{"id":132,"date":"2023-11-10T23:41:46","date_gmt":"2023-11-10T23:41:46","guid":{"rendered":"https:\/\/wp.lancs.ac.uk\/colab\/?p=132"},"modified":"2024-12-15T23:45:48","modified_gmt":"2024-12-15T23:45:48","slug":"scale-invariant-reinforcement-learning-in-real-time-strategy-games","status":"publish","type":"post","link":"https:\/\/wp.lancs.ac.uk\/colab\/2023\/11\/10\/scale-invariant-reinforcement-learning-in-real-time-strategy-games\/","title":{"rendered":"Scale-Invariant Reinforcement Learning in Real-Time Strategy Games"},"content":{"rendered":"<p><img loading=\"lazy\" decoding=\"async\" src=\"http:\/\/wp.lancs.ac.uk\/colab\/files\/2024\/12\/rtsDifferentMaps.png\" alt=\"\" width=\"787\" height=\"339\" class=\"aligncenter size-full wp-image-133\" srcset=\"https:\/\/wp.lancs.ac.uk\/colab\/files\/2024\/12\/rtsDifferentMaps.png 787w, https:\/\/wp.lancs.ac.uk\/colab\/files\/2024\/12\/rtsDifferentMaps-300x129.png 300w, https:\/\/wp.lancs.ac.uk\/colab\/files\/2024\/12\/rtsDifferentMaps-768x331.png 768w, https:\/\/wp.lancs.ac.uk\/colab\/files\/2024\/12\/rtsDifferentMaps-676x291.png 676w\" sizes=\"auto, (max-width: 787px) 100vw, 787px\" \/><\/p>\n<p>We presented in the Brazilian Symposium On Games and Digital Entertainment our work &#8220;Scale-Invariant Reinforcement Learning in Real-Time Strategy Games&#8221;. We integrate Spatial Pyramid Pooling (SPP) with Deep Reinforcement Learning, in order to allow a trained agent to play in maps of different dimensions in Real Time Strategy Games. The paper is <a href=\"https:\/\/www.research.lancs.ac.uk\/portal\/services\/downloadRegister\/398419068\/SBGames-final2023.pdf\">freely available<\/a>, including our <a href=\"https:\/\/github.com\/marcelo-lemos\/MicroRTS-Py\">source code<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We presented in the Brazilian Symposium On Games and Digital Entertainment our work &#8220;Scale-Invariant Reinforcement Learning in Real-Time Strategy Games&#8221;. We integrate Spatial Pyramid Pooling (SPP) with Deep Reinforcement Learning, in order to allow a trained agent to play in maps of different dimensions in Real Time Strategy Games. The paper is freely available, including [&hellip;]<\/p>\n","protected":false},"author":1432,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[3],"tags":[],"class_list":["post-132","post","type-post","status-publish","format-standard","hentry","category-news"],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/posts\/132","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/users\/1432"}],"replies":[{"embeddable":true,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/comments?post=132"}],"version-history":[{"count":1,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/posts\/132\/revisions"}],"predecessor-version":[{"id":134,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/posts\/132\/revisions\/134"}],"wp:attachment":[{"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/media?parent=132"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/categories?post=132"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/tags?post=132"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}