{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T20:05:19Z","timestamp":1776110719613,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1145\/3565472.3595611","type":"proceedings-article","created":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T14:31:07Z","timestamp":1687185067000},"page":"146-155","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Improving Proactive Dialog Agents Using Socially-Aware Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7400-2584","authenticated-orcid":false,"given":"Matthias","family":"Kraus","sequence":"first","affiliation":[{"name":"Universit\u00e4t Augsburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5383-711X","authenticated-orcid":false,"given":"Nicolas","family":"Wagner","sequence":"additional","affiliation":[{"name":"Ulm University, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5607-5824","authenticated-orcid":false,"given":"Ron","family":"Riekenbrauck","sequence":"additional","affiliation":[{"name":"Ulm University, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4531-0662","authenticated-orcid":false,"given":"Wolfgang","family":"Minker","sequence":"additional","affiliation":[{"name":"University of Ulm, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,6,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/2906831.2906844"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1067860.1067867"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2020.1841438"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939746"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1719970.1719980"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218194007003033"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1177\/0018720814547570"},{"key":"e_1_3_2_1_8_1","volume-title":"Lumiere project: Bayesian reasoning for automated assistance","author":"Horvitz Eric","year":"1998","unstructured":"Eric Horvitz. 1998. Lumiere project: Bayesian reasoning for automated assistance. Decision Theory & Adaptive Systems Group, Microsoft Research. Microsoft Corp. Redmond, WA (1998)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/302979.303030"},{"key":"e_1_3_2_1_10_1","volume-title":"Proc. of HCI International.","author":"Isbell L","year":"2005","unstructured":"Charles\u00a0L Isbell and Jeffrey\u00a0S Pierce. 2005. An IP continuum for adaptive interface design. In Proc. of HCI International."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3267851.3267916"},{"key":"e_1_3_2_1_12_1","volume-title":"Technikaffinit\u00e4t erfassen\u2013der Fragebogen TA-EG. Der Mensch im Mittelpunkt technischer Systeme 8","author":"Karrer Katja","year":"2009","unstructured":"Katja Karrer, Charlotte Glaser, Caroline Clemens, and Carmen Bruder. 2009. Technikaffinit\u00e4t erfassen\u2013der Fragebogen TA-EG. Der Mensch im Mittelpunkt technischer Systeme 8 (2009), 196\u2013201."},{"key":"e_1_3_2_1_13_1","volume-title":"Adam: A Method for Stochastic Optimization. arXiv e-prints","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. arXiv e-prints (2014), arXiv\u20131412."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Matthias Kraus Ron Riekenbrauck and Wolfgang Minker. 2023. Development of a Trust-Aware User Simulator for Statistical Proactive Dialog Modeling in Human-AI Teams. arxiv:2304.11913\u00a0[cs.AI]","DOI":"10.1145\/3563359.3597403"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3103893"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340631.3394840"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479906"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC","author":"Kraus Matthias","year":"2022","unstructured":"Matthias Kraus, Nicolas Wagner, and Wolfgang Minker. 2022. ProDial \u2013 An Annotated Proactive Dialogue Act Corpus for Conversational Assistants using Crowdsourcing. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2022). ELRA."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503252.3531294"},{"key":"e_1_3_2_1_20_1","volume-title":"On information and sufficiency. The annals of mathematical statistics 22, 1","author":"Kullback Solomon","year":"1951","unstructured":"Solomon Kullback and Richard\u00a0A Leibler. 1951. On information and sufficiency. The annals of mathematical statistics 22, 1 (1951), 79\u201386."},{"key":"e_1_3_2_1_21_1","volume-title":"self-confidence, and operators","author":"Lee D","year":"1994","unstructured":"John\u00a0D Lee and Neville Moray. 1994. Trust, self-confidence, and operators\u2019 adaptation to automation. International journal of human-computer studies 40, 1 (1994), 153\u2013184."},{"key":"e_1_3_2_1_22_1","volume-title":"Trust in automation: Designing for appropriate reliance. Human factors 46, 1","author":"Lee D","year":"2004","unstructured":"John\u00a0D Lee and Katrina\u00a0A See. 2004. Trust in automation: Designing for appropriate reliance. Human factors 46, 1 (2004), 50\u201380."},{"key":"e_1_3_2_1_23_1","volume-title":"LONDIAL 2008 the 12th Workshop on the Semantics and Pragmatics of Dialogue. 149","author":"Lemon Oliver","year":"2008","unstructured":"Oliver Lemon. 2008. Adaptive Natural Language Generation in Dialogue using Reinforcement Learning. In LONDIAL 2008 the 12th Workshop on the Semantics and Pragmatics of Dialogue. 149."},{"key":"e_1_3_2_1_24_1","volume-title":"11th australasian conference on information systems, Vol.\u00a053. Citeseer, 6\u20138.","author":"Madsen Maria","unstructured":"Maria Madsen and Shirley Gregor. 2000. Measuring human-computer trust. In 11th australasian conference on information systems, Vol.\u00a053. Citeseer, 6\u20138."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-6494.1992.tb00970.x"},{"key":"e_1_3_2_1_26_1","volume-title":"Leaving the Butler Behind: The Future of Role Reproduction in CUI. In CUI 2021-3rd Conference on Conversational User Interfaces. 1\u20134.","author":"McMillan Donald","year":"2021","unstructured":"Donald McMillan and Razan Jaber. 2021. Leaving the Butler Behind: The Future of Role Reproduction in CUI. In CUI 2021-3rd Conference on Conversational User Interfaces. 1\u20134."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02176-3"},{"key":"e_1_3_2_1_28_1","volume-title":"I trust it, but I don\u2019t know why: Effects of implicit attitudes toward automation on trust in an automated system. Human factors 55, 3","author":"Merritt M","year":"2013","unstructured":"Stephanie\u00a0M Merritt, Heather Heimbaugh, Jennifer LaChapell, and Deborah Lee. 2013. I trust it, but I don\u2019t know why: Effects of implicit attitudes toward automation on trust in an automated system. Human factors 55, 3 (2013), 520\u2013534."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3432193"},{"key":"e_1_3_2_1_30_1","volume-title":"Human-level control through deep reinforcement learning. nature 518, 7540","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei\u00a0A Rusu, Joel Veness, Marc\u00a0G Bellemare, Alex Graves, Martin Riedmiller, Andreas\u00a0K Fidjeland, Georg Ostrovski, 2015. Human-level control through deep reinforcement learning. nature 518, 7540 (2015), 529\u2013533."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1080\/00140139408964957"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1080\/00140139608964474"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 2nd European and the 5th Nordic Symposium on Multimodal Communication","author":"Nothdurft Florian","year":"2015","unstructured":"Florian Nothdurft, Stefan Ultes, and Wolfgang Minker. 2015. Finding appropriate interaction strategies for proactive dialogue systems-an open quest. In Proceedings of the 2nd European and the 5th Nordic Symposium on Multimodal Communication, August 6-8, 2014, Tartu, Estonia. Link\u00f6ping University Electronic Press, 73\u201380."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383652.3423877"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300328"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/263721"},{"key":"e_1_3_2_1_37_1","volume-title":"Reinforcement learning for adaptive dialogue systems: a data-driven methodology for dialogue management and natural language generation","author":"Rieser Verena","unstructured":"Verena Rieser and Oliver Lemon. 2011. Reinforcement learning for adaptive dialogue systems: a data-driven methodology for dialogue management and natural language generation. Springer Science & Business Media."},{"key":"e_1_3_2_1_38_1","volume-title":"symposium on robot and human interactive communication (ro-man). IEEE, 378\u2013384","author":"Ritschel Hannes","year":"2017","unstructured":"Hannes Ritschel, Tobias Baur, and Elisabeth Andr\u00e9. 2017. Adapting a robot\u2019s linguistic style based on socially-aware reinforcement learning. In 2017 26th ieee international symposium on robot and human interactive communication (ro-man). IEEE, 378\u2013384."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2016.2617341"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1177\/0018720816634228"},{"key":"e_1_3_2_1_42_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton S","unstructured":"Richard\u00a0S Sutton and Andrew\u00a0G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_1_43_1","volume-title":"Target-guided open-domain conversation. arXiv preprint arXiv:1905.11553","author":"Tang Jianheng","year":"2019","unstructured":"Jianheng Tang, Tiancheng Zhao, Chenyan Xiong, Xiaodan Liang, Eric\u00a0P Xing, and Zhiting Hu. 2019. Target-guided open-domain conversation. arXiv preprint arXiv:1905.11553 (2019)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5902"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-4649"},{"key":"e_1_3_2_1_46_1","volume-title":"Proactive human-machine conversation with explicit conversation goals. arXiv preprint arXiv:1906.05572","author":"Wu Wenquan","year":"2019","unstructured":"Wenquan Wu, Zhen Guo, Xiangyang Zhou, Hua Wu, Xiyuan Zhang, Rongzhong Lian, and Haifeng Wang. 2019. Proactive human-machine conversation with explicit conversation goals. arXiv preprint arXiv:1906.05572 (2019)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6474"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218213012500042"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2225812"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463011"}],"event":{"name":"UMAP '23: 31st ACM Conference on User Modeling, Adaptation and Personalization","location":"Limassol Cyprus","acronym":"UMAP '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3565472.3595611","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3565472.3595611","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:50:59Z","timestamp":1750182659000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3565472.3595611"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":49,"alternative-id":["10.1145\/3565472.3595611","10.1145\/3565472"],"URL":"https:\/\/doi.org\/10.1145\/3565472.3595611","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]},"assertion":[{"value":"2023-06-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}