{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T02:40:00Z","timestamp":1792809600224,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T00:00:00Z","timestamp":1678665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Army Research Laboratory","award":["ARL DCIST CRA W911NF-17-2-0181"],"award-info":[{"award-number":["ARL DCIST CRA W911NF-17-2-0181"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,3,13]]},"DOI":"10.1145\/3568294.3580147","type":"proceedings-article","created":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T18:51:31Z","timestamp":1678301491000},"page":"557-560","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Transparent Value Alignment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4247-3004","authenticated-orcid":false,"given":"Lindsay","family":"Sanneman","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1338-8107","authenticated-orcid":false,"given":"Julie","family":"Shah","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,3,13]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems. 1203--1207","author":"Amir Ofra","year":"2018","unstructured":"Ofra Amir, Finale Doshi-Velez, and David Sarne. 2018. Agent strategy summarization. In Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems. 1203--1207."},{"key":"e_1_3_2_2_2_1","volume-title":"Concrete problems in AI safety. arXiv preprint arXiv:1606.06565","author":"Amodei Dario","year":"2016","unstructured":"Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, and Dan Man\u00e9. 2016. Concrete problems in AI safety. arXiv preprint arXiv:1606.06565 (2016)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Andrew Anderson et al. 2019. Explaining reinforcement learning to mere mortals: An empirical study. arXiv preprint arXiv:1903.09708 (2019).","DOI":"10.24963\/ijcai.2019\/184"},{"key":"e_1_3_2_2_4_1","volume-title":"A survey of robot learning from demonstration. Robotics and autonomous systems","author":"Argall Brenna D","year":"2009","unstructured":"Brenna D Argall, Sonia Chernova, Manuela Veloso, and Brett Browning. 2009. A survey of robot learning from demonstration. Robotics and autonomous systems, Vol. 57, 5 (2009), 469--483."},{"key":"e_1_3_2_2_5_1","volume-title":"Asking easy questions: A user-friendly approach to active reward learning. arXiv preprint arXiv:1910.04365","author":"Biyik Erdem","year":"2019","unstructured":"Erdem Biyik, Malayandi Palan, Nicholas C Landolfi, Dylan P Losey, and Dorsa Sadigh. 2019. Asking easy questions: A user-friendly approach to active reward learning. arXiv preprint arXiv:1910.04365 (2019)."},{"key":"e_1_3_2_2_6_1","volume-title":"Conference on Robot Learning. PMLR, 796--805","author":"Bobu Andreea","year":"2018","unstructured":"Andreea Bobu, Andrea Bajcsy, Jaime F Fisac, and Anca D Dragan. 2018. Learning under misspecified objective spaces. In Conference on Robot Learning. PMLR, 796--805."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3434073.3444667"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/3523760.3523784"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017749"},{"key":"e_1_3_2_2_10_1","volume-title":"International Conference on Machine Learning. PMLR, 1105--1115","author":"Brown Daniel S","year":"2021","unstructured":"Daniel S Brown, Jordan Schneider, Anca Dragan, and Scott Niekum. 2021. Value alignment verification. In International Conference on Machine Learning. PMLR, 1105--1115."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39360-0_30"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460854"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3434073.3444657"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2013.6483603"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278736"},{"key":"e_1_3_2_2_16_1","volume-title":"Robotics Research","author":"Fisac Jaime F","unstructured":"Jaime F Fisac, Monica A Gates, Jessica B Hamrick, Chang Liu, Dylan Hadfield-Menell, Malayandi Palaniappan, Dhruv Malik, S Shankar Sastry, Thomas L Griffiths, and Anca D Dragan. 2020. Pragmatic-pedagogic value alignment. In Robotics Research. Springer, 49--57."},{"key":"e_1_3_2_2_17_1","volume-title":"Value-sensitive design. interactions","author":"Friedman Batya","year":"1996","unstructured":"Batya Friedman. 1996. Value-sensitive design. interactions, Vol. 3, 6 (1996), 16--23."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Kevin A Gluck and John E Laird. 2018. Interactive task learning: Humans robots and agents acquiring new tasks through natural interactions. 169--191.","DOI":"10.7551\/mitpress\/11956.001.0001"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v40i2.2850"},{"key":"e_1_3_2_2_20_1","volume-title":"Cooperative inverse reinforcement learning. arXiv preprint arXiv:1606.03137","author":"Hadfield-Menell Dylan","year":"2016","unstructured":"Dylan Hadfield-Menell, Anca Dragan, Pieter Abbeel, and Stuart Russell. 2016. Cooperative inverse reinforcement learning. arXiv preprint arXiv:1606.03137 (2016)."},{"key":"e_1_3_2_2_21_1","volume-title":"Inverse reward design. arXiv preprint arXiv:1711.02827","author":"Hadfield-Menell Dylan","year":"2017","unstructured":"Dylan Hadfield-Menell, Smitha Milli, Pieter Abbeel, Stuart Russell, and Anca Dragan. 2017. Inverse reward design. arXiv preprint arXiv:1711.02827 (2017)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9771-0"},{"key":"e_1_3_2_2_23_1","volume-title":"IJCAI\/ECAI Workshop on Explainable Artificial Intelligence.","author":"Zoe","unstructured":"Zoe Juozapaitis et al. 2019. Explainable reinforcement learning via reward decomposition. In IJCAI\/ECAI Workshop on Explainable Artificial Intelligence."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i11.21488"},{"key":"e_1_3_2_2_25_1","volume-title":"The bayesian case model: A generative approach for case-based reasoning and prototype classification. Advances in neural information processing systems","author":"Kim Been","year":"2014","unstructured":"Been Kim, Cynthia Rudin, and Julie A Shah. 2014. The bayesian case model: A generative approach for case-based reasoning and prototype classification. Advances in neural information processing systems, Vol. 27 (2014)."},{"key":"e_1_3_2_2_26_1","volume-title":"Human-in-the-Loop Learning of Interpretable and Intuitive Representations. In ICML Workshop on Human Interpretability in Machine Learning","author":"Lage Isaac","year":"2020","unstructured":"Isaac Lage and Finale Doshi-Velez. 2020. Human-in-the-Loop Learning of Interpretable and Intuitive Representations. In ICML Workshop on Human Interpretability in Machine Learning, Vienna, Austria."},{"key":"e_1_3_2_2_27_1","volume-title":"Exploring computational user models for agent policy summarization. arXiv preprint arXiv:1905.13271","author":"Lage Isaac","year":"2019","unstructured":"Isaac Lage, Daphna Lifschitz, Finale Doshi-Velez, and Ofra Amir. 2019. Exploring computational user models for agent policy summarization. arXiv preprint arXiv:1905.13271 (2019)."},{"key":"e_1_3_2_2_28_1","volume-title":"Reasoning about Counterfactuals to Improve Human Inverse Reinforcement Learning. arXiv preprint arXiv:2203.01855","author":"Lee Michael S","year":"2022","unstructured":"Michael S Lee, Henny Admoni, and Reid Simmons. 2022. Reasoning about Counterfactuals to Improve Human Inverse Reinforcement Learning. arXiv preprint arXiv:2203.01855 (2022)."},{"key":"e_1_3_2_2_29_1","volume-title":"Active inverse reward design. arXiv preprint arXiv:1809.03060","author":"Mindermann S\u00f6ren","year":"2018","unstructured":"S\u00f6ren Mindermann, Rohin Shah, Adam Gleave, and Dylan Hadfield-Menell. 2018. Active inverse reward design. arXiv preprint arXiv:1809.03060 (2018)."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/153571.255960"},{"key":"e_1_3_2_2_31_1","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"Ng Andrew Y","year":"2000","unstructured":"Andrew Y Ng, Stuart J Russell, et al. 2000. Algorithms for inverse reinforcement learning.. In Icml, Vol. 1. 2.","journal-title":"Icml"},{"key":"e_1_3_2_2_32_1","volume-title":"The effects of reward misspecification: Mapping and mitigating misaligned models. arXiv preprint arXiv:2201.03544","author":"Pan Alexander","year":"2022","unstructured":"Alexander Pan, Kush Bhatia, and Jacob Steinhardt. 2022. The effects of reward misspecification: Mapping and mitigating misaligned models. arXiv preprint arXiv:2201.03544 (2022)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3189441"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2022.2081282"},{"key":"e_1_3_2_2_36_1","unstructured":"Burr Settles. 2009. Active learning literature survey. (2009)."},{"key":"e_1_3_2_2_37_1","volume-title":"Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Black Box Simulators. arXiv preprint arXiv:2002.01080","author":"Sarath Sreedharan","year":"2020","unstructured":"Sarath Sreedharan et al. 2020. Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Black Box Simulators. arXiv preprint arXiv:2002.01080 (2020)."},{"key":"e_1_3_2_2_38_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S","unstructured":"Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2019.8673104"}],"event":{"name":"HRI '23: ACM\/IEEE International Conference on Human-Robot Interaction","location":"Stockholm Sweden","acronym":"HRI '23","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Companion of the 2023 ACM\/IEEE International Conference on Human-Robot Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3568294.3580147","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3568294.3580147","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T22:56:58Z","timestamp":1755817018000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3568294.3580147"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,13]]},"references-count":39,"alternative-id":["10.1145\/3568294.3580147","10.1145\/3568294"],"URL":"https:\/\/doi.org\/10.1145\/3568294.3580147","relation":{},"subject":[],"published":{"date-parts":[[2023,3,13]]},"assertion":[{"value":"2023-03-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}