{"id":11187,"date":"2024-04-02T16:26:13","date_gmt":"2024-04-02T16:26:13","guid":{"rendered":"https:\/\/dailyai.com\/?p=11187"},"modified":"2024-04-04T05:59:53","modified_gmt":"2024-04-04T05:59:53","slug":"deepmind-develop-a-foundation-model-for-building-2d-game-environments","status":"publish","type":"post","link":"https:\/\/dailyai.com\/fr\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/","title":{"rendered":"DeepMind d\u00e9veloppe un mod\u00e8le de base pour la construction d'environnements de jeux en 2D"},"content":{"rendered":"

Genie de Google DeepMind est un mod\u00e8le g\u00e9n\u00e9ratif qui traduit de simples images ou des invites textuelles en mondes dynamiques et interactifs.\u00a0<\/b><\/p>\n

Genie a \u00e9t\u00e9 entra\u00een\u00e9 sur un vaste ensemble de donn\u00e9es comprenant plus de 200 000 heures de s\u00e9quences vid\u00e9o de jeux, y compris des jeux de plateformes en 2D et des interactions robotiques dans le monde r\u00e9el.\u00a0<\/span><\/p>\n

Ce vaste ensemble de donn\u00e9es a permis \u00e0 Genie de comprendre et de g\u00e9n\u00e9rer la physique, la dynamique et l'esth\u00e9tique de nombreux environnements et objets.<\/span><\/p>\n

Le mod\u00e8le finalis\u00e9, document\u00e9 dans un <\/span>document de recherche<\/span><\/a>contient 11 milliards de param\u00e8tres permettant de g\u00e9n\u00e9rer des mondes virtuels interactifs \u00e0 partir d'images de formats multiples ou d'invites textuelles.\u00a0<\/span><\/p>\n

Ainsi, vous pouvez envoyer \u00e0 Genie une image de votre salon ou de votre jardin et la transformer en un niveau de plate-forme 2D jouable.<\/p>\n

Ou encore griffonner un environnement 2D sur une feuille de papier et le convertir en un environnement de jeu jouable.<\/p>\n

\"DeepMind
Genie peut fonctionner comme un environnement interactif, acceptant diverses invites telles que des images g\u00e9n\u00e9r\u00e9es ou des croquis dessin\u00e9s \u00e0 la main. Les utilisateurs peuvent guider les r\u00e9sultats du mod\u00e8le en fournissant des actions latentes \u00e0 chaque pas de temps, que Genie utilise ensuite pour g\u00e9n\u00e9rer l'image suivante de la s\u00e9quence \u00e0 1 FPS. Source : DeepMind via ArXiv : DeepMind via ArXiv (acc\u00e8s libre).<\/figcaption><\/figure>\n

Ce qui distingue Genie des autres mod\u00e8les de monde, c'est sa capacit\u00e9 \u00e0 permettre aux utilisateurs d'interagir avec les environnements g\u00e9n\u00e9r\u00e9s, image par image.<\/span><\/p>\n

Par exemple, vous pouvez voir ci-dessous comment Genie prend des photos d'environnements r\u00e9els et les transforme en niveaux de jeu en 2D.<\/p>\n

\"DeepMind
Genie peut cr\u00e9er des niveaux de jeu \u00e0 partir a) d'autres niveaux de jeu, b) d'esquisses dessin\u00e9es \u00e0 la main et c) de photographies d'environnements r\u00e9els. Voir les niveaux de jeu (rang\u00e9e du bas) g\u00e9n\u00e9r\u00e9s \u00e0 partir d'images du monde r\u00e9el (rang\u00e9e du haut). Source : DeepMind : DeepMind.<\/figcaption><\/figure>\n

Comment fonctionne Genie<\/h2>\n

Genie est un \"mod\u00e8le de monde de base\" compos\u00e9 de trois \u00e9l\u00e9ments cl\u00e9s : un tokenizer vid\u00e9o spatio-temporel, un mod\u00e8le dynamique autor\u00e9gressif et un mod\u00e8le d'action latente (LAM) simple et \u00e9volutif.<\/span><\/p>\n

Voici comment cela fonctionne :<\/span><\/p>\n

    \n
  1. Transformateurs spatio-temporels<\/b>: Les transformateurs spatiotemporels (ST), qui traitent des s\u00e9quences d'images vid\u00e9o, sont au c\u0153ur de Genie. Contrairement aux transformateurs traditionnels qui traitent du texte ou des images statiques, les transformateurs ST sont con\u00e7us pour comprendre la progression des donn\u00e9es visuelles dans le temps, ce qui les rend id\u00e9aux pour la g\u00e9n\u00e9ration de vid\u00e9os et d'environnements dynamiques.<\/span><\/li>\n
  2. Mod\u00e8le d'action latente (LAM)<\/b>: Genie comprend et pr\u00e9dit les actions dans les mondes qu'il g\u00e9n\u00e8re gr\u00e2ce au LAM. Il d\u00e9duit les actions potentielles qui pourraient se produire entre les images d'une vid\u00e9o, en apprenant un ensemble d'\"actions latentes\" directement \u00e0 partir des donn\u00e9es visuelles. Cela permet \u00e0 Genie de contr\u00f4ler la progression des \u00e9v\u00e9nements dans les environnements interactifs, malgr\u00e9 l'absence d'\u00e9tiquettes d'action explicites dans les donn\u00e9es d'apprentissage.<\/span><\/li>\n
  3. Mod\u00e8le d'encodage et de dynamique de la vid\u00e9o<\/b>: Pour g\u00e9rer les donn\u00e9es vid\u00e9o, Genie fait appel \u00e0 un syst\u00e8me de codage vid\u00e9o qui compresse les images vid\u00e9o brutes dans un format plus facile \u00e0 g\u00e9rer de jetons discrets. Apr\u00e8s la compression, le mod\u00e8le dynamique pr\u00e9dit l'ensemble suivant de jetons d'images, g\u00e9n\u00e9rant ainsi les images suivantes dans l'environnement interactif.<\/span><\/li>\n<\/ol>\n

    L'\u00e9quipe DeepMind explique que \"Genie pourrait permettre \u00e0 un grand nombre de personnes de g\u00e9n\u00e9rer leurs propres exp\u00e9riences de jeu.<\/span> Cela pourrait \u00eatre positif pour ceux qui souhaitent exprimer leur cr\u00e9ativit\u00e9 d'une nouvelle mani\u00e8re, par exemple les enfants qui pourraient concevoir et p\u00e9n\u00e9trer dans leurs propres mondes imaginaires\".<\/span><\/p>\n

    Dans une exp\u00e9rience parall\u00e8le, lorsqu'on lui a pr\u00e9sent\u00e9 des vid\u00e9os de vrais bras de robots s'engageant dans des objets r\u00e9els, Genie a fait preuve d'une capacit\u00e9 \u00e9tonnante \u00e0 d\u00e9chiffrer les actions que ces bras pouvaient effectuer. Cela d\u00e9montre les possibilit\u00e9s d'utilisation dans le domaine de la recherche en robotique.\u00a0<\/span><\/p>\n

    Tim Rockt\u00e4schel, de l'\u00e9quipe Genie, a d\u00e9crit le potentiel illimit\u00e9 de Genie : \"Il est difficile de pr\u00e9dire quels cas d'utilisation seront possibles. <\/span>Nous esp\u00e9rons que des projets comme Genie offriront aux gens de nouveaux outils pour exprimer leur cr\u00e9ativit\u00e9\".\u00a0<\/span><\/p>\n

    DeepMind \u00e9tait conscient des risques li\u00e9s \u00e0 la publication de ce mod\u00e8le de base et a d\u00e9clar\u00e9 dans l'article : \"Nous avons choisi de ne pas publier les points de contr\u00f4le du mod\u00e8le entra\u00een\u00e9, l'ensemble de donn\u00e9es d'entra\u00eenement du mod\u00e8le ou des exemples tir\u00e9s de ces donn\u00e9es pour accompagner cet article ou le site web\".<\/p>\n

    \"Nous aimerions avoir l'occasion de nous engager plus avant avec la communaut\u00e9 de la recherche (et des jeux vid\u00e9o) et de veiller \u00e0 ce que toute diffusion future de ce type soit respectueuse, s\u00fbre et responsable\".<\/p>\n

    Utiliser des jeux pour simuler des applications du monde r\u00e9el<\/h2>\n

    DeepMind a utilis\u00e9 des jeux vid\u00e9o pour plusieurs projets d'apprentissage automatique.\u00a0<\/span><\/p>\n

    Par exemple, en 2021, DeepMind a construit XLand<\/a>Le projet de recherche sur l'apprentissage par renforcement, un terrain de jeu virtuel permettant de tester les approches d'apprentissage par renforcement pour les agents d'intelligence artificielle g\u00e9n\u00e9ralistes, a \u00e9t\u00e9 lanc\u00e9. Ici, les mod\u00e8les d'IA ma\u00eetrisent la coop\u00e9ration et la r\u00e9solution de probl\u00e8mes en effectuant des t\u00e2ches telles que le d\u00e9placement d'obstacles dans des environnements de jeu ouverts.\u00a0<\/span><\/p>\n

    Puis, le mois dernier, LMSI<\/a> (Scalable, Instructable, Multiworld Agent) a \u00e9t\u00e9 con\u00e7u pour comprendre et ex\u00e9cuter des instructions en langage humain dans diff\u00e9rents jeux et sc\u00e9narios.\u00a0<\/span><\/p>\n

    SIMA a \u00e9t\u00e9 form\u00e9 \u00e0 l'aide de neuf jeux vid\u00e9o n\u00e9cessitant diff\u00e9rentes comp\u00e9tences, de la navigation de base au pilotage de v\u00e9hicules.\u00a0<\/span><\/p>\n

    Les environnements de jeu offrent un bac \u00e0 sable contr\u00f4lable et \u00e9volutif pour l'entra\u00eenement et le test des mod\u00e8les d'IA.<\/p>\n

    L'expertise de DeepMind en mati\u00e8re de jeux remonte \u00e0 2014-2015, lorsqu'elle a mis au point un algorithme capable de vaincre les humains dans des jeux tels que Pong et Space Invaders, sans parler d'AlphaGo, qui a battu le joueur professionnel Fan Hui sur un plateau de 19\u00d719 grandeur nature.<\/p>","protected":false},"excerpt":{"rendered":"

    Genie de Google DeepMind est un mod\u00e8le g\u00e9n\u00e9ratif qui traduit de simples images ou des invites textuelles en mondes dynamiques et interactifs. Genie a \u00e9t\u00e9 entra\u00een\u00e9 sur un vaste ensemble de donn\u00e9es comprenant plus de 200 000 heures de s\u00e9quences vid\u00e9o de jeux, y compris des jeux de plateformes en 2D et des interactions robotiques r\u00e9elles. Ce vaste ensemble de donn\u00e9es a permis \u00e0 Genie de comprendre et de g\u00e9n\u00e9rer la physique, la dynamique et l'esth\u00e9tique de nombreux environnements et objets. Le mod\u00e8le finalis\u00e9, document\u00e9 dans un rapport de recherche, contient 11 milliards de param\u00e8tres permettant de g\u00e9n\u00e9rer des mondes virtuels interactifs \u00e0 partir d'images de diff\u00e9rents formats ou d'invites textuelles. Ainsi, vous pouvez donner \u00e0 Genie une image de votre salon ou de votre jardin<\/p>","protected":false},"author":2,"featured_media":11190,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[147,169],"class_list":["post-11187","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-deepmind","tag-robotics"],"yoast_head":"\nDeepMind develop a foundation model for building 2D game environments | DailyAI<\/title>\n<meta name=\"description\" content=\"Google DeepMind's Genie is a generative model that translates simple images or text prompts into dynamic, interactive worlds.\u00a0\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dailyai.com\/fr\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"DeepMind develop a foundation model for building 2D game environments | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Google DeepMind's Genie is a generative model that translates simple images or text prompts into dynamic, interactive worlds.\u00a0\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/fr\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-04-02T16:26:13+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-04T05:59:53+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-02-17.23.22-Imagine-a-vivid-scene-from-a-2D-platform-game-simple-yet-engaging.-The-game-environment-includes-a-series-of-platforms-each-varying-in-height-and-di.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1792\" \/>\n\t<meta property=\"og:image:height\" content=\"1024\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Sam Jeans\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:site\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:label1\" content=\"\u00c9crit par\" \/>\n\t<meta name=\"twitter:data1\" content=\"Sam Jeans\" \/>\n\t<meta name=\"twitter:label2\" content=\"Dur\u00e9e de lecture estim\u00e9e\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\\\/\"},\"author\":{\"name\":\"Sam Jeans\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\"},\"headline\":\"DeepMind develop a foundation model for building 2D game environments\",\"datePublished\":\"2024-04-02T16:26:13+00:00\",\"dateModified\":\"2024-04-04T05:59:53+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\\\/\"},\"wordCount\":806,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DALL\u00b7E-2024-04-02-17.23.22-Imagine-a-vivid-scene-from-a-2D-platform-game-simple-yet-engaging.-The-game-environment-includes-a-series-of-platforms-each-varying-in-height-and-di.webp\",\"keywords\":[\"DeepMind\",\"Robotics\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"fr-FR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\\\/\",\"name\":\"DeepMind develop a foundation model for building 2D game environments | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DALL\u00b7E-2024-04-02-17.23.22-Imagine-a-vivid-scene-from-a-2D-platform-game-simple-yet-engaging.-The-game-environment-includes-a-series-of-platforms-each-varying-in-height-and-di.webp\",\"datePublished\":\"2024-04-02T16:26:13+00:00\",\"dateModified\":\"2024-04-04T05:59:53+00:00\",\"description\":\"Google DeepMind's Genie is a generative model that translates simple images or text prompts into dynamic, interactive worlds.\u00a0\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\\\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DALL\u00b7E-2024-04-02-17.23.22-Imagine-a-vivid-scene-from-a-2D-platform-game-simple-yet-engaging.-The-game-environment-includes-a-series-of-platforms-each-varying-in-height-and-di.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/DALL\u00b7E-2024-04-02-17.23.22-Imagine-a-vivid-scene-from-a-2D-platform-game-simple-yet-engaging.-The-game-environment-includes-a-series-of-platforms-each-varying-in-height-and-di.webp\",\"width\":1792,\"height\":1024,\"caption\":\"AI game\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/04\\\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"DeepMind develop a foundation model for building 2D game environments\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"name\":\"DailyAI\",\"description\":\"Your Daily Dose of AI News\",\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/dailyai.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"fr-FR\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"width\":4501,\"height\":934,\"caption\":\"DailyAI\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/DailyAIOfficial\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/dailyaiofficial\\\/\",\"https:\\\/\\\/www.youtube.com\\\/@DailyAIOfficial\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\",\"name\":\"Sam Jeans\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"caption\":\"Sam Jeans\"},\"description\":\"Sam is a science and technology writer who has worked in various AI startups. When he\u2019s not writing, he can be found reading medical journals or digging through boxes of vinyl records.\",\"sameAs\":[\"https:\\\/\\\/www.linkedin.com\\\/in\\\/sam-jeans-6746b9142\\\/\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/fr\\\/author\\\/samjeans\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"DeepMind d\u00e9veloppe un mod\u00e8le de base pour la construction d'environnements de jeux en 2D | DailyAI","description":"Genie de Google DeepMind est un mod\u00e8le g\u00e9n\u00e9ratif qui traduit de simples images ou des invites textuelles en mondes dynamiques et interactifs.\u00a0","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:\/\/dailyai.com\/fr\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/","og_locale":"fr_FR","og_type":"article","og_title":"DeepMind develop a foundation model for building 2D game environments | DailyAI","og_description":"Google DeepMind's Genie is a generative model that translates simple images or text prompts into dynamic, interactive worlds.\u00a0","og_url":"https:\/\/dailyai.com\/fr\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/","og_site_name":"DailyAI","article_published_time":"2024-04-02T16:26:13+00:00","article_modified_time":"2024-04-04T05:59:53+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-02-17.23.22-Imagine-a-vivid-scene-from-a-2D-platform-game-simple-yet-engaging.-The-game-environment-includes-a-series-of-platforms-each-varying-in-height-and-di.webp","type":"image\/webp"}],"author":"Sam Jeans","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"\u00c9crit par":"Sam Jeans","Dur\u00e9e de lecture estim\u00e9e":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/"},"author":{"name":"Sam Jeans","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9"},"headline":"DeepMind develop a foundation model for building 2D game environments","datePublished":"2024-04-02T16:26:13+00:00","dateModified":"2024-04-04T05:59:53+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/"},"wordCount":806,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-02-17.23.22-Imagine-a-vivid-scene-from-a-2D-platform-game-simple-yet-engaging.-The-game-environment-includes-a-series-of-platforms-each-varying-in-height-and-di.webp","keywords":["DeepMind","Robotics"],"articleSection":["Industry"],"inLanguage":"fr-FR"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/","url":"https:\/\/dailyai.com\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/","name":"DeepMind d\u00e9veloppe un mod\u00e8le de base pour la construction d'environnements de jeux en 2D | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-02-17.23.22-Imagine-a-vivid-scene-from-a-2D-platform-game-simple-yet-engaging.-The-game-environment-includes-a-series-of-platforms-each-varying-in-height-and-di.webp","datePublished":"2024-04-02T16:26:13+00:00","dateModified":"2024-04-04T05:59:53+00:00","description":"Genie de Google DeepMind est un mod\u00e8le g\u00e9n\u00e9ratif qui traduit de simples images ou des invites textuelles en mondes dynamiques et interactifs.\u00a0","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-02-17.23.22-Imagine-a-vivid-scene-from-a-2D-platform-game-simple-yet-engaging.-The-game-environment-includes-a-series-of-platforms-each-varying-in-height-and-di.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/04\/DALL\u00b7E-2024-04-02-17.23.22-Imagine-a-vivid-scene-from-a-2D-platform-game-simple-yet-engaging.-The-game-environment-includes-a-series-of-platforms-each-varying-in-height-and-di.webp","width":1792,"height":1024,"caption":"AI game"},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/04\/deepmind-develop-a-foundation-model-for-building-2d-game-environments\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"DeepMind develop a foundation model for building 2D game environments"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"Votre dose quotidienne de nouvelles sur l'IA","publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dailyai.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"fr-FR"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","width":4501,"height":934,"caption":"DailyAI"},"image":{"@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/DailyAIOfficial","https:\/\/www.linkedin.com\/company\/dailyaiofficial\/","https:\/\/www.youtube.com\/@DailyAIOfficial"]},{"@type":"Person","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9","name":"Sam Jeans","image":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","caption":"Sam Jeans"},"description":"Sam est un r\u00e9dacteur scientifique et technologique qui a travaill\u00e9 dans diverses start-ups sp\u00e9cialis\u00e9es dans l'IA. Lorsqu'il n'\u00e9crit pas, on peut le trouver en train de lire des revues m\u00e9dicales ou de fouiller dans des bo\u00eetes de disques vinyles.","sameAs":["https:\/\/www.linkedin.com\/in\/sam-jeans-6746b9142\/"],"url":"https:\/\/dailyai.com\/fr\/author\/samjeans\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/11187","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/comments?post=11187"}],"version-history":[{"count":11,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/11187\/revisions"}],"predecessor-version":[{"id":11245,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/11187\/revisions\/11245"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/media\/11190"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/media?parent=11187"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/categories?post=11187"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/tags?post=11187"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}