{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T17:26:35Z","timestamp":1767979595636,"version":"3.49.0"},"reference-count":78,"publisher":"Association for Computing Machinery (ACM)","issue":"3-4","license":[{"start":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T00:00:00Z","timestamp":1630627200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000185","name":"DARPA","doi-asserted-by":"crossref","award":["#N66001-17-2-4030"],"award-info":[{"award-number":["#N66001-17-2-4030"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Interact. Intell. Syst."],"published-print":{"date-parts":[[2021,12,31]]},"abstract":"<jats:p>\n            Explainable AI is growing in importance as AI pervades modern society, but few have studied how explainable AI can directly support people trying to\n            <jats:italic>assess<\/jats:italic>\n            an AI agent. Without a rigorous process, people may approach assessment in ad hoc ways\u2014leading to the possibility of wide variations in assessment of the same agent due only to variations in their processes. AAR, or After-Action Review, is a method some military organizations use to assess human agents, and it has been validated in many domains. Drawing upon this strategy, we derived an After-Action Review for AI (AAR\/AI), to organize ways people assess reinforcement learning agents in a sequential decision-making environment. We then investigated what AAR\/AI brought to human assessors in two qualitative studies. The first investigated AAR\/AI to gather formative information, and the second built upon the results, and also varied the type of explanation (model-free vs. model-based) used in the AAR\/AI process. Among the results were the following: (1)\u00a0participants reporting that AAR\/AI helped to\n            <jats:italic>organize their thoughts<\/jats:italic>\n            and\n            <jats:italic>think logically<\/jats:italic>\n            about the agent, (2)\u00a0AAR\/AI encouraged participants to reason about the agent from a\n            <jats:italic>wide range of perspectives<\/jats:italic>\n            , and (3)\u00a0participants were able to leverage AAR\/AI with the model-based explanations to\n            <jats:italic>falsify<\/jats:italic>\n            the agent\u2019s predictions.\n          <\/jats:p>","DOI":"10.1145\/3453173","type":"journal-article","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T19:30:07Z","timestamp":1630697407000},"page":"1-35","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["After-Action Review for AI (AAR\/AI)"],"prefix":"10.1145","volume":"11","author":[{"given":"Jonathan","family":"Dodge","sequence":"first","affiliation":[{"name":"Oregon State University, Corvallis, OR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roli","family":"Khanna","sequence":"additional","affiliation":[{"name":"Oregon State University, Corvallis, OR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jed","family":"Irvine","sequence":"additional","affiliation":[{"name":"Oregon State University, Corvallis, OR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kin-ho","family":"Lam","sequence":"additional","affiliation":[{"name":"Oregon State University, Corvallis, OR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Theresa","family":"Mai","sequence":"additional","affiliation":[{"name":"Oregon State University, Corvallis, OR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengxian","family":"Lin","sequence":"additional","affiliation":[{"name":"Oregon State University, Corvallis, OR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas","family":"Kiddle","sequence":"additional","affiliation":[{"name":"Oregon State University, Corvallis, OR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evan","family":"Newman","sequence":"additional","affiliation":[{"name":"Oregon State University, Corvallis, OR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Anderson","sequence":"additional","affiliation":[{"name":"Oregon State University, Corvallis, OR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sai","family":"Raja","sequence":"additional","affiliation":[{"name":"Oregon State University, Corvallis, OR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caleb","family":"Matthews","sequence":"additional","affiliation":[{"name":"Oregon State University, Corvallis, OR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Perdriau","sequence":"additional","affiliation":[{"name":"Oregon State University, Corvallis, OR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Margaret","family":"Burnett","sequence":"additional","affiliation":[{"name":"Oregon State University, Corvallis, OR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alan","family":"Fern","sequence":"additional","affiliation":[{"name":"Oregon State University, Corvallis, OR"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,9,3]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300233"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/184"},{"key":"e_1_2_1_3_1","first-page":"2","article-title":"Mental models of mere mortals with explanations of reinforcement learning","volume":"10","author":"Anderson Andrew","year":"2020","unstructured":"Andrew Anderson , Jonathan Dodge , Amrita Sadarangani , Zoe Juozapaitis , Evan Newman , Jed Irvine , Souti Chattopadhyay , Matthew Olson , Alan Fern , and Margaret Burnett . 2020 . Mental models of mere mortals with explanations of reinforcement learning . ACM Transactions on Interactive Intelligence Systems 10 , 2 (May 2020), Article 15, 37 pages. https:\/\/doi.org\/10.1145\/3366485 10.1145\/3366485 Andrew Anderson, Jonathan Dodge, Amrita Sadarangani, Zoe Juozapaitis, Evan Newman, Jed Irvine, Souti Chattopadhyay, Matthew Olson, Alan Fern, and Margaret Burnett. 2020. Mental models of mere mortals with explanations of reinforcement learning. ACM Transactions on Interactive Intelligence Systems 10, 2 (May 2020), Article 15, 37 pages. https:\/\/doi.org\/10.1145\/3366485","journal-title":"ACM Transactions on Interactive Intelligence Systems"},{"key":"e_1_2_1_4_1","volume-title":"Wittrock","author":"Anderson Lorin W.","year":"2001","unstructured":"Lorin W. Anderson , David R. Krathwohl , Peter W. Airasian , Kathleen A. Cruikshank , Richard E. Mayer , Paul R. Pintrich , James Raths , and Merlin C . Wittrock . 2001 . A Taxonomy for Learning, Teaching , and Assessing: A Revision of Bloom\u2019s Taxonomy of Educational Objectives. Pearson, New York, NY. Lorin W. Anderson, David R. Krathwohl, Peter W. Airasian, Kathleen A. Cruikshank, Richard E. Mayer, Paul R. Pintrich, James Raths, and Merlin C. Wittrock. 2001. A Taxonomy for Learning, Teaching, and Assessing: A Revision of Bloom\u2019s Taxonomy of Educational Objectives. Pearson, New York, NY."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173951"},{"key":"e_1_2_1_6_1","volume-title":"Krathwohl","author":"Bloom Benjamin S.","year":"1956","unstructured":"Benjamin S. Bloom , Max D. Engelhart , Edward J. Furst , Walker H. Hill , and David R . Krathwohl . 1956 . Taxonomy of Educational Objectives. Longmans, Green and Co. LTD, London, England . Benjamin S. Bloom, Max D. Engelhart, Edward J. Furst, Walker H. Hill, and David R. Krathwohl. 1956. Taxonomy of Educational Objectives. Longmans, Green and Co. LTD, London, England."},{"key":"e_1_2_1_7_1","volume-title":"Proceedings of the 2019 International Conference on Human Factors in Robots and Unmanned Systems (AHFE\u201919)","author":"Brewer Ralph","year":"2019","unstructured":"Ralph Brewer , Anthony Walker , E. Ray Pursel , Eduardo Cerame , Anthony Baker , and Kristin Schaefer . 2019 . Assessment of manned-unmanned team performance: Comprehensive after-action review technology development . In Proceedings of the 2019 International Conference on Human Factors in Robots and Unmanned Systems (AHFE\u201919) . Springer Nature Switzerland AG, Cham, Switzerland, 119\u2013130. Ralph Brewer, Anthony Walker, E. Ray Pursel, Eduardo Cerame, Anthony Baker, and Kristin Schaefer. 2019. Assessment of manned-unmanned team performance: Comprehensive after-action review technology development. In Proceedings of the 2019 International Conference on Human Factors in Robots and Unmanned Systems (AHFE\u201919). Springer Nature Switzerland AG, Cham, Switzerland, 119\u2013130."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359206"},{"key":"e_1_2_1_9_1","unstructured":"Nicholas Carlini and David Wagner. 2016. Towards evaluating the robustness of neural networks. arxiv:cs.CR\/1608.04644  Nicholas Carlini and David Wagner. 2016. Towards evaluating the robustness of neural networks. arxiv:cs.CR\/1608.04644"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1302_1"},{"key":"e_1_2_1_11_1","volume-title":"CNN Business. Retrieved","author":"CNN.","year":"2016","unstructured":"CNN. 2016 . Who\u2019s responsible when an autonomous car crashes ? CNN Business. Retrieved June 19, 2021 fromhttp:\/\/money.cnn.com\/2016\/07\/07\/technology\/tesla-liability-risk\/index.html. CNN. 2016. Who\u2019s responsible when an autonomous car crashes? CNN Business. Retrieved June 19, 2021 fromhttp:\/\/money.cnn.com\/2016\/07\/07\/technology\/tesla-liability-risk\/index.html."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3027063.3053114"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1017\/dmp.2018.82"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.2307\/249008"},{"key":"e_1_2_1_15_1","volume-title":"Proceedings of ExSS-ATEC@IUI","author":"Dodge Jonathan","year":"2020","unstructured":"Jonathan Dodge and M. Burnett . 2020. Position: We can measure XAI explanations better with templates . In Proceedings of ExSS-ATEC@IUI 2020 . 1\u20135. Jonathan Dodge and M. Burnett. 2020. Position: We can measure XAI explanations better with templates. In Proceedings of ExSS-ATEC@IUI 2020. 1\u20135."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174136"},{"key":"e_1_2_1_17_1","volume-title":"Proceedings of the 24th International Conference on Intelligent User Interfaces (IUI\u201919)","author":"Ehsan Upol","unstructured":"Upol Ehsan , Pradyumna Tambwekar , Larry Chan , Brent Harrison , and Mark O. Riedl . 2019. Automated rationale generation: A technique for explainable AI and its effects on human perceptions . In Proceedings of the 24th International Conference on Intelligent User Interfaces (IUI\u201919) . ACM, New York, NY, 263\u2013274. https:\/\/doi.org\/10.1145\/3301275.3302316 10.1145\/3301275.3302316 Upol Ehsan, Pradyumna Tambwekar, Larry Chan, Brent Harrison, and Mark O. Riedl. 2019. Automated rationale generation: A technique for explainable AI and its effects on human perceptions. In Proceedings of the 24th International Conference on Intelligent User Interfaces (IUI\u201919). ACM, New York, NY, 263\u2013274. https:\/\/doi.org\/10.1145\/3301275.3302316"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00175"},{"key":"e_1_2_1_19_1","volume-title":"Theoretical Perspectives","author":"Forrest-Pressley Donna-Lynn","unstructured":"Donna-Lynn Forrest-Pressley and G. E. MacKinnon . 1985. Metacognition, Cognition, and Human Performance : Theoretical Perspectives . Vol. 1 . Academic Press . Donna-Lynn Forrest-Pressley and G. E. MacKinnon. 1985. Metacognition, Cognition, and Human Performance: Theoretical Perspectives. Vol. 1. Academic Press."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.22381\/PIHRM4220161"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:TRUC.0000021809.10236.71"},{"key":"e_1_2_1_22_1","volume-title":"Cleverhans-Blog. Retrieved","author":"Goodfellow Ian","year":"2017","unstructured":"Ian Goodfellow and Nicolas Papernot . 2017 . The challenge of verification and testing of machine learning . Cleverhans-Blog. Retrieved June 19, 2021 from http:\/\/www.cleverhans.io\/security\/privacy\/ml\/2017\/06\/14\/verification.html. Ian Goodfellow and Nicolas Papernot. 2017. The challenge of verification and testing of machine learning. Cleverhans-Blog. Retrieved June 19, 2021 from http:\/\/www.cleverhans.io\/security\/privacy\/ml\/2017\/06\/14\/verification.html."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/SYSCON.2018.8369516"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4115(08)62386-9"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-010-0068-5"},{"key":"e_1_2_1_27_1","unstructured":"Robert R. Hoffman Shane T. Mueller Gary Klein and Jordan Litman. 2018. Metrics for explainable AI: Challenges and prospects. arXiv:1812.04608. http:\/\/arxiv.org\/abs\/1812.04608  Robert R. Hoffman Shane T. Mueller Gary Klein and Jordan Litman. 2018. Metrics for explainable AI: Challenges and prospects. arXiv:1812.04608. http:\/\/arxiv.org\/abs\/1812.04608"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300830"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1177\/1049732305276687"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1177\/1046496417697148"},{"key":"e_1_2_1_31_1","first-page":"223","article-title":"Nouvelles recherches sur la distribution florale","volume":"44","author":"Jaccard Paul","year":"1908","unstructured":"Paul Jaccard . 1908 . Nouvelles recherches sur la distribution florale . Bulletin de la Societe Vaudoise Des Sciences Naturelles 44 (1908), 223 \u2013 270 . Paul Jaccard. 1908. Nouvelles recherches sur la distribution florale. Bulletin de la Societe Vaudoise Des Sciences Naturelles 44 (1908), 223\u2013270.","journal-title":"Bulletin de la Societe Vaudoise Des Sciences Naturelles"},{"key":"e_1_2_1_32_1","article-title":"A meta-analysis of the effectiveness of the after-action review (or debrief) and factors that influence its effectiveness","author":"Keiser Nathanael","year":"2020","unstructured":"Nathanael Keiser and Winfred Arthur Jr . 2020 . A meta-analysis of the effectiveness of the after-action review (or debrief) and factors that influence its effectiveness . Journal of Applied Psychology. Early access , August 27, 2020. https:\/\/doi.org\/10.1037\/apl0000821 10.1037\/apl0000821 Nathanael Keiser and Winfred Arthur Jr. 2020. A meta-analysis of the effectiveness of the after-action review (or debrief) and factors that influence its effectiveness. Journal of Applied Psychology. Early access, August 27, 2020. https:\/\/doi.org\/10.1037\/apl0000821","journal-title":"Journal of Applied Psychology. Early access"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300487"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2800016"},{"key":"e_1_2_1_35_1","volume-title":"ACM CHI Conference Extended Abstracts. ACM","author":"Kim Man-Je","year":"1915","unstructured":"Man-Je Kim , Kyung-Joong Kim , SeungJun Kim , and Anind K. Dey . 2016. Evaluation of StarCraft artificial intelligence competition bots by experienced human players . In ACM CHI Conference Extended Abstracts. ACM , New York, NY , 1915 \u20131921. Man-Je Kim, Kyung-Joong Kim, SeungJun Kim, and Anind K. Dey. 2016. Evaluation of StarCraft artificial intelligence competition bots by experienced human players. In ACM CHI Conference Extended Abstracts. ACM, New York, NY, 1915\u20131921."},{"key":"e_1_2_1_36_1","volume-title":"Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI\u201919)","author":"Kocielnik Rafal","unstructured":"Rafal Kocielnik , Saleema Amershi , and Paul N. Bennett . 2019. Will you accept an imperfect AI? Exploring designs for adjusting end-user expectations of AI systems . In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI\u201919) . ACM, New York, NY, 1\u201314. https:\/\/doi.org\/10.1145\/3290605.3300641 10.1145\/3290605.3300641 Rafal Kocielnik, Saleema Amershi, and Paul N. Bennett. 2019. Will you accept an imperfect AI? Exploring designs for adjusting end-user expectations of AI systems. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI\u201919). ACM, New York, NY, 1\u201314. https:\/\/doi.org\/10.1145\/3290605.3300641"},{"key":"e_1_2_1_37_1","volume-title":"Proceedings of the ACM International Conference on Intelligent User Interfaces. ACM","author":"Kulesza T.","unstructured":"T. Kulesza , M. Burnett , W. Wong , and S. Stumpf . 2015. Principles of explanatory debugging to personalize interactive machine learning . In Proceedings of the ACM International Conference on Intelligent User Interfaces. ACM , New York, NY, 126\u2013137. T. Kulesza, M. Burnett, W. Wong, and S. Stumpf. 2015. Principles of explanatory debugging to personalize interactive machine learning. In Proceedings of the ACM International Conference on Intelligent User Interfaces. ACM, New York, NY, 126\u2013137."},{"key":"e_1_2_1_38_1","volume-title":"Proceedings of the ACM Conference on Human Factors in Computing Systems. ACM","author":"Kulesza Todd","year":"2012","unstructured":"Todd Kulesza , Simone Stumpf , Margaret Burnett , and Irwin Kwan . 2012 . Tell me more? The effects of mental model soundness on personalizing an intelligent agent . In Proceedings of the ACM Conference on Human Factors in Computing Systems. ACM , New York, NY, 1\u201310. Todd Kulesza, Simone Stumpf, Margaret Burnett, and Irwin Kwan. 2012. Tell me more? The effects of mental model soundness on personalizing an intelligent agent. In Proceedings of the ACM Conference on Human Factors in Computing Systems. ACM, New York, NY, 1\u201310."},{"key":"e_1_2_1_39_1","first-page":"5","article-title":"The art of the after-action review","volume":"171","author":"Lareau Adam","year":"2018","unstructured":"Adam Lareau and Brice Long . 2018 . The art of the after-action review . Fire Engineering 171 , 5 (May 2018), 61\u201364. http:\/\/search.proquest.com\/docview\/2157468757\/ Adam Lareau and Brice Long. 2018. The art of the after-action review. Fire Engineering 171, 5 (May 2018), 61\u201364. http:\/\/search.proquest.com\/docview\/2157468757\/","journal-title":"Fire Engineering"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/1518701.1519023"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0090-2616(99)90027-X"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377325.3377525"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2009.11.006"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287596"},{"key":"e_1_2_1_46_1","volume-title":"Meliza","author":"Morrison John E.","year":"1999","unstructured":"John E. Morrison and Larry L . Meliza . 1999 . Foundations of the After Action Review Process. Technical Report. Institute for Defense Analyses . https:\/\/apps.dtic.mil\/docs\/citations\/ADA368651. John E. Morrison and Larry L. Meliza. 1999. Foundations of the After Action Review Process. Technical Report. Institute for Defense Analyses. https:\/\/apps.dtic.mil\/docs\/citations\/ADA368651."},{"key":"e_1_2_1_47_1","first-page":"7","article-title":"Some observations on mental models","volume":"7","author":"Norman Donald A.","year":"1983","unstructured":"Donald A. Norman . 1983 . Some observations on mental models . Mental Models 7 , 112 (1983), 7 \u2013 14 . Donald A. Norman. 1983. Some observations on mental models. Mental Models 7, 112 (1983), 7\u201314.","journal-title":"Mental Models"},{"key":"e_1_2_1_48_1","volume-title":"Retrieved","author":"Times New York","year":"2017","unstructured":"New York Times . 2017 . Tesla\u2019s Self-Driving System Cleared in Deadly Crash . Retrieved June 19, 2021 from https:\/\/www.nytimes.com\/2017\/01\/19\/business\/tesla-model-s-autopilot-fatal-crash.html. New York Times. 2017. Tesla\u2019s Self-Driving System Cleared in Deadly Crash. Retrieved June 19, 2021 from https:\/\/www.nytimes.com\/2017\/01\/19\/business\/tesla-model-s-autopilot-fatal-crash.html."},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.5210\/ojphi.v8i3.7100"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2013.2286295"},{"key":"e_1_2_1_51_1","volume-title":"Proceedings of the International Symposium on Human Mental Workload: Models and Applications. 23\u201348","author":"Orru Giuliano","year":"2018","unstructured":"Giuliano Orru and Luca Longo . 2018 . The evolution of cognitive load theory and the measurement of its intrinsic, extraneous and Germane loads: A review . In Proceedings of the International Symposium on Human Mental Workload: Models and Applications. 23\u201348 . Giuliano Orru and Luca Longo. 2018. The evolution of cognitive load theory and the measurement of its intrinsic, extraneous and Germane loads: A review. In Proceedings of the International Symposium on Human Mental Workload: Models and Applications. 23\u201348."},{"key":"e_1_2_1_52_1","volume-title":"DeepXplore. In Proceedings of the 26th Symposium on Operating Systems Principles (SOSP\u201917)","author":"Pei Kexin","year":"2017","unstructured":"Kexin Pei , Yinzhi Cao , Junfeng Yang , and Suman Jana . 2017 . DeepXplore. In Proceedings of the 26th Symposium on Operating Systems Principles (SOSP\u201917) .https:\/\/doi.org\/10.1145\/3132747.3132785 10.1145\/3132747.3132785 Kexin Pei, Yinzhi Cao, Junfeng Yang, and Suman Jana. 2017. DeepXplore. In Proceedings of the 26th Symposium on Operating Systems Principles (SOSP\u201917).https:\/\/doi.org\/10.1145\/3132747.3132785"},{"key":"e_1_2_1_53_1","volume-title":"Proceedings of the 23rd International Conference on Intelligent User Interfaces (IUI \u201918)","author":"Penney Sean","year":"2018","unstructured":"Sean Penney , Jonathan Dodge , Claudia Hilderbrand , Andrew Anderson , Logan Simpson , and Margaret Burnett . 2018 . Toward foraging for understanding of StartCraft agents: An empirical study . In Proceedings of the 23rd International Conference on Intelligent User Interfaces (IUI \u201918) . ACM, New York, NY, 225\u2013237. https:\/\/doi.org\/10.1145\/3172944.3172946 10.1145\/3172944.3172946 Sean Penney, Jonathan Dodge, Claudia Hilderbrand, Andrew Anderson, Logan Simpson, and Margaret Burnett. 2018. Toward foraging for understanding of StartCraft agents: An empirical study. In Proceedings of the 23rd International Conference on Intelligent User Interfaces (IUI \u201918). ACM, New York, NY, 225\u2013237. https:\/\/doi.org\/10.1145\/3172944.3172946"},{"key":"e_1_2_1_54_1","first-page":"33","article-title":"Science as falsification","volume":"1","author":"Popper Karl R.","year":"1963","unstructured":"Karl R. Popper . 1963 . Science as falsification . Conjectures and Refutations 1 (1963), 33 \u2013 39 . Karl R. Popper. 1963. Science as falsification. Conjectures and Refutations 1 (1963), 33\u201339.","journal-title":"Conjectures and Refutations"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10055-013-0229-6"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1037\/0278-7393.11.1.106"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1006\/ceps.1997.0959"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300750"},{"key":"e_1_2_1_59_1","volume-title":"Russell and Peter Norvig","author":"Stuart","year":"2016","unstructured":"Stuart J. Russell and Peter Norvig . 2016 . Artificial Intelligence : A Modern Approach. Pearson Education Limited, Malaysia . Stuart J. Russell and Peter Norvig. 2016. Artificial Intelligence: A Modern Approach. Pearson Education Limited, Malaysia."},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1097\/SIH.0b013e31829ac85c"},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0263-7863(02)00096-0"},{"key":"e_1_2_1_63_1","volume-title":"Julian Schrittwieser, et\u00a0al.","author":"Silver David","year":"2016","unstructured":"David Silver , Aja Huang , Chris J. Maddison , Arthur Guez , Laurent Sifre , George Van Den Driessche , Julian Schrittwieser, et\u00a0al. 2016 . Mastering the game of Go with deep neural networks and tree search. Nature 529, 7587 (2016), 484. David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George Van Den Driessche, Julian Schrittwieser, et\u00a0al. 2016. Mastering the game of Go with deep neural networks and tree search. Nature 529, 7587 (2016), 484."},{"key":"e_1_2_1_64_1","volume-title":"et\u00a0al","author":"Silver David","year":"2018","unstructured":"David Silver , Thomas Hubert , Julian Schrittwieser , Ioannis Antonoglou , Matthew Lai , Arthur Guez , Marc Lanctot , et\u00a0al . 2018 . A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science 362, 6419 (2018), 1140\u20131144. https:\/\/doi.org\/10.1126\/science.aar6404arXiv:https:\/\/science.sciencemag.org\/content\/ 362\/6419\/1140.full.pdf 10.1126\/science.aar6404arXiv:https: David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, et\u00a0al. 2018. A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science 362, 6419 (2018), 1140\u20131144. https:\/\/doi.org\/10.1126\/science.aar6404arXiv:https:\/\/science.sciencemag.org\/content\/ 362\/6419\/1140.full.pdf"},{"key":"e_1_2_1_65_1","volume-title":"Hannay","author":"Sj\u00f8berg Dag I. K.","year":"2008","unstructured":"Dag I. K. Sj\u00f8berg , Tore Dyb\u00e5 , Bente C. D. Anda , and Jo E . Hannay . 2008 . Building theories in software engineering. In Guide to Advanced Empirical Software Engineering. Springer , 312\u2013336. Dag I. K. Sj\u00f8berg, Tore Dyb\u00e5, Bente C. D. Anda, and Jo E. Hannay. 2008. Building theories in software engineering. In Guide to Advanced Empirical Software Engineering. Springer, 312\u2013336."},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377325.3377491"},{"key":"e_1_2_1_67_1","volume-title":"Retrieved","author":"Dan","year":"2021","unstructured":"Dan \u201c Artosis\u201d Stemkoski. 2019. AlphaStar\u2014Analysis by Artosis . Retrieved June 19, 2021 from https:\/\/www.youtube.com\/watch?v=_YWmU-E2WFc. Dan \u201cArtosis\u201d Stemkoski. 2019. AlphaStar\u2014Analysis by Artosis. Retrieved June 19, 2021 from https:\/\/www.youtube.com\/watch?v=_YWmU-E2WFc."},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2009.03.004"},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1016\/0959-4752(94)90003-5"},{"key":"e_1_2_1_70_1","volume-title":"Retrieved","author":"Community The","year":"2019","unstructured":"The StarCraft II Community . 2019 . Tutorials\u2014Sc2MapsterWiki . Retrieved June 19, 2021 from https:\/\/sc2mapster.gamepedia.com\/Tutorials. The StarCraft II Community. 2019. Tutorials\u2014Sc2MapsterWiki. Retrieved June 19, 2021 from https:\/\/sc2mapster.gamepedia.com\/Tutorials."},{"key":"e_1_2_1_71_1","doi-asserted-by":"crossref","unstructured":"Yuchi Tian Kexin Pei Suman Jana and Baishakhi Ray. 2017. DeepTest: Automated testing of deep-neural-network-driven autonomous cars. arXiv:cs.SE\/1708.08559.  Yuchi Tian Kexin Pei Suman Jana and Baishakhi Ray. 2017. DeepTest: Automated testing of deep-neural-network-driven autonomous cars. arXiv:cs.SE\/1708.08559.","DOI":"10.1145\/3180155.3180220"},{"key":"e_1_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173590"},{"key":"e_1_2_1_74_1","volume-title":"DeepMind. Retrieved","author":"Vinyals Oriol","year":"2017","unstructured":"Oriol Vinyals . 2017 . DeepMind and Blizzard open StarCraft II as an AI research environment . DeepMind. Retrieved June 19, 2021 from https:\/\/deepmind.com\/blog\/deepmind-and-blizzard-open-starcraft-ii-ai-research-environment\/. Oriol Vinyals. 2017. DeepMind and Blizzard open StarCraft II as an AI research environment. DeepMind. Retrieved June 19, 2021 from https:\/\/deepmind.com\/blog\/deepmind-and-blizzard-open-starcraft-ii-ai-research-environment\/."},{"key":"e_1_2_1_75_1","volume-title":"Retrieved","author":"Vinyals Oriol","year":"2019","unstructured":"Oriol Vinyals and David Silver . 2019 . AlphaStar: Mastering the Real-Time Strategy Game StarCraft II . Retrieved June 19, 2021 from https:\/\/deepmind.com\/blog\/article\/alphastar-mastering-real-time-strategy-game-starcraft-ii. Oriol Vinyals and David Silver. 2019. AlphaStar: Mastering the Real-Time Strategy Game StarCraft II. Retrieved June 19, 2021 from https:\/\/deepmind.com\/blog\/article\/alphastar-mastering-real-time-strategy-game-starcraft-ii."},{"key":"e_1_2_1_76_1","volume-title":"Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI\u201919)","author":"Wang Danding","unstructured":"Danding Wang , Qian Yang , Ashraf Abdul , and Brian Y. Lim . 2019. Designing theory-driven user-centric explainable ai . In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI\u201919) . Danding Wang, Qian Yang, Ashraf Abdul, and Brian Y. Lim. 2019. Designing theory-driven user-centric explainable ai. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI\u201919)."},{"key":"e_1_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300911"},{"key":"e_1_2_1_78_1","unstructured":"Franz Emanuel Weinert and Rainer H. Kluwe (Eds.). 1987. Metacognition Motivation and Understanding. Psychology of Education and Instruction Series. Psychology Press.  Franz Emanuel Weinert and Rainer H. Kluwe (Eds.). 1987. Metacognition Motivation and Understanding. Psychology of Education and Instruction Series. Psychology Press."},{"key":"e_1_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.5555\/330775"},{"key":"e_1_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174230"},{"key":"e_1_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376301"}],"container-title":["ACM Transactions on Interactive Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3453173","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3453173","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3453173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:28:39Z","timestamp":1750195719000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3453173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,3]]},"references-count":78,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2021,12,31]]}},"alternative-id":["10.1145\/3453173"],"URL":"https:\/\/doi.org\/10.1145\/3453173","relation":{},"ISSN":["2160-6455","2160-6463"],"issn-type":[{"value":"2160-6455","type":"print"},{"value":"2160-6463","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,3]]},"assertion":[{"value":"2020-08-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}