{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:27:03Z","timestamp":1778081223162,"version":"3.51.4"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,25]]},"DOI":"10.1109\/ro-man63969.2025.11217604","type":"proceedings-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:42:29Z","timestamp":1762195349000},"page":"7-14","source":"Crossref","is-referenced-by-count":1,"title":["CHARM: Considering Human Attributes for Reinforcement Modeling"],"prefix":"10.1109","author":[{"given":"Qidi","family":"Fang","sequence":"first","affiliation":[{"name":"Tufts University,School of Engineering, Computer Science,Medford,Massachusetts,United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Yu","sequence":"additional","affiliation":[{"name":"Tufts University,School of Engineering, Computer Science,Medford,Massachusetts,United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shijie","family":"Fang","sequence":"additional","affiliation":[{"name":"Tufts University,School of Engineering, Computer Science,Medford,Massachusetts,United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jindan","family":"Huang","sequence":"additional","affiliation":[{"name":"Tufts University,School of Engineering, Computer Science,Medford,Massachusetts,United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Tufts University,School of Engineering, Computer Science,Medford,Massachusetts,United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reuben M.","family":"Aronson","sequence":"additional","affiliation":[{"name":"Tufts University,School of Engineering, Computer Science,Medford,Massachusetts,United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elaine S.","family":"Short","sequence":"additional","affiliation":[{"name":"Tufts University,School of Engineering, Computer Science,Medford,Massachusetts,United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342458"},{"key":"ref2","first-page":"303","article-title":"Modeling variation in human feedback with user inputs: An exploratory methodology","volume-title":"Proceedings of the 2024 ACM\/IEEE International Conference on Human-Robot Interaction","author":"Huang"},{"key":"ref3","first-page":"100416","article-title":"A review of feedback models and typologies: Towards an integrative model of feedback elements","volume-title":"Educational Research Review","volume":"35","author":"Panadero","year":"2022"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v37i5.25740","article-title":"The effect of modeling human rationality level on learning rewards from multiple feedback types","author":"Ghosal","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3277904"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161105"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2466\/pms.2001.92.3c.1022"},{"key":"ref8","article-title":"Reward learning from human preferences and demonstrations in atari","volume":"31","author":"Ibarz","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3576983"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN47096.2020.9223451"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-51532-8_10"},{"key":"ref13","first-page":"1455","article-title":"Policy shaping in domains with multiple optimal policies","author":"Sahni","year":"2016","journal-title":"AAMAS"},{"key":"ref14","article-title":"A minimaximalist approach to reinforcement learning from human feedback","author":"Swamy","year":"2024"},{"key":"ref15","volume-title":"Policy shaping: Integrating human feedback with reinforcement learning","author":"Griffith","year":"2013"},{"key":"ref16","article-title":"Provably efficient q-learning with function approximation via distribution shift error checking oracle","volume":"32","author":"Du","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982282"},{"key":"ref18","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018","journal-title":"A Bradford Book"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981076"},{"key":"ref21","first-page":"3366","article-title":"Policy shaping with human teachers","author":"Cederborg","year":"2015","journal-title":"IJCAI"},{"key":"ref22","article-title":"Deep reinforcement learning from policy-dependent human feedback","author":"Arumugam","year":"2019"},{"key":"ref23","article-title":"Guiding a reinforcement learner with natural language advice: Initial results in robocup soccer","volume-title":"The AAAI-2004 workshop on supervisory control of learning and adaptive systems","author":"Kuhlmann"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280477"},{"key":"ref25","article-title":"Guided data augmentation for offline reinforcement learning and imitation learning","volume":"1","author":"Corrado","year":"2024","journal-title":"Reinforcement Learning Journal"},{"key":"ref26","first-page":"649","article-title":"Teaching a robot tasks of arbitrary complexity via human feedback","volume-title":"Proceedings of the 2020 ACM\/IEEE International Conference on Human-Robot Interaction","author":"Wang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.005"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-43645-5_2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888918000206"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3623384"},{"key":"ref31","article-title":"Humans are not boltzmann distributions: Challenges and opportunities for modelling human feedback and interaction in reinforcement learning","author":"Lindner","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2006.314459"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197219"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/biomimetics6010013"},{"key":"ref35","first-page":"728","article-title":"Active attention-modified policy shaping: socially interactive agents track","volume-title":"Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems","author":"Kessler Faulkner"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8839"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2005.1513803"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1006\/jrpe.1999.2243"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-6494.1992.tb00970.x"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6920-14-65"},{"issue":"1","key":"ref41","article-title":"Peer feedback processes in distance education: The giver-receiver experience","volume":"10","author":"Georgountzou","year":"2019","journal-title":"Research Papers in Language Teaching & Learning"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2307\/2959994"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2018.8525515"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3576964"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3173380"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-015-0333-8"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2004.1374726"},{"key":"ref48","article-title":"The perception and measurement of human-robot trust","volume-title":"Ph.D. dissertation","author":"Schaefer","year":"2013"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.jrp.2006.02.001"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.tate.2010.07.002"},{"key":"ref51","article-title":"Mimicgen: A data generation system for scalable robot learning using human demonstrations","author":"Mandlekar","year":"2023"},{"key":"ref52","article-title":"What matters in learning from offline human demonstrations for robot manipulation","author":"Mandlekar","year":"2021"},{"key":"ref53","article-title":"imitation: Clean imitation learning implementations","author":"Gleave","year":"2022"},{"key":"ref54","article-title":"robosuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1037\/0278-7393.10.4.598"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1213\/ane.0000000000002864"},{"key":"ref57","first-page":"343704","article-title":"A critical analysis of adaptive box-cox transformation for skewed distributed data management: Metabolomics of spanish and argentinian truffles as a case study","volume-title":"Analytica Chimica Acta","volume":"1345","author":"Sibono","year":"2025"}],"event":{"name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","location":"Eindhoven, Netherlands","start":{"date-parts":[[2025,8,25]]},"end":{"date-parts":[[2025,8,29]]}},"container-title":["2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11217544\/11217526\/11217604.pdf?arnumber=11217604","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T06:00:30Z","timestamp":1762236030000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11217604\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,25]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/ro-man63969.2025.11217604","relation":{},"subject":[],"published":{"date-parts":[[2025,8,25]]}}}