd\ud558\uace0, \uadf8 \ud589\ub3d9\uc5d0 \ub300\ud55c \ubcf4\uc0c1\uc744 \ubc1b\uc544 \uc774\ub97c \ud1b5\ud574 \ud559\uc2b5\uc744 \ud569\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \uac15\ud654 \ud559\uc2b5\uc758 \uae30\ubcf8 \uac1c\ub150, PyTorch\ub97c \uc774\uc6a9\ud55c \uad6c\ud604 \ubc29\ubc95, \uc608\uc81c \ucf54\ub4dc\ub97c \ud1b5\ud574 \uac15\ud654 \ud559\uc2b5\uc758 \uc791\ub3d9 \ubc29\uc2dd\uc744 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. \uac15\ud654 \ud559\uc2b5\uc758 \uae30\ubcf8 … \ub354 \ubcf4\uae30 "\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780"\" \/>\n<meta property=\"og:url\" content=\"https:\/\/atmokpo.com\/w\/29996\/\" \/>\n<meta property=\"og:site_name\" content=\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"article:published_time\" content=\"2024-10-28T03:19:03+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-11-26T06:50:29+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\/29996\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/29996\/\"},\"author\":{\"name\":\"root\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\"},\"headline\":\"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780\",\"datePublished\":\"2024-10-28T03:19:03+00:00\",\"dateModified\":\"2024-11-26T06:50:29+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/atmokpo.com\/w\/29996\/\"},\"wordCount\":56,\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"articleSection\":[\"\ud30c\uc774\ud1a0\uce58 \uac15\uc88c\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/atmokpo.com\/w\/29996\/\",\"url\":\"https:\/\/atmokpo.com\/w\/29996\/\",\"name\":\"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#website\"},\"datePublished\":\"2024-10-28T03:19:03+00:00\",\"dateModified\":\"2024-11-26T06:50:29+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/atmokpo.com\/w\/29996\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/atmokpo.com\/w\/29996\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/atmokpo.com\/w\/29996\/#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, \uac15\ud654 \ud559\uc2b5\uc774\ub780\"}]},{\"@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_head_json":{"title":"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780 - \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\/29996\/","og_locale":"ko_KR","og_type":"article","og_title":"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","og_description":"\uac15\ud654 \ud559\uc2b5(RL, Reinforcement Learning)\uc740 \uc778\uacf5\uc9c0\ub2a5 \ubd84\uc57c\uc5d0\uc11c \uc911\uc694\ud55c \ubd84\uc57c \uc911 \ud558\ub098\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 \ub370 \uc911\uc810\uc744 \ub461\ub2c8\ub2e4. \uc5d0\uc774\uc804\ud2b8\ub294 \ud2b9\uc815 \uc0c1\ud0dc\uc5d0\uc11c \ud589\ub3d9\uc744 \uc120\ud0dd\ud558\uace0, \uadf8 \ud589\ub3d9\uc5d0 \ub300\ud55c \ubcf4\uc0c1\uc744 \ubc1b\uc544 \uc774\ub97c \ud1b5\ud574 \ud559\uc2b5\uc744 \ud569\ub2c8\ub2e4. \uc774 \uae00\uc5d0\uc11c\ub294 \uac15\ud654 \ud559\uc2b5\uc758 \uae30\ubcf8 \uac1c\ub150, PyTorch\ub97c \uc774\uc6a9\ud55c \uad6c\ud604 \ubc29\ubc95, \uc608\uc81c \ucf54\ub4dc\ub97c \ud1b5\ud574 \uac15\ud654 \ud559\uc2b5\uc758 \uc791\ub3d9 \ubc29\uc2dd\uc744 \uc54c\uc544\ubcf4\uaca0\uc2b5\ub2c8\ub2e4. 1. \uac15\ud654 \ud559\uc2b5\uc758 \uae30\ubcf8 … \ub354 \ubcf4\uae30 \"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780\"","og_url":"https:\/\/atmokpo.com\/w\/29996\/","og_site_name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","article_published_time":"2024-10-28T03:19:03+00:00","article_modified_time":"2024-11-26T06:50:29+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\/29996\/#article","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/29996\/"},"author":{"name":"root","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7"},"headline":"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780","datePublished":"2024-10-28T03:19:03+00:00","dateModified":"2024-11-26T06:50:29+00:00","mainEntityOfPage":{"@id":"https:\/\/atmokpo.com\/w\/29996\/"},"wordCount":56,"publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"articleSection":["\ud30c\uc774\ud1a0\uce58 \uac15\uc88c"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/atmokpo.com\/w\/29996\/","url":"https:\/\/atmokpo.com\/w\/29996\/","name":"\ub525\ub7ec\ub2dd \ud30c\uc774\ud1a0\uce58 \uac15\uc88c, \uac15\ud654 \ud559\uc2b5\uc774\ub780 - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/#website"},"datePublished":"2024-10-28T03:19:03+00:00","dateModified":"2024-11-26T06:50:29+00:00","breadcrumb":{"@id":"https:\/\/atmokpo.com\/w\/29996\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/atmokpo.com\/w\/29996\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/atmokpo.com\/w\/29996\/#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, \uac15\ud654 \ud559\uc2b5\uc774\ub780"}]},{"@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":40452,"url":"https:\/\/atmokpo.com\/w\/40452\/","url_meta":{"origin":29996,"position":0},"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":40514,"url":"https:\/\/atmokpo.com\/w\/40514\/","url_meta":{"origin":29996,"position":1},"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":40512,"url":"https:\/\/atmokpo.com\/w\/40512\/","url_meta":{"origin":29996,"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":""\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":29996,"position":3},"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":40460,"url":"https:\/\/atmokpo.com\/w\/40460\/","url_meta":{"origin":29996,"position":4},"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":""\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":29996,"position":5},"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":[]}],"_links":{"self":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/29996","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=29996"}],"version-history":[{"count":1,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/29996\/revisions"}],"predecessor-version":[{"id":29997,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/29996\/revisions\/29997"}],"wp:attachment":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/media?parent=29996"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/categories?post=29996"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/tags?post=29996"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}