{"id":669597,"date":"2020-08-03T07:00:29","date_gmt":"2020-08-03T14:00:29","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&p=669597"},"modified":"2024-04-03T10:45:51","modified_gmt":"2024-04-03T17:45:51","slug":"project-paidia","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/project-paidia\/","title":{"rendered":"Project Paidia: a Microsoft Research & Ninja Theory Collaboration"},"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\tResearch for Industry\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

Project Paidia: a Microsoft Research & Ninja Theory Collaboration<\/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
\"Ninja<\/figure>\n\n\n\n

Project Paidia is a research project in close collaboration between Microsoft Research Cambridge and Ninja Theory (opens in new tab)<\/span><\/a>. Its focus 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\n\n\n

In contrast to traditional approaches to crafting the behavior of bots, non-player characters, or other in-game characters, reinforcement learning does not require a game developer to anticipate a wide range of possible game situations and map out and code all required behaviors. Instead, with reinforcement learning, game developers control a reward signal which the game character then learns to optimize while responding fluidly to all aspects of a game\u2019s dynamics. The result is nuanced situation and player-aware emergent behavior that would be challenging or prohibitive to achieve using traditional Game AI.<\/p>\n\n\n\n

\"Project
Project Paidia demo – Learning to collaborate in Bleeding Edge, footage of trained Project Paidia agents. Not representative of final game gameplay or visuals.<\/figcaption><\/figure>\n\n\n\n

Project Paidia focuses on learning a particularly challenging type of behavior: collaboration with human players. Because human players are notoriously creative and hard to predict, creating the experience of genuine collaboration towards shared goals has long been elusive. Together with colleagues at Ninja Theory, the MSR team identified a perfect test bed for driving this research, Ninja Theory\u2019s latest game Bleeding Edge. Bleeding Edge is a team-based game, and includes a range of characters that have to work together to score points and defeat their opponents. In their latest demo, the team showcases how reinforcement learning enables agents to learn to coordinate their actions.<\/p>\n\n\n\n

\n
Research publications<\/a><\/div>\n\n\n\n
Game Stack Live blog<\/a><\/div>\n<\/div>\n\n\n\n
<\/div>\n\n\n","protected":false},"excerpt":{"rendered":"

One goal of Project Paidia, a collaborative research project, is to drive state of the art research in reinforcement learning to enable game agents that learn to collaborate with human players.<\/p>\n","protected":false},"featured_media":675837,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13556],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-669597","msr-project","type-msr-project","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"","related-publications":[686709,953994,728659,728665,728671,740749,742288,622842,747847,625983,833743,630102,890679,630108,953973,630114,953982],"related-downloads":[770374],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Dave Bignell","user_id":38320,"people_section":"Microsoft Researcher team","alias":"dabignel"},{"type":"user_nicename","display_name":"Yuhan Cao","user_id":41767,"people_section":"Microsoft Researcher team","alias":"t-yuhancao"},{"type":"user_nicename","display_name":"Sam Devlin","user_id":37550,"people_section":"Microsoft Researcher team","alias":"sadevlin"},{"type":"user_nicename","display_name":"Raluca Stevenson","user_id":37392,"people_section":"Microsoft Researcher team","alias":"rageorg"},{"type":"user_nicename","display_name":"Katja Hofmann","user_id":32468,"people_section":"Microsoft Researcher team","alias":"kahofman"},{"type":"user_nicename","display_name":"Ida Momennejad","user_id":39832,"people_section":"Microsoft Researcher team","alias":"idamo"},{"type":"guest","display_name":"Tabish Rashid","user_id":640431,"people_section":"Microsoft Researcher team","alias":""},{"type":"user_nicename","display_name":"Shanzheng Tan","user_id":41551,"people_section":"Microsoft Researcher team","alias":"t-stan"},{"type":"guest","display_name":"Jacob Beck","user_id":585001,"people_section":"Former collaborators","alias":""},{"type":"guest","display_name":"Sebastian Dziadzio","user_id":676026,"people_section":"Former collaborators","alias":""},{"type":"guest","display_name":"Vincent Fortuin","user_id":621216,"people_section":"Former collaborators","alias":""},{"type":"guest","display_name":"Jayesh Gupta","user_id":595177,"people_section":"Former collaborators","alias":""},{"type":"guest","display_name":"Maximilian Igl","user_id":588319,"people_section":"Former collaborators","alias":""},{"type":"guest","display_name":"Andre Kramer","user_id":587986,"people_section":"Former collaborators","alias":""},{"type":"guest","display_name":"Robert Loftin","user_id":595171,"people_section":"Former collaborators","alias":""},{"type":"guest","display_name":"Cristiana Pacheco","user_id":676029,"people_section":"Former collaborators","alias":""},{"type":"guest","display_name":"Quan Vuong","user_id":586819,"people_section":"Former collaborators","alias":""},{"type":"guest","display_name":"Luisa Zintgraf","user_id":637290,"people_section":"Former collaborators","alias":""},{"type":"guest","display_name":"Evelyn Zuniga","user_id":852255,"people_section":"Former collaborators","alias":""}],"msr_research_lab":[199561],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/669597"}],"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":31,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/669597\/revisions"}],"predecessor-version":[{"id":1022013,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/669597\/revisions\/1022013"}],"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=669597"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=669597"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=669597"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=669597"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=669597"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}