{"id":235753,"date":"2016-06-01T09:39:38","date_gmt":"2016-06-01T16:39:38","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&#038;p=235753"},"modified":"2025-04-03T11:34:20","modified_gmt":"2025-04-03T18:34:20","slug":"project-malmo","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/project-malmo\/","title":{"rendered":"Project Malmo"},"content":{"rendered":"<section class=\"mb-3 moray-highlight\">\n\t<div class=\"card-img-overlay mx-lg-0\">\n\t\t<div class=\"card-background  has-background- card-background--full-bleed\">\n\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"1920\" height=\"577\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/Project_Malmo_1920x577.jpg\" class=\"attachment-full size-full\" alt=\"Project Malmo\" style=\"\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/Project_Malmo_1920x577.jpg 1920w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/Project_Malmo_1920x577-300x90.jpg 300w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/Project_Malmo_1920x577-768x231.jpg 768w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/Project_Malmo_1920x577-1024x308.jpg 1024w\" sizes=\"auto, (max-width: 1920px) 100vw, 1920px\" \/>\t\t<\/div>\n\t\t<!-- Foreground -->\n\t\t<div class=\"card-foreground d-flex mt-md-n5 my-lg-5 px-g px-lg-0\">\n\t\t\t<!-- Container -->\n\t\t\t<div class=\"container d-flex mt-md-n5 my-lg-5 \">\n\t\t\t\t<!-- Card wrapper -->\n\t\t\t\t<div class=\"w-100 w-lg-col-5\">\n\t\t\t\t\t<!-- Card -->\n\t\t\t\t\t<div class=\"card material-md-card py-5 px-md-5\">\n\t\t\t\t\t\t<div class=\"card-body \">\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n<h1 class=\"wp-block-heading h2\" id=\"project-malmo\">Project Malmo<\/h1>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n<p>How can we develop artificial intelligence that learns to make sense of complex environments? That learns from others, including humans, how to interact with the world? That learns transferable skills throughout its existence, and applies them to solve new, challenging problems?<\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"Project Malmo \u2013 Enabling AI technology that can collaborate with humans\" width=\"500\" height=\"281\" src=\"https:\/\/www.youtube-nocookie.com\/embed\/KkVj_ddseO8?feature=oembed&rel=0\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<div class=\"wp-block-buttons is-content-justification-center is-content-justification-center is-layout-flex wp-container-core-buttons-is-layout-1 wp-block-buttons-is-layout-flex\">\n<div class=\"wp-block-button\"><a data-bi-type=\"button\" class=\"wp-block-button__link wp-element-button\" href=\"https:\/\/github.com\/Microsoft\/malmo#getting-started\" target=\"_blank\" rel=\"noreferrer noopener\">Try it<\/a><\/div>\n<\/div>\n\n\n\n<p>Project Malmo sets out to address these core research challenges, addressing them by integrating (deep) reinforcement learning, cognitive science, and many ideas from artificial intelligence.<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter\"><img loading=\"lazy\" decoding=\"async\" width=\"800\" height=\"247\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/malmo_human_ai_interaction-web.png\" alt=\"Project malmo\" class=\"wp-image-235757\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/malmo_human_ai_interaction-web.png 800w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/malmo_human_ai_interaction-web-300x93.png 300w, https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/malmo_human_ai_interaction-web-768x237.png 768w\" sizes=\"auto, (max-width: 800px) 100vw, 800px\" \/><\/figure>\n\n\n\n<div style=\"height:20px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p>The Malmo platform is a sophisticated AI experimentation platform built on top of Minecraft, and designed to support fundamental research in artificial intelligence.<\/p>\n\n\n\n<p>The Project Malmo platform consists of a mod for the Java version, and code that helps artificial intelligence agents sense and act within the Minecraft environment. The two components can run on Windows, Linux, or Mac OS, and researchers can program their agents in any programming language they\u2019re comfortable with.<\/p>\n\n\n\n<p>Minecraft is ideal for artificial intelligence research for the same reason it is addictively appealing to the millions of fans who enter its virtual world every day. Unlike other computer games, Minecraft offers its users endless possibilities, ranging from simple tasks, like walking around looking for treasure, to complex ones, like building a structure with a group of teammates.<\/p>\n\n\n\n<div class=\"wp-block-buttons is-layout-flex wp-block-buttons-is-layout-flex\">\n<div class=\"wp-block-button is-style-outline is-style-outline--1\"><a data-bi-type=\"button\" class=\"wp-block-button__link wp-element-button\" href=\"http:\/\/blogs.microsoft.com\/next\/2016\/03\/13\/project-malmo-using-minecraft-build-intelligent-technology\/#sm.0001674urakf1fo4w8n13a4hwd1ae\" target=\"_blank\" rel=\"noreferrer noopener\">Project Malmo using Minecraft to build intelligent technology<\/a><\/div>\n\n\n\n<div class=\"wp-block-button is-style-outline is-style-outline--2\"><a data-bi-type=\"button\" class=\"wp-block-button__link wp-element-button\" href=\"http:\/\/blogs.microsoft.com\/next\/2016\/07\/07\/project-malmo-lets-researchers-use-minecraft-ai-research-makes-public-debut\/\" target=\"_blank\" rel=\"noreferrer noopener\">Read about our open-source release<\/a><\/div>\n<\/div>\n\n\n\n<p>Are you interested in accelerating the path of innovation in AI? Then make the Malmo platform your choice.<\/p>\n\n\n\n<div class=\"wp-block-buttons is-layout-flex wp-block-buttons-is-layout-flex\">\n<div class=\"wp-block-button is-style-fill\"><a data-bi-type=\"button\" class=\"wp-block-button__link wp-element-button\" href=\"https:\/\/gitter.im\/Microsoft\/malmo\" target=\"_blank\" rel=\"noreferrer noopener\">Join the community<\/a><\/div>\n\n\n\n<div class=\"wp-block-button is-style-fill\"><a data-bi-type=\"button\" class=\"wp-block-button__link wp-element-button\" href=\"https:\/\/x.com\/Project_Malmo\" target=\"_blank\" rel=\"noreferrer noopener\">Follow @Project_Malmo<\/a><\/div>\n<\/div>\n\n\n\n\n\n<h2 class=\"wp-block-heading\" id=\"competitions\">Competitions<\/h2>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"minerl-competition-2020\"><a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/minerl.io\/competition\/\">MineRL Competition 2020<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/h3>\n\n\n\n<p>Round 1 of the MineRL NeurIPS 2020 Competition is now open for submissions! The competition is on sample-efficient reinforcement learning using human priors.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"minerl-competition-2019\"><a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/www.aicrowd.com\/challenges\/neurips-2019-minerl-competition\">MineRL Competition 2019<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/h3>\n\n\n\n<p>Starting June 1st, we are holding a competition on sample-efficient reinforcement learning using human priors. In our competition, participants develop a system to obtain a diamond in Minecraft using only four days of training time.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"multi-agent-reinforcement-learning-in-malmo-marlo-competition-2018\"><a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/www.crowdai.org\/challenges\/marlo-2018\">Multi-Agent Reinforcement Learning in Malmo (MARLO) Competition 2018<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/h3>\n\n\n\n<p>The second round of competition was to create learning agents that can play multiple 3D games as de\ufb01ned in the Malmo platform.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"malmo-collaborative-ai-challenge-2017\"><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/academic-program\/collaborative-ai-challenge\/\">Malmo Collaborative AI Challenge 2017<\/a><\/h3>\n\n\n\n<p>The first round of the Malmo Collaborative AI Challenge was to develop and train collaborative AI solutions that learn to achieve high scores across a range of partners.<\/p>\n\n\n\n<div style=\"height:35px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n","protected":false},"excerpt":{"rendered":"<p>The Malmo platform is a sophisticated AI experimentation platform built on top of Minecraft, and designed to support fundamental research in artificial intelligence.<\/p>\n","protected":false},"featured_media":238697,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13556],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-235753","msr-project","type-msr-project","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-archive-status-complete"],"msr_project_start":"","related-publications":[589015,589030,565707,565749,451050,387338,389849,565719,565725,294140,237369,728677,636378,636369,630174,630114,630108,630102,624714],"related-downloads":[253184,496286],"related-videos":[377012,402197,426339,264774,277419,272220,422160,596335,616626,685281,734470,748969],"related-groups":[395930,583324],"related-events":[721873,602214,428574,350765,229852],"related-opportunities":[],"related-posts":[367736,388346,432156,497597,551052,568788,602541,502847,621516,622608,685122,709156,712588,720673],"related-articles":[],"tab-content":[{"id":0,"name":"Competitions","content":"[row]\r\n[card title=\"MineRL Competition 2020\" url=\"https:\/\/minerl.io\/competition\/\" ]Round 1 of the MineRL NeurIPS 2020 Competition is now open for submissions! The competition is on sample-efficient reinforcement learning using human priors.[\/card]\r\n\r\n[card title=\"MineRL Competition 2019\" url=\"https:\/\/www.aicrowd.com\/challenges\/neurips-2019-minerl-competition\" ]Starting June 1st, we are holding a competition on sample-efficient reinforcement learning using human priors. In our competition, participants develop a system to obtain a diamond in Minecraft using only four days of training time.[\/card]\r\n\r\n[card title=\"Multi-Agent Reinforcement Learning in Malmo (MARLO) Competition 2018\" url=\"https:\/\/www.crowdai.org\/challenges\/marlo-2018\" ]The second round of competition was to create learning agents that can play multiple 3D games as de\ufb01ned in the Malmo platform.[\/card]\r\n[\/row]\r\n[row]\r\n[card title=\"Malmo Collaborative AI Challenge 2017\" url=\"https:\/\/www.microsoft.com\/en-us\/research\/academic-program\/collaborative-ai-challenge\/\" ]The first round of the Malmo Collaborative AI Challenge was to develop and train collaborative AI solutions that learn to achieve high scores across a range of partners. [\/card]\r\n[\/row]"}],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Dave Bignell","user_id":38320,"people_section":"Research team","alias":"dabignel"},{"type":"user_nicename","display_name":"Katja Hofmann","user_id":32468,"people_section":"Research team","alias":"kahofman"},{"type":"user_nicename","display_name":"Evelyne Viegas","user_id":31768,"people_section":"Research team","alias":"evelynev"},{"type":"user_nicename","display_name":"Matthew Johnson","user_id":32830,"people_section":"Malmo alumni","alias":"matjoh"},{"type":"guest","display_name":"Oliver Kilian","user_id":650370,"people_section":"Malmo alumni","alias":""},{"type":"user_nicename","display_name":"Bhaskar Mitra","user_id":31257,"people_section":"Malmo alumni","alias":"bmitra"},{"type":"user_nicename","display_name":"Robert Schapire","user_id":33549,"people_section":"Malmo alumni","alias":"schapire"}],"msr_research_lab":[199561,437514],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/235753","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":33,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/235753\/revisions"}],"predecessor-version":[{"id":1135912,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/235753\/revisions\/1135912"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/238697"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=235753"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=235753"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=235753"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=235753"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=235753"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}