{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:31:18Z","timestamp":1777735878770,"version":"3.51.4"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T00:00:00Z","timestamp":1724630400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T00:00:00Z","timestamp":1724630400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,8,26]]},"DOI":"10.1109\/ro-man60168.2024.10731359","type":"proceedings-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T17:45:45Z","timestamp":1730310345000},"page":"1739-1746","source":"Crossref","is-referenced-by-count":3,"title":["How Much Progress Did I Make? An Unexplored Human Feedback Signal for Teaching Robots"],"prefix":"10.1109","author":[{"given":"Hang","family":"Yu","sequence":"first","affiliation":[{"name":"Tufts University,Medford,MA,USA,02144"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qidi","family":"Fang","sequence":"additional","affiliation":[{"name":"Tufts University,Medford,MA,USA,02144"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shijie","family":"Fang","sequence":"additional","affiliation":[{"name":"Tufts University,Medford,MA,USA,02144"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reuben M.","family":"Aronson","sequence":"additional","affiliation":[{"name":"Tufts University,Medford,MA,USA,02144"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elaine Schaertl","family":"Short","sequence":"additional","affiliation":[{"name":"Tufts University,Medford,MA,USA,02144"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"330","article-title":"Better-than-demonstrator imitation learning via automatically-ranked demonstrations","volume-title":"Conf. on robot learning","author":"Brown"},{"key":"ref2","first-page":"1262","article-title":"Learning from suboptimal demonstration via self-supervised reward regression","volume-title":"Conf. on robot learning","author":"Chen"},{"key":"ref3","first-page":"604","article-title":"The empathic framework for task learning from implicit human feedback","volume-title":"Conf. on Robot Learning","author":"Cui"},{"key":"ref4","first-page":"3366","article-title":"Policy shaping with human teachers","author":"Cederborg","year":"2015","journal-title":"IJCAI"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref6","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":"ref7","article-title":"Ranking-based reward extrapolation without rankings","author":"Brown","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3357236.3395525"},{"key":"ref10","first-page":"15 070","article-title":"Uncertain decisions facilitate better preference learning","volume":"34","author":"Laidlaw","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342458"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2013.07.008"},{"key":"ref13","first-page":"1247","article-title":"Understanding teacher gaze patterns for robot learning","volume-title":"Conf. on Robot Learning","author":"Saran"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2013.2291714"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref16","article-title":"Dqn-tamer: Human-in-the-loop reinforcement learning with intractable feedback","author":"Arakawa","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11485"},{"key":"ref18","article-title":"Open problems and fundamental limitations of reinforcement learning from human feedback","author":"Casper","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/331"},{"key":"ref20","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":"ref21","article-title":"Deep reinforcement learning from policy-dependent human feedback","author":"Arumugam","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.06.064"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23780-5_11"},{"key":"ref24","first-page":"arXiv:2303.08774","article-title":"GPT-4 Technical Report","author":"Achiam","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01570-0"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/robotics7020017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793762"},{"key":"ref28","first-page":"3502","article-title":"Learning stable stochastic nonlinear dynamical systems","volume-title":"Int. Conf. on Machine Learning","author":"Umlauft"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref30","article-title":"Sample efficient imitation learning for continuous control","volume-title":"Int. Conf. on learning representations","author":"Sasaki"},{"key":"ref31","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s41315-019-00103-5"},{"key":"ref33","first-page":"6818","article-title":"Imitation learning from imperfect demonstration","volume-title":"Int. Conf. on Machine Learning","author":"Wu"},{"key":"ref34","article-title":"Behavioral cloning from noisy demonstrations","volume-title":"Int. Conf. on Learning Representations","author":"Sasaki"},{"key":"ref35","first-page":"10 961","article-title":"Learning to weight imperfect demonstrations","volume-title":"Int. Conf. on Machine Learning","author":"Wang"},{"key":"ref36","article-title":"Scaling data-driven robotics with reward sketching and batch reinforcement learning","author":"Cabi","year":"2019"},{"key":"ref37","first-page":"1165","article-title":"Safe imitation learning via fast bayesian reward inference from preferences","volume-title":"Int. Conf. on Machine Learning","author":"Brown"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3610977.3634925"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1177\/154193120605000909"},{"key":"ref40","volume-title":"Statistics","author":"Witte","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-020-01798-5"},{"key":"ref42","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","author":"Fu","year":"2018"}],"event":{"name":"2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN)","location":"Pasadena, CA, USA","start":{"date-parts":[[2024,8,26]]},"end":{"date-parts":[[2024,8,30]]}},"container-title":["2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10731142\/10731137\/10731359.pdf?arnumber=10731359","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T04:21:37Z","timestamp":1732681297000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10731359\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,26]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ro-man60168.2024.10731359","relation":{},"subject":[],"published":{"date-parts":[[2024,8,26]]}}}