The ability to create artificial intelligence (AI) capable of performing complex tasks is rapidly outpacing our ability to ensure the safe and assured operation of AI-enabled systems. Fortunately, a landscape of AI safety research is emerging in response to this asymmetry and yet there is a long way to go. In particular, recent simulation environments created to illustrate AI safety risks are relatively simple or narrowly-focused on a particular issue. Hence, we see a critical need for AI safety research environments that abstract essential aspects of complex real-world applications. In this work, we introduce the AI safety TanksWorld as an environment for AI safety research with three essential aspects: competing performance objectives, human-machine teaming, and multi-agent competition. The AI safety TanksWorld aims to accelerate the advancement of safe multi-agent decision-making algorithms by providing a software framework to support competitions with both system performance and safety objectives. As a work in progress, this paper introduces our research objectives and learning environment with reference code and baseline performance metrics to follow in a future work.<\/p>\n","protected":false},"excerpt":{"rendered":"
The ability to create artificial intelligence (AI) capable of performing complex tasks is rapidly outpacing our ability to ensure the safe and assured operation of AI-enabled systems. Fortunately, a landscape of AI safety research is emerging in response to this asymmetry and yet there is a long way to go. In particular, recent simulation environments […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556],"msr-publication-type":[193724],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[246691,249820,250168,250171,250174,250162,250165],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-719593","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-field-of-study-computer-science","msr-field-of-study-engineering-management","msr-field-of-study-learning-environment","msr-field-of-study-performance-objective","msr-field-of-study-research-objectives","msr-field-of-study-software-framework","msr-field-of-study-work-in-process"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2020-2-24","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"ArXiv preprint","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":0,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/arxiv.org\/abs\/2002.11174","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Corban G. Rivera","user_id":0,"rest_url":false},{"type":"text","value":"Olivia Lyons","user_id":0,"rest_url":false},{"type":"text","value":"Arielle Summitt","user_id":0,"rest_url":false},{"type":"text","value":"Ayman Fatima","user_id":0,"rest_url":false},{"type":"text","value":"Ji Pak","user_id":0,"rest_url":false},{"type":"text","value":"William Shao","user_id":0,"rest_url":false},{"type":"text","value":"Robert Chalmers","user_id":0,"rest_url":false},{"type":"text","value":"Aryeh Englander","user_id":0,"rest_url":false},{"type":"text","value":"Edward W. Staley","user_id":0,"rest_url":false},{"type":"text","value":"I-Jeng Wang","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Ashley Llorens","user_id":39964,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ashley Llorens"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"miscellaneous","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/719593"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/719593\/revisions"}],"predecessor-version":[{"id":719596,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/719593\/revisions\/719596"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=719593"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=719593"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=719593"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=719593"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=719593"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=719593"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=719593"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=719593"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=719593"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=719593"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=719593"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=719593"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=719593"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=719593"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=719593"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}