{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T11:03:02Z","timestamp":1781002982480,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":119,"publisher":"ACM","funder":[{"name":"ANR","award":["ANR-24-CE33-7994-01"],"award-info":[{"award-number":["ANR-24-CE33-7994-01"]}]},{"name":"ERC","award":["101141916"],"award-info":[{"award-number":["101141916"]}]},{"name":"Research Council of Finland, FCAI","award":["328400"],"award-info":[{"award-number":["328400"]}]},{"name":"Research Council of Finland, FCAI","award":["345604"],"award-info":[{"award-number":["345604"]}]},{"name":"Research Council of Finland, FCAI","award":["341763"],"award-info":[{"award-number":["341763"]}]},{"name":"Research Council of Finland, Subjective Functions","award":["357578"],"award-info":[{"award-number":["357578"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3772318.3791819","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:12:21Z","timestamp":1776053541000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A decision-theoretic representation of assistive interfaces"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3272-9176","authenticated-orcid":false,"given":"Julien","family":"Gori","sequence":"first","affiliation":[{"name":"ISIR, Institut des Syst\u00e8mes Intelligents et de Robotique, CNRS, Inserm, Sorbonne Universit\u00e9, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0567-2637","authenticated-orcid":false,"given":"Aurelien","family":"Nioche","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom and Aalto University, Espoo, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4175-340X","authenticated-orcid":false,"given":"Christoph A.","family":"Johns","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Aarhus University, Aarhus, Denmark and Applied Artificial Intelligence, University of Oldenburg, Oldenburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2498-7837","authenticated-orcid":false,"given":"Antti","family":"Oulasvirta","sequence":"additional","affiliation":[{"name":"Department of Information and Communications Engineering, School of Electrical Engineering, Aalto University, Espoo, Finland and ELLIS Institute Finland, Espoo, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Stefano\u00a0V Albrecht and Peter Stone. 2018. Autonomous agents modelling other agents: A comprehensive survey and open problems. Artificial Intelligence 258 (2018) 66\u201395.","DOI":"10.1016\/j.artint.2018.01.002"},{"key":"e_1_3_3_2_3_2","unstructured":"Christopher Amato. 2024. An introduction to centralized training for decentralized execution in cooperative multi-agent reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.03052 (2024)."},{"key":"e_1_3_3_2_4_2","volume-title":"Submitted to The Fourteenth International Conference on Learning Representations","year":"2025","unstructured":"Anonymous. 2025. Designing Observation and Action Models for Efficient Reinforcement Learning with LLMs. In Submitted to The Fourteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=v1tTJN2svr under review."},{"key":"e_1_3_3_2_5_2","unstructured":"Stuart Armstrong and S\u00f6ren Mindermann. 2018. Occam\u2019s razor is insufficient to infer the preferences of irrational agents. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/1449715.1449724"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545651"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Daniel\u00a0S Bernstein Robert Givan Neil Immerman and Shlomo Zilberstein. 2002. The complexity of decentralized control of Markov decision processes. Mathematics of operations research 27 4 (2002) 819\u2013840.","DOI":"10.1287\/moor.27.4.819.297"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/985692.985758"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979180"},{"key":"e_1_3_3_2_11_2","first-page":"195","volume-title":"TARK","author":"Boutilier Craig","year":"1996","unstructured":"Craig Boutilier. 1996. Planning, learning and coordination in multiagent decision processes. In TARK , Vol.\u00a096. Citeseer, 195\u2013210."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1201\/9781315557380-14"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Peter Brusilovsky. 2001. Adaptive hypermedia. User modeling and user-adapted interaction 11 (2001) 87\u2013110.","DOI":"10.1023\/A:1011143116306"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047276"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"G\u00e9ry Casiez Daniel Vogel Ravin Balakrishnan and Andy Cockburn. 2008. The impact of control-display gain on user performance in pointing tasks. Human\u2013computer interaction 23 3 (2008) 215\u2013250.","DOI":"10.1080\/07370020802278163"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Mustafa\u00a0Mert \u00c7elikok Pierre-Alexandre Murena and Samuel Kaski. 2023. Modeling needs user modeling. Frontiers in Artificial Intelligence 6 (2023) 61.","DOI":"10.3389\/frai.2023.1097891"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5739"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Krishnendu Chatterjee and Laurent Doyen. 2014. Partial-observation stochastic games: How to win when belief fails. ACM Transactions on Computational Logic (TOCL) 15 2 (2014) 1\u201344.","DOI":"10.1145\/2579821"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376701"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445177"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474750"},{"key":"e_1_3_3_2_22_2","unstructured":"Allan Dafoe Edward Hughes Yoram Bachrach Tantum Collins Kevin\u00a0R McKee Joel\u00a0Z Leibo Kate Larson and Thore Graepel. 2020. Open problems in cooperative AI. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2012.08630 (2020)."},{"key":"e_1_3_3_2_23_2","volume-title":"Formal methods for interactive systems","author":"Dix Alan\u00a0John","year":"1991","unstructured":"Alan\u00a0John Dix. 1991. Formal methods for interactive systems. Vol.\u00a016. Academic Press London."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Anca\u00a0D Dragan and Siddhartha\u00a0S Srinivasa. 2013. A policy-blending formalism for shared control. The International Journal of Robotics Research 32 7 (2013) 790\u2013805.","DOI":"10.1177\/0278364913490324"},{"key":"e_1_3_3_2_25_2","unstructured":"Yuqing Du Stas Tiomkin Emre Kiciman Daniel Polani Pieter Abbeel and Anca Dragan. 2020. Ave: Assistance via empowerment. Advances in Neural Information Processing Systems 33 (2020) 4560\u20134571."},{"key":"e_1_3_3_2_26_2","unstructured":"Ayoub Echchahed and Pablo\u00a0Samuel Castro. 2025. A Survey of State Representation Learning for Deep Reinforcement Learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.17518 (2025)."},{"key":"e_1_3_3_2_27_2","unstructured":"Maxim Egorov Zachary\u00a0N Sunberg Edward Balaban Tim\u00a0A Wheeler Jayesh\u00a0K Gupta and Mykel\u00a0J Kochenderfer. 2017. POMDPs. jl: A framework for sequential decision making under uncertainty. Journal of Machine Learning Research 18 26 (2017) 1\u20135."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Umer Farooq and Jonathan Grudin. 2016. Human-computer integration. interactions 23 6 (2016) 26\u201332.","DOI":"10.1145\/3001896"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/800276.810969"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Alan Fern Sriraam Natarajan Kshitij Judah and Prasad Tadepalli. 2014. A decision-theoretic model of assistance. Journal of Artificial Intelligence Research 50 (2014) 71\u2013104.","DOI":"10.1613\/jair.4213"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Gerhard Fischer. 1989. Human-computer interaction software: lessons learned challenges ahead. IEEE Software 6 1 (1989) 44\u201352.","DOI":"10.1109\/52.16901"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Gerhard Fischer. 2001. User modeling in human\u2013computer interaction. User modeling and user-adapted interaction 11 1 (2001) 65\u201386.","DOI":"10.1023\/A:1011145532042"},{"key":"e_1_3_3_2_33_2","volume-title":"Human engineering for an effective air-navigation and traffic-control system, and appendixes 1 thru 3","author":"Fitts Paul\u00a0M","year":"1951","unstructured":"Paul\u00a0M Fitts, MS Viteles, NL Barr, DR Brimhall, Glen Finch, Eric Gardner, WF Grether, WE Kellum, and SS Stevens. 1951. Human engineering for an effective air-navigation and traffic-control system, and appendixes 1 thru 3. Technical Report. Ohio State Univ Research Foundation Columbus."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44566-8_6"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/964442.964461"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Krzysztof\u00a0Z Gajos Daniel\u00a0S Weld and Jacob\u00a0O Wobbrock. 2010. Automatically generating personalized user interfaces with Supple. Artificial Intelligence 174 12-13 (2010) 910\u2013950.","DOI":"10.1016\/j.artint.2010.05.005"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Samuel\u00a0J Gershman Eric\u00a0J Horvitz and Joshua\u00a0B Tenenbaum. 2015. Computational rationality: A converging paradigm for intelligence in brains minds and machines. Science 349 6245 (2015) 273\u2013278.","DOI":"10.1126\/science.aac6076"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"MK Ghosh D McDonald and S Sinha. 2004. Zero-sum stochastic games with partial information. Journal of optimization theory and applications 121 1 (2004) 99\u2013118.","DOI":"10.1023\/B:JOTA.0000026133.56615.cf"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31454-4_35"},{"key":"e_1_3_3_2_40_2","unstructured":"Blandine Ginon. 2014. Mod\u00e8les et outils g\u00e9n\u00e9riques pour mettre en place des syst\u00e8mes d\u2019assistance \u00e9piphytes. Ph.\u00a0D. Dissertation. INSA de Lyon."},{"key":"e_1_3_3_2_41_2","first-page":"9","volume-title":"Proceedings of Graphics Interface 2004","author":"Guiard Yves","year":"2004","unstructured":"Yves Guiard, Renaud Blanch, and Michel Beaudouin-Lafon. 2004. Object pointing: a complement to bitmap pointing in GUIs. In Proceedings of Graphics Interface 2004. Citeseer, 9\u201316."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3585913"},{"key":"e_1_3_3_2_43_2","unstructured":"Dylan Hadfield-Menell Stuart\u00a0J Russell Pieter Abbeel and Anca Dragan. 2016. Cooperative inverse reinforcement learning. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_3_2_44_2","unstructured":"Danijar Hafner Timothy Lillicrap Mohammad Norouzi and Jimmy Ba. 2020. Mastering atari with discrete world models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.02193 (2020)."},{"key":"e_1_3_3_2_45_2","first-page":"709","volume-title":"AAAI","author":"Hansen Eric\u00a0A","year":"2004","unstructured":"Eric\u00a0A Hansen, Daniel\u00a0S Bernstein, and Shlomo Zilberstein. 2004. Dynamic programming for partially observable stochastic games. In AAAI , Vol.\u00a04. 709\u2013715."},{"key":"e_1_3_3_2_46_2","first-page":"1","volume-title":"Alt. Chi. Session at the SIGCHI Conference on human factors in computing systems San Jose, California, USA","author":"Harrison Steve","year":"2007","unstructured":"Steve Harrison, Deborah Tatar, and Phoebe Sengers. 2007. The three paradigms of HCI. In Alt. Chi. Session at the SIGCHI Conference on human factors in computing systems San Jose, California, USA. 1\u201318."},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"crossref","unstructured":"John\u00a0H Holland. 1992. Complex adaptive systems. Daedalus 121 1 (1992) 17\u201330.","DOI":"10.1515\/crll.1992.424.17"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Kristina H\u00f6\u00f6k. 2000. Steps to take before intelligent user interfaces become real. Interacting with computers 12 4 (2000) 409\u2013426.","DOI":"10.1016\/S0953-5438(99)00006-5"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012029"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/302979.303030"},{"key":"e_1_3_3_2_51_2","unstructured":"Eric\u00a0J Horvitz. 2007. Reflections on challenges and promises of mixed-initiative interaction. AI Magazine 28 2 (2007) 3\u20133."},{"key":"e_1_3_3_2_52_2","unstructured":"Ronald\u00a0A Howard. 1960. Dynamic programming and markov processes. (1960)."},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Andrew Howes Richard\u00a0L Lewis and Alonso Vera. 2009. Rational adaptation under task and processing constraints: implications for testing theories of cognition and action. Psychological review 116 4 (2009) 717.","DOI":"10.1037\/a0017187"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"crossref","unstructured":"Andrew Howes Paul\u00a0A Warren George Farmer Wael El-Deredy and Richard\u00a0L Lewis. 2016. Why contextual preference reversals maximize expected value. Psychological review 123 4 (2016) 368.","DOI":"10.1037\/a0039996"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"crossref","unstructured":"PR Innocent. 1982. Towards self-adaptive interface systems. International Journal of Man-Machine Studies 16 3 (1982) 287\u2013299.","DOI":"10.1016\/S0020-7373(82)80063-1"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1201\/9781410615862.ch22"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/1979742.1979888"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"crossref","unstructured":"Shervin Javdani Siddhartha\u00a0S Srinivasa and J\u00a0Andrew Bagnell. 2015. Shared autonomy via hindsight optimization. Robotics science and systems: online proceedings 2015 (2015).","DOI":"10.15607\/RSS.2015.XI.032"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619204"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445483"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","unstructured":"Mayank Kabra Alice\u00a0A. Robie Marta Rivera-Alba Steven Branson and Kristin Branson. 2013. JAABA: interactive machine learning for automatic annotation of animal behavior. Nature Methods 10 1 (Jan. 2013) 64\u201367. 10.1038\/nmeth.2281Publisher: Nature Publishing Group.","DOI":"10.1038\/nmeth.2281"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"crossref","unstructured":"Leslie\u00a0Pack Kaelbling Michael\u00a0L Littman and Anthony\u00a0R Cassandra. 1998. Planning and acting in partially observable stochastic domains. Artificial intelligence 101 1-2 (1998) 99\u2013134.","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1142\/9789814417358_0006"},{"key":"e_1_3_3_2_64_2","unstructured":"Lodewijk Kallenberg. 2011. Markov decision processes. Lecture Notes. University of Leiden 428 (2011)."},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"crossref","unstructured":"Tobias Kaupp Alexei Makarenko and Hugh Durrant-Whyte. 2010. Human\u2013robot communication for collaborative decision making\u2014A probabilistic approach. Robotics and Autonomous Systems 58 5 (2010) 444\u2013456.","DOI":"10.1016\/j.robot.2010.02.003"},{"key":"e_1_3_3_2_66_2","unstructured":"Vojt\u011bch Kova\u0159\u00edk Martin Schmid Neil Burch Michael Bowling and Viliam Lis\u1ef3. 2019. Rethinking formal models of partially observable multiagent decision making. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1906.11110 (2019)."},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.65109\/ZZBH2431"},{"key":"e_1_3_3_2_68_2","volume-title":"Twenty-Second International FLAIRS Conference","author":"Kumar Akshat","year":"2009","unstructured":"Akshat Kumar and Shlomo Zilberstein. 2009. Dynamic programming approximations for partially observable stochastic games. In Twenty-Second International FLAIRS Conference."},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"crossref","unstructured":"Thomas Langerak Sammy Christen Mert Albaba Christoph Gebhardt Christian Holz and Otmar Hilliges. 2024. MARLUI: Multi-Agent Reinforcement Learning for Adaptive Point-and-Click UIs. Proceedings of the ACM on Human-Computer Interaction 8 EICS (2024) 1\u201327.","DOI":"10.1145\/3661147"},{"key":"e_1_3_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376244"},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"crossref","unstructured":"Richard\u00a0L Lewis Andrew Howes and Satinder Singh. 2014. Computational rationality: Linking mechanism and behavior through bounded utility maximization. Topics in cognitive science 6 2 (2014) 279\u2013311.","DOI":"10.1111\/tops.12086"},{"key":"e_1_3_3_2_72_2","doi-asserted-by":"crossref","unstructured":"Joseph\u00a0CR Licklider. 1960. Man-computer symbiosis. IRE transactions on human factors in electronics1 (1960) 4\u201311.","DOI":"10.1109\/THFE2.1960.4503259"},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"crossref","unstructured":"Henry Lieberman. 2009. User interface goals AI opportunities. AI Magazine 30 4 (2009) 16\u201316.","DOI":"10.1609\/aimag.v30i4.2266"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025524"},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173959"},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2556969"},{"key":"e_1_3_3_2_77_2","unstructured":"Yecheng\u00a0Jason Ma William Liang Guanzhi Wang De-An Huang Osbert Bastani Dinesh Jayaraman Yuke Zhu Linxi Fan and Anima Anandkumar. 2023. Eureka: Human-level reward design via coding large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.12931 (2023)."},{"key":"e_1_3_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.5555\/212925.213004"},{"key":"e_1_3_3_2_79_2","doi-asserted-by":"crossref","unstructured":"Todd\u00a0L McKerchar and C\u00a0Renee Renda. 2012. Delay and probability discounting in humans: An overview. The Psychological Record 62 4 (2012) 817\u2013834.","DOI":"10.1007\/BF03395837"},{"key":"e_1_3_3_2_80_2","doi-asserted-by":"crossref","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei\u00a0A Rusu Joel Veness Marc\u00a0G Bellemare Alex Graves Martin Riedmiller Andreas\u00a0K Fidjeland Georg Ostrovski et\u00a0al. 2015. Human-level control through deep reinforcement learning. nature 518 7540 (2015) 529\u2013533.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_3_2_81_2","doi-asserted-by":"crossref","unstructured":"Roderick Murray-Smith Antti Oulasvirta Andrew Howes J\u00f6rg M\u00fcller Aleksi Ikkala Miroslav Bachinski Arthur Fleig Florian Fischer and Markus Klar. 2022. What simulation can do for HCI research. Interactions 29 6 (2022) 48\u201353.","DOI":"10.1145\/3564038"},{"key":"e_1_3_3_2_82_2","unstructured":"Karen Myers Pauline Berry Jim Blythe Ken Conley Melinda Gervasio Deborah\u00a0L McGuinness David Morley Avi Pfeffer Martha Pollack and Milind Tambe. 2007. An intelligent personal assistant for task and time management. AI Magazine 28 2 (2007) 47\u201347."},{"key":"e_1_3_3_2_83_2","doi-asserted-by":"crossref","unstructured":"John\u00a0F Nash\u00a0Jr. 1950. Equilibrium points in n-person games. Proceedings of the national academy of sciences 36 1 (1950) 48\u201349.","DOI":"10.1073\/pnas.36.1.48"},{"key":"e_1_3_3_2_84_2","first-page":"2","volume-title":"Icml","author":"Ng Andrew\u00a0Y","year":"2000","unstructured":"Andrew\u00a0Y Ng, Stuart Russell, et\u00a0al. 2000. Algorithms for inverse reinforcement learning.. In Icml , Vol.\u00a01. 2."},{"key":"e_1_3_3_2_85_2","doi-asserted-by":"publisher","DOI":"10.1145\/191666.191729"},{"key":"e_1_3_3_2_86_2","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2016.7451736"},{"key":"e_1_3_3_2_87_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450696"},{"key":"e_1_3_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1201\/b15703-3"},{"key":"e_1_3_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.5555\/2187809"},{"key":"e_1_3_3_2_90_2","doi-asserted-by":"crossref","unstructured":"Frans\u00a0A Oliehoek and Christopher Amato. 2015. A concise introduction to decentralized POMDPs.","DOI":"10.1007\/978-3-319-28929-8"},{"key":"e_1_3_3_2_91_2","unstructured":"Afshin OroojlooyJadid and Davood Hajinezhad. 2019. A review of cooperative multi-agent deep reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1908.03963 (2019)."},{"key":"e_1_3_3_2_92_2","doi-asserted-by":"crossref","unstructured":"Antti Oulasvirta Niraj\u00a0Ramesh Dayama Morteza Shiripour Maximilian John and Andreas Karrenbauer. 2020. Combinatorial optimization of graphical user interface designs. Proc. IEEE 108 3 (2020) 434\u2013464.","DOI":"10.1109\/JPROC.2020.2969687"},{"key":"e_1_3_3_2_93_2","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198799603.001.0001"},{"key":"e_1_3_3_2_94_2","unstructured":"Alexander Pan Kush Bhatia and Jacob Steinhardt. 2022. The effects of reward misspecification: Mapping and mitigating misaligned models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2201.03544 (2022)."},{"key":"e_1_3_3_2_95_2","doi-asserted-by":"crossref","unstructured":"Liviu Panait and Sean Luke. 2005. Cooperative multi-agent learning: The state of the art. Autonomous agents and multi-agent systems 11 3 (2005) 387\u2013434.","DOI":"10.1007\/s10458-005-2631-2"},{"key":"e_1_3_3_2_96_2","doi-asserted-by":"crossref","unstructured":"Simon Parsons and Michael Wooldridge. 2002. Game theory and decision theory in multi-agent systems. Autonomous Agents and Multi-Agent Systems 5 3 (2002) 243\u2013254.","DOI":"10.1023\/A:1015575522401"},{"key":"e_1_3_3_2_97_2","first-page":"71","volume-title":"Proceedings of InterSymp-1997: The 9th International Conference on Systems Research, Informatics and Cybernetics: Baden-Baden, Germany","author":"Pohl Jens\u00a0G","year":"1997","unstructured":"Jens\u00a0G Pohl. 1997. Human-Computer Partnership in Decision-Support Systems: Some Design Guidelines. In Proceedings of InterSymp-1997: The 9th International Conference on Systems Research, Informatics and Cybernetics: Baden-Baden, Germany. 71."},{"key":"e_1_3_3_2_98_2","doi-asserted-by":"publisher","DOI":"10.5555\/211382.211411"},{"key":"e_1_3_3_2_99_2","volume-title":"Markov decision processes: discrete stochastic dynamic programming","author":"Puterman Martin\u00a0L","year":"2014","unstructured":"Martin\u00a0L Puterman. 2014. Markov decision processes: discrete stochastic dynamic programming. John Wiley & Sons."},{"key":"e_1_3_3_2_100_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939850"},{"key":"e_1_3_3_2_101_2","doi-asserted-by":"crossref","unstructured":"Yvonne Rogers. 2004. New theoretical approaches for human-computer interaction. Annual review of information science and technology 38 1 (2004) 87\u2013143.","DOI":"10.1002\/aris.1440380103"},{"key":"e_1_3_3_2_102_2","doi-asserted-by":"crossref","unstructured":"Silvia Schiaffino and Anal\u0131a Amandi. 2004. User\u2013interface agent interaction: personalization issues. International Journal of Human-Computer Studies 60 1 (2004) 129\u2013148.","DOI":"10.1016\/j.ijhcs.2003.09.003"},{"key":"e_1_3_3_2_103_2","unstructured":"Rohin Shah Pedro Freire Neel Alex Rachel Freedman Dmitrii Krasheninnikov Lawrence Chan Michael\u00a0D Dennis Pieter Abbeel Anca Dragan and Stuart Russell. 2020. Benefits of assistance over reward learning. (2020)."},{"key":"e_1_3_3_2_104_2","doi-asserted-by":"crossref","unstructured":"Ben Shneiderman and Pattie Maes. 1997. Direct manipulation vs. interface agents. interactions 4 6 (1997) 42\u201361.","DOI":"10.1145\/267505.267514"},{"key":"e_1_3_3_2_105_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811654"},{"key":"e_1_3_3_2_106_2","doi-asserted-by":"crossref","unstructured":"David Silver Satinder Singh Doina Precup and Richard\u00a0S Sutton. 2021. Reward is enough. Artificial Intelligence (2021) 103535.","DOI":"10.1016\/j.artint.2021.103535"},{"key":"e_1_3_3_2_107_2","doi-asserted-by":"crossref","unstructured":"Aleksandrs Slivkins et\u00a0al. 2019. Introduction to multi-armed bandits. Foundations and Trends\u00ae in Machine Learning 12 1-2 (2019) 1\u2013286.","DOI":"10.1561\/2200000068"},{"key":"e_1_3_3_2_108_2","doi-asserted-by":"crossref","unstructured":"Eilon Solan and Nicolas Vieille. 2015. Stochastic games. Proceedings of the National Academy of Sciences 112 45 (2015) 13743\u201313746.","DOI":"10.1073\/pnas.1513508112"},{"key":"e_1_3_3_2_109_2","doi-asserted-by":"crossref","unstructured":"Constantine Stephanidis Gavriel Salvendy Margherita Antona Jessie\u00a0YC Chen Jianming Dong Vincent\u00a0G Duffy Xiaowen Fang Cali Fidopiastis Gino Fragomeni Limin\u00a0Paul Fu et\u00a0al. 2019. Seven HCI grand challenges. International Journal of Human\u2013Computer Interaction 35 14 (2019) 1229\u20131269.","DOI":"10.1080\/10447318.2019.1619259"},{"key":"e_1_3_3_2_110_2","doi-asserted-by":"crossref","unstructured":"Constantine Stephanidis Gavriel Salvendy Margherita Antona Vincent\u00a0G Duffy Qin Gao Waldemar Karwowski Shin\u2019ichi Konomi Fiona Nah Stavroula Ntoa Pei-Luen\u00a0Patrick Rau et\u00a0al. 2025. Seven HCI grand challenges revisited: Five-year progress. International Journal of Human\u2013Computer Interaction (2025) 1\u201349.","DOI":"10.1080\/10447318.2025.2450411"},{"key":"e_1_3_3_2_111_2","doi-asserted-by":"publisher","DOI":"10.5555\/551283"},{"key":"e_1_3_3_2_112_2","unstructured":"J Terry Benjamin Black Nathaniel Grammel Mario Jayakumar Ananth Hari Ryan Sullivan Luis\u00a0S Santos Clemens Dieffendahl Caroline Horsch Rodrigo Perez-Vicente et\u00a0al. 2021. Pettingzoo: Gym for multi-agent reinforcement learning. Advances in Neural Information Processing Systems 34 (2021) 15032\u201315043."},{"key":"e_1_3_3_2_113_2","unstructured":"Justin\u00a0K Terry Nathaniel Grammel Benjamin Black Ananth Hari Caroline Horsch and Luis Santos. 2020. Agent Environment Cycle Games. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.13051 (2020)."},{"key":"e_1_3_3_2_114_2","doi-asserted-by":"crossref","unstructured":"Loren\u00a0G Terveen. 1995. Overview of human-computer collaboration. Knowledge-Based Systems 8 2-3 (1995) 67\u201381.","DOI":"10.1016\/0950-7051(95)98369-H"},{"key":"e_1_3_3_2_115_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445497"},{"key":"e_1_3_3_2_116_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377325.3377500"},{"key":"e_1_3_3_2_117_2","doi-asserted-by":"crossref","unstructured":"Matthew\u00a0M Walsh Kevin\u00a0A Gluck Glenn Gunzelmann Tiffany Jastrzembski and Michael Krusmark. 2018. Evaluating the theoretic adequacy and applied potential of computational models of the spacing effect. Cognitive science 42 (2018) 644\u2013691.","DOI":"10.1111\/cogs.12602"},{"key":"e_1_3_3_2_118_2","unstructured":"Bernard Widrow and Samuel\u00a0D Stearns. 1985. Adaptive signal processing."},{"key":"e_1_3_3_2_119_2","doi-asserted-by":"crossref","unstructured":"Jacob\u00a0O Wobbrock Shaun\u00a0K Kane Krzysztof\u00a0Z Gajos Susumu Harada and Jon Froehlich. 2011. Ability-based design: Concept principles and examples. ACM Transactions on Accessible Computing (TACCESS) 3 3 (2011) 1\u201327.","DOI":"10.1145\/1952383.1952384"},{"key":"e_1_3_3_2_120_2","doi-asserted-by":"crossref","unstructured":"Kaiqing Zhang Zhuoran Yang and Tamer Ba\u015far. 2021. Multi-agent reinforcement learning: A selective overview of theories and algorithms. Handbook of Reinforcement Learning and Control (2021) 321\u2013384.","DOI":"10.1007\/978-3-030-60990-0_12"}],"event":{"name":"CHI 2026: CHI Conference on Human Factors in Computing Systems","location":"Barcelona Spain","acronym":"CHI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772318.3791819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T10:39:06Z","timestamp":1781001546000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772318.3791819"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":119,"alternative-id":["10.1145\/3772318.3791819","10.1145\/3772318"],"URL":"https:\/\/doi.org\/10.1145\/3772318.3791819","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}