{"id":227566,"date":"2025-12-20T21:11:02","date_gmt":"2025-12-21T03:11:02","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2025\/12\/nitrogen-a-foundation-model-for-generalist-gaming-agents"},"modified":"2025-12-20T21:11:02","modified_gmt":"2025-12-21T03:11:02","slug":"nitrogen-a-foundation-model-for-generalist-gaming-agents","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2025\/12\/nitrogen-a-foundation-model-for-generalist-gaming-agents","title":{"rendered":"NitroGen: A Foundation Model for Generalist Gaming Agents"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/nitrogen-a-foundation-model-for-generalist-gaming-agents.webp.jpg\"><\/a><\/p>\n<p>We introduce NitroGen, a vision-action foundation model for generalist gaming agents that is trained on 40,000 hours of gameplay videos across more than 1,000 games. We incorporate three key ingredients: 1) an internet-scale video-action dataset constructed by automatically extracting player actions from publicly available gameplay videos, 2) a multi-game benchmark environment that can measure cross-game generalization, and 3) a unified vision-action policy trained with large-scale behavior cloning. NitroGen exhibits strong competence across diverse domains, including combat encounters in 3D action games, high-precision control in 2D platformers, and exploration in procedurally generated worlds. It transfers effectively to unseen games, achieving up to 52% relative improvement in task success rates over models trained from scratch.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We introduce NitroGen, a vision-action foundation model for generalist gaming agents that is trained on 40,000 hours of gameplay videos across more than 1,000 games. We incorporate three key ingredients: 1) an internet-scale video-action dataset constructed by automatically extracting player actions from publicly available gameplay videos, 2) a multi-game benchmark environment that can measure cross-game [\u2026]<\/p>\n","protected":false},"author":709,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[11,1509,418,31],"tags":[],"class_list":["post-227566","post","type-post","status-publish","format-standard","hentry","category-biotech-medical","category-entertainment","category-internet","category-policy"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/227566","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/709"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=227566"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/227566\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=227566"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=227566"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=227566"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}