{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:43:09Z","timestamp":1730270589859,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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","award":["1954782"],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10341801","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"3680-3687","source":"Crossref","is-referenced-by-count":1,"title":["Learning Constraints on Autonomous Behavior from Proactive Feedback"],"prefix":"10.1109","author":[{"given":"Connor","family":"Basich","sequence":"first","affiliation":[{"name":"University of Massachusetts Amherst, Manning College of Information and Computer Sciences,Amherst,MA,USA"}]},{"given":"Saaduddin","family":"Mahmud","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Manning College of Information and Computer Sciences,Amherst,MA,USA"}]},{"given":"Shlomo","family":"Zilberstein","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Manning College of Information and Computer Sciences,Amherst,MA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v38i3.2756"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13581"},{"key":"ref3","article-title":"Efficient reductions for imitation learning","volume-title":"International Conference on Artificial Intelligence and Statistics (AIStat)","author":"Ross","year":"2010"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v32i1.19838"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016137"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10108-x"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-021-10006-9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3171221.3171267"},{"key":"ref10","article-title":"Learning to optimize autonomy in competence-aware systems","volume-title":"International Conference on Autonomous Agents and MultiAgent Systems (AAMAS)","author":"Basich","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.005"},{"key":"ref12","article-title":"Efficient learning of safe driving policy via human-AI copilot optimization","volume-title":"International Conference on Learning Representations, (ICLR)","author":"Li","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2011.12.010"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/jocn_a_00542"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2584"},{"key":"ref16","article-title":"Supervised actor-critic reinforcement learning","volume-title":"Handbook of Learning and Approximate Dynamic Programming","author":"Rosenstein","year":"2004"},{"key":"ref17","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","volume-title":"International Conference on Machine Learning (ICML)","author":"Brown","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-02675-6_46"},{"key":"ref19","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","author":"Griffith","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"ref21","article-title":"Thriftydagger: Budget-aware novelty and risk gating for interactive imitation learning","volume-title":"Conference on Robot Learning","author":"Hoque","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636239"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460854"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HRI53351.2022.9889616"},{"key":"ref25","article-title":"Reciprocal MIND MELD: Improving learning from demonstration via personalized, reciprocal teaching","volume-title":"Conference on Robot Learning (CoRL)","author":"Schrum","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211035177"},{"key":"ref27","article-title":"Maximum likelihood constraint inference for inverse reinforcement learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Scobee","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CCTA48906.2021.9658862"},{"key":"ref29","article-title":"Inverse constrained reinforcement learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Malik","year":"2021"},{"key":"ref30","article-title":"Bayesian methods for constraint inference in reinforcement learning","author":"Papadimitriou","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2022.103844"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9647"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3987"},{"key":"ref34","article-title":"A survey of uncertainty in deep neural networks","volume":"abs\/2107.03342","author":"Gawlikowski","year":"2021","journal-title":"Computing Research Repository"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1249"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.6.3.259"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i5.25740"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2023,10,1]]},"location":"Detroit, MI, USA","end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10341801.pdf?arnumber=10341801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:14:33Z","timestamp":1703031273000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341801\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341801","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}