{"id":583324,"date":"2020-03-02T06:08:38","date_gmt":"2019-06-12T10:42:06","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-group&p=583324"},"modified":"2024-11-22T03:45:50","modified_gmt":"2024-11-22T11:45:50","slug":"game-intelligence","status":"publish","type":"msr-group","link":"https:\/\/www.microsoft.com\/en-us\/research\/group\/game-intelligence\/","title":{"rendered":"Game Intelligence"},"content":{"rendered":"
\n\t
\n\t\t
\n\t\t\t\"Project\t\t<\/div>\n\t\t\n\t\t
\n\t\t\t\n\t\t\t
\n\t\t\t\t\n\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\tReturn to Microsoft Research Lab – Cambridge\t\t\t\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n

Game Intelligence<\/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
\n

With over three billion players in the world, AI is poised to transform the landscape of gaming experiences and the games industry itself. Microsoft’s vision for gaming is a world where players are empowered to play the games they want, with the people they want, whenever they want, where-ever they are, and on any device. In close collaboration with the Xbox Gaming division, we drive towards this transformation through world-leading machine learning research.<\/p>\n<\/div>

\"Project<\/figure><\/div>\n\n\n
\n\t
\n\n\t\t\n\t\t
\n\t\t\t\t\t\t\n\t\t\t\t\t<\/div>\n\t<\/div>\n<\/div>\n\n\n\n\n\n

Featured collaboration<\/h3>\n\n\n\n
\"Oxford<\/figure>\n\n\n\n

MSR PI:<\/strong> Katja Hofmann (opens in new tab)<\/span><\/a>
University of Oxford PI:<\/strong> Shimon Whiteson (opens in new tab)<\/span><\/a>
Joint Postdoctoral Researcher:<\/strong> Mingfei Sun<\/p>\n\n\n\n

\"portrait
Mingfei Sun<\/figcaption><\/figure>\n\n\n\n

Reinforcement Learning for Gaming<\/h4>\n\n\n\n

This project will focus on developing and analysing state-of-the-art reinforcement learning (RL) methods for application to video games. The project aims to tackle two key challenges. First, building effective game AI with RL requires dramatically scaling up existing tools for cooperative multi-agent RL, in which teams of agents must collaborate to complete tasks. Doing so requires new methods for performing multi-agent credit assignment and multi-agent exploration in large state and action spaces.  Second, effective game AI must also be able to transfer effectively to new scenarios, such as new game levels and versions, without having to learn from scratch. Doing so requires new methods for transfer and meta-learning in RL that scale to the complexity of modern video games.<\/p>\n\n\n\n

<\/div>\n\n\n\n

Industry collaborators<\/h3>\n\n\n\n
\n
\n
\"Ninja<\/figure>\n\n\n\n
<\/div>\n\n\n\n

Ninja Theory (opens in new tab)<\/span><\/a> was formed in 2004 by four partners, including current directors Nina Kristensen (Chief Development Director), Tameem Antoniades (Chief Creative Director) and Jez San OBE (Non-Executive Director). The studio pride themselves on striving for the highest production values and continually pushing the boundaries of technology, art and design to create evermore exciting video game experiences.<\/p>\n\n\n\n

Find out more about our collaboration with Ninja Theory<\/a> ><\/p>\n<\/div>\n\n\n\n

\n
\"IGGI<\/figure>\n\n\n\n
<\/div>\n\n\n\n

Industry Partner and Advisory Board Member of the IGGI Centre for Doctoral Training (opens in new tab)<\/span><\/a><\/p>\n<\/div>\n<\/div>\n\n\n\n

<\/div>\n\n\n\n

Academic collaborations<\/h3>\n\n\n\n

Learning to Collaborate with Human Players<\/b>
Katja Hofmann (opens in new tab)<\/span><\/a> (MSR Cambridge), Sam Devlin (opens in new tab)<\/span><\/a> (MSR Cambridge), Professor Anca Dragan (opens in new tab)<\/span><\/a> (BAIR), Micah Carroll (opens in new tab)<\/span><\/a> (PhD student)<\/em><\/p>\n\n\n\n

Find out more on our Berkeley AI Research collaboration page ><\/a><\/p>\n\n\n\n

Malmo 2020 Multi-Agent Upgrade
<\/strong>Diego Perez Liebana (opens in new tab)<\/span><\/a>
Queen Mary University London
Microsoft\u2019s Project Malmo platform enables users to create worlds and learning agents able to play multiple 3D games within Minecraft. In recent years, we have co-organised two international competitions. First on multi-agent learning and, secondly, on sample efficient reinforcement learning with human priors . These competitions have extended the features of the platform, but each introduced their own API, installation instructions and documentation, which has created an unnecessary barrier to researchers wanting to get started with the platform. The objective of this project is to unify the extensions from both competitions back into the original Malmo benchmark, to provide a common entry point for researchers.<\/em><\/p>\n\n\n\n

Sponsored PhDs<\/h3>\n\n\n\n

Reinforcement Learning for Enabling Next Generation Human-Machine Partnerships
<\/strong>Max Planck Institute for Software Systems
MSR Supervisor:<\/strong> Sam Devlin (opens in new tab)<\/span><\/a>
External Supervisor:<\/strong> Adish Singla (opens in new tab)<\/span><\/a><\/p>\n\n\n\n

Local Forward Model Learning for Sample-Efficient Sequential Decision Making in Open-World 3D Games
<\/strong>Queen Mary University
<\/strong>MSR Supervisor:<\/strong> Sam Devlin (opens in new tab)<\/span><\/a>
External Supervisor:<\/strong> Diego Perez Liebana (opens in new tab)<\/span><\/a><\/p>\n\n\n\n

Deep Reinforcement Learning For Collaborative Game AI To Enhance Player Experience
<\/strong>University of York
MSR Supervisor:<\/strong> Sam Devlin (opens in new tab)<\/span><\/a>
External Supervisor:<\/strong> James Walker (opens in new tab)<\/span><\/a> and Dan (opens in new tab)<\/span><\/a>iel Kudenko (opens in new tab)<\/span><\/a><\/p>\n\n\n\n

Better Sample Efficiency of Reinforcement Learning
<\/strong>University of Edinburgh
MSR Supervisor:<\/strong> Sam Devlin (opens in new tab)<\/span><\/a>
External Supervisor:<\/strong> Amos Storkey (opens in new tab)<\/span><\/a><\/p>\n\n\n\n

Reinforcement Learning for Adaptive User Interaction
<\/strong>University of Oxford
<\/strong>MSR Supervisor:<\/strong> Katja Hofmann (opens in new tab)<\/span><\/a>
External Supervisor:<\/strong> Shimon Whiteson (opens in new tab)<\/span><\/a><\/p>\n\n\n\n

Intrinsically Motivated Exploration for Lifelong Deep Reinforcement Learning of Multiple Tasks
<\/strong>INRIA
<\/strong>MSR Supervisor: <\/strong>Katja Hofmann (opens in new tab)<\/span><\/a>
External Supervisor:<\/strong> Pierre-Yves Oudeyer (opens in new tab)<\/span><\/a><\/p>\n\n\n\n\n\n

Talks<\/h2>\n\n\n\n

March 2022 | GDC 2022 – Age of Empires IV: Machine Learning Trials and Tribulations (opens in new tab)<\/span><\/a><\/p>\n\n\n\n

August 2020 | Microsoft Game Stack – Game Stack Live August 2020 – Panel Discussion – Katja Hofmann (opens in new tab)<\/span><\/a><\/p>\n\n\n\n

August 2020 | Microsoft Game Stack – Training In-Game Agents with Reinforcement Learning – Katja Hofmann (opens in new tab)<\/span><\/a><\/p>\n\n\n\n

July 2020 | Minecraft – Meet a Minecrafter: Artificial Intelligence (Part 1) – Katja Hofmann (opens in new tab)<\/span><\/a><\/p>\n\n\n\n

April 2020 | UK Symposium on Multi-Agent Systems (UK-MAS) – Multi-agent learning & evaluation for open world games – Sam Devlin (opens in new tab)<\/span><\/a><\/p>\n\n\n\n

October 2019 | Reinforcement Learning Day 2019 – Generalization in Reinforcement Learning with Selective Noise Injection – Sam Devlin (opens in new tab)<\/span><\/a><\/p>\n\n\n\n

Workshops<\/h2>\n\n\n\n

November 2018 | MARLO AIIDE 2018 WORKSHOP (opens in new tab)<\/span><\/a><\/p>\n\n\n\n\n\n

\n
\n
\"Minecraft<\/figure>\n\n\n\n

Project Malmo<\/a><\/h2>\n\n\n\n

Our research on multi-agent learning aims to develop intelligent agents that can collaborate with people, in applications ranging from video games to assistive technology. As we endeavour to unravel the principles of multi-agent learning and collaboration, our research is facilitated by the Project Malmo (opens in new tab)<\/span><\/a>, our open-source experimentation platform (opens in new tab)<\/span><\/a> built on the game Minecraft.<\/p>\n<\/div>\n\n\n\n

\n
\"Project<\/figure>\n\n\n\n

Project Paidia<\/a><\/h2>\n\n\n\n

The focus of Project Paidia is to drive state of the art research in reinforcement learning to enable novel applications in modern video games, in particular: agents that learn to collaborate with human players.<\/p>\n<\/div>\n<\/div>\n\n\n","protected":false},"excerpt":{"rendered":"

Microsoft’s vision for gaming is a world where players are empowered to play the games they want, with the people they want, whenever they want, where-ever they are, and on any device. The Game Intelligence team, in close collaboration with the Xbox Gaming division, are driving towards this transformation through world-leading machine learning research.<\/p>\n","protected":false},"featured_media":675837,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr_group_start":"","footnotes":""},"research-area":[13556],"msr-group-type":[243694],"msr-locale":[268875],"msr-impact-theme":[],"class_list":["post-583324","msr-group","type-msr-group","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-group-type-group","msr-locale-en_us"],"msr_group_start":"","msr_detailed_description":"","msr_further_details":"","msr_hero_images":[],"msr_research_lab":[199561],"related-researchers":[{"type":"user_nicename","display_name":"Katja Hofmann","user_id":32468,"people_section":"Team","alias":"kahofman"},{"type":"user_nicename","display_name":"Sam Devlin","user_id":37550,"people_section":"Team","alias":"sadevlin"},{"type":"user_nicename","display_name":"Sergio Valcarcel Macua","user_id":42507,"people_section":"Team","alias":"sergiov"},{"type":"user_nicename","display_name":"Tabish Rashid","user_id":41784,"people_section":"Team","alias":"tabishrashid"},{"type":"user_nicename","display_name":"Dave Bignell","user_id":38320,"people_section":"Team","alias":"dabignel"},{"type":"user_nicename","display_name":"Raluca Stevenson","user_id":37392,"people_section":"Team","alias":"rageorg"},{"type":"user_nicename","display_name":"Yuhan Cao","user_id":41767,"people_section":"Team","alias":"t-yuhancao"},{"type":"user_nicename","display_name":"Abdelhak Lemkhenter","user_id":43059,"people_section":"Team","alias":"t-abdelhakl"},{"type":"user_nicename","display_name":"Lukas Schäfer","user_id":43602,"people_section":"Team","alias":"t-luschaefer"},{"type":"user_nicename","display_name":"Linda Yilin Wen","user_id":42576,"people_section":"Team","alias":"t-wenlinda"},{"type":"user_nicename","display_name":"Shanzheng Tan","user_id":41551,"people_section":"Team","alias":"t-stan"},{"type":"guest","display_name":"Chentian Jiang","user_id":1048116,"people_section":"Team","alias":""},{"type":"guest","display_name":"Mariya Hendriksen","user_id":1087953,"people_section":"Team","alias":""},{"type":"guest","display_name":"Eloi Alonso","user_id":960456,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Ron Amit","user_id":637293,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Batu Aytemiz","user_id":726652,"people_section":"Alumni","alias":""},{"type":"user_nicename","display_name":"Richard Banks","user_id":33361,"people_section":"Alumni","alias":"rbanks"},{"type":"guest","display_name":"Jacob Beck","user_id":585001,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Micah Carroll","user_id":756637,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Vincent Fortuin","user_id":621216,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Raluca Gaina","user_id":637377,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Christian Guckelsberger","user_id":637299,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Jayesh Gupta","user_id":595177,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Abhinav Gupta","user_id":787006,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Tarun Gupta","user_id":937158,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Gunshi Gupta","user_id":937143,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Maximilian Igl","user_id":588319,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Shu Ishida","user_id":1039161,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Mikhail Jacob","user_id":621225,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Adam Jelley","user_id":960465,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Anssi Kanervisto","user_id":999792,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Khimya Khetarpal","user_id":849061,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Oliver Kilian","user_id":650370,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Andre Kramer","user_id":587986,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Nate Kushman","user_id":650373,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Xiaoyu Lu","user_id":637383,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Yuxiang Li","user_id":637386,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Cong Lu","user_id":849055,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Robyn McMillan","user_id":637371,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Stephanie Milani","user_id":756634,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Ben Nicholson","user_id":621219,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Adrian O'Grady","user_id":756628,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Nadzeya Paleyes","user_id":587950,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Tim Pearce","user_id":1090554,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Roberta Raileanu","user_id":637380,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Dino Ratcliffe","user_id":637374,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Caroline Rizzi Raymundo","user_id":756631,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"David Robertson","user_id":637368,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Lukas Sch\u00e4fer","user_id":937152,"people_section":"Alumni","alias":""},{"type":"user_nicename","display_name":"David Sweeney","user_id":31553,"people_section":"Alumni","alias":"dasweene"},{"type":"guest","display_name":"Panagiotis Tigkas","user_id":756640,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Aristide Tossou","user_id":637296,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Marko Tot","user_id":1039155,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Sebastian Tschiatschek","user_id":633534,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Quan Vuong","user_id":586819,"people_section":"Alumni","alias":""},{"type":"user_nicename","display_name":"Haiyan Zhang","user_id":31986,"people_section":"Alumni","alias":"hazhang"},{"type":"guest","display_name":"Luisa Zintgraf","user_id":637290,"people_section":"Alumni","alias":""},{"type":"guest","display_name":"Evelyn Zuniga","user_id":1090560,"people_section":"Alumni","alias":""}],"related-publications":[565713,742288,618027,953982,630114,565719,747847,622842,953994,630174,565725,756472,624708,954027,636369,565731,760264,624714,954033,636378,565737,760447,624720,1106478,686709,565743,817573,625965,1106484,237369,728659,565749,833743,625971,1106496,389849,728665,589015,890679,625977,1106502,427662,728671,589030,900174,625983,1106511,475635,728677,589033,936006,630102,565707,728686,593947,953973,630108],"related-downloads":[770374],"related-videos":[],"related-projects":[],"related-events":[],"related-opportunities":[1105062],"related-posts":[],"tab-content":[{"id":0,"name":"Collaborations","content":"

Featured collaboration<\/strong><\/h3>\r\n\"Oxford\r\n\r\nMSR PI:<\/strong> Katja Hofmann<\/a>\r\nUniversity of Oxford PI:<\/strong> Shimon Whiteson<\/a>\r\nJoint Postdoctoral Researcher:<\/strong> Mingfei Sun\r\n

Reinforcement Learning for Gaming<\/h3>\r\n[caption id=\"\" align=\"alignleft\" width=\"150\"]\"Mingfei Mingfei Sun[\/caption]\r\n\r\nThis project will focus on developing and analysing state-of-the-art reinforcement learning (RL) methods for application to video games.\u00a0 The project aims to tackle two key challenges.\u00a0 First, building effective game AI with RL requires dramatically scaling up existing tools for cooperative multi-agent RL, in which teams of agents must collaborate to complete tasks.\u00a0 Doing so requires new methods for performing multi-agent credit assignment and multi-agent exploration in large state and action spaces.\u00a0 Second, effective game AI must also be able to transfer effectively to new scenarios, such as new game levels and versions, without having to learn from scratch.\u00a0 Doing so requires new methods for transfer and meta-learning in RL that scale to the complexity of modern video games.\r\n
<\/div>\r\n

Industry collaborators<\/strong><\/h3>\r\n\"Ninja\r\n\r\nNinja Theory<\/a> was formed in 2004 by four partners, including current Directors Nina Kristensen (Chief Development Director), Tameem Antoniades (Chief Creative Director) and Jez San OBE (Non-Executive Director). The studio pride themselves on striving for the highest production values and continually pushing the boundaries of technology, art and design to create evermore exciting video game experiences.\r\n\r\nFind out more about our collaboration with Ninja Theory on the Project Paidia page<\/a> >\r\n\r\n\"IGGI\r\n
Industry Partner and Advisory Board Member of the\u00a0IGGI Centre for Doctoral Training<\/a><\/div>\r\n
<\/div>\r\n \r\n

Academic Collaborations<\/strong><\/h3>\r\nLearning to Collaborate with Human Players<\/b>\r\nKatja Hofmann<\/a> (MSR Cambridge), Sam Devlin<\/a> (MSR Cambridge), Kamil Ciosek<\/a> (MSR Cambridge), Professor Anca Dragan<\/a> (BAIR), Micah Carroll (PhD student)<\/em>\r\n\r\nFind out more on our Berkeley AI Research collaboration page ><\/a>\r\n\r\nMalmo 2020 Multi-Agent Upgrade\r\n<\/strong>Diego Perez Liebana<\/a>\r\nQueen Mary University London\r\nMicrosoft\u2019s Project Malmo platform enables users to create worlds and learning agents able to play multiple 3D games within Minecraft. In recent years, we have co-organised two international competitions. First on multi-agent learning and, secondly, on sample efficient reinforcement learning with human priors . These competitions have extended the features of the platform, but each introduced their own API, installation instructions and documentation, which has created an unnecessary barrier to researchers wanting to get started with the platform. The objective of this project is to unify the extensions from both competitions back into the original Malmo benchmark, to provide a common entry point for researchers.<\/em>\r\n

Sponsored PhDs<\/strong><\/h3>\r\nReinforcement Learning for Enabling Next Generation Human-Machine Partnerships\r\n<\/strong>Max Planck Institute for Software Systems\r\nMSR Supervisor:<\/strong> Sam Devlin<\/a>\r\nExternal Supervisor:<\/strong> Adish Singla<\/a>\r\n\r\nLocal Forward Model Learning for Sample-Efficient Sequential Decision Making in Open-World 3D Games\r\n<\/strong>Queen Mary University\r\n<\/strong>MSR Supervisor:<\/strong> Sam Devlin<\/a>\r\nExternal Supervisor:<\/strong> Diego Perez Liebana<\/a>\r\n\r\nDeep Reinforcement Learning For Collaborative Game AI To Enhance Player Experience\r\n<\/strong>University of York\r\n<\/strong>MSR Supervisor:<\/strong> Sam Devlin<\/a>\r\nExternal Supervisor:<\/strong> TBC\r\n\r\nBetter Sample Efficiency of Reinforcement Learning\r\n<\/strong>University of Edinburgh\r\n<\/strong>MSR Supervisor:<\/strong> Kamil Ciosek<\/a>\r\nExternal Supervisor:<\/strong> Amos Storkey<\/a>\r\n\r\nReinforcement Learning for Adaptive User Interaction\r\n<\/strong>University of Oxford\r\n<\/strong>MSR Supervisor:<\/strong> Katja Hofmann<\/a>\r\nExternal Supervisor:<\/strong> Shimon Whiteson<\/a>\r\n\r\nIntrinsically Motivated Exploration for Lifelong Deep Reinforcement Learning of Multiple Tasks\r\n<\/strong>INRIA\r\n<\/strong>MSR Supervisor: <\/strong>Katja Hofmann<\/a>\r\nExternal Supervisor:<\/strong> Pierre-Yves Oudeyer<\/a>"},{"id":1,"name":"Talks & Workshops","content":"

Talks<\/h2>\r\nOctober 2019 | Reinforcement Learning Day 2019 - Generalization in Reinforcement Learning with Selective Noise Injection - Sam Devlin<\/a>\r\n\r\nApril 2020 | UK Symposium on Multi-Agent Systems (UK-MAS) - Multi-agent learning & evaluation for open world games - Sam Devlin<\/a>\r\n\r\nJuly 2020 | Minecraft - Meet a Minecrafter: Artificial Intelligence (Part 1) - Katja Hofmann<\/a>\r\n\r\nAugust 2020 | Microsoft Game Stack - Training In-Game Agents with Reinforcement Learning - Katja Hofmann<\/a>\r\n\r\nAugust 2020 | Microsoft Game Stack - Game Stack Live August 2020 - Panel Discussion - Katja Hofmann<\/a>\r\n

Workshops<\/h2>\r\nNovember 2018 |\u00a0MARLO AIIDE 2018 WORKSHOP<\/a>"}],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-group\/583324"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-group"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-group"}],"version-history":[{"count":84,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-group\/583324\/revisions"}],"predecessor-version":[{"id":1039164,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-group\/583324\/revisions\/1039164"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/675837"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=583324"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=583324"},{"taxonomy":"msr-group-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-group-type?post=583324"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=583324"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=583324"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}