{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:12:26Z","timestamp":1774631546507,"version":"3.50.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,21]],"date-time":"2024-08-21T00:00:00Z","timestamp":1724198400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,21]],"date-time":"2024-08-21T00:00:00Z","timestamp":1724198400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"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":[[2024,8,21]]},"DOI":"10.1109\/ccta60707.2024.10666622","type":"proceedings-article","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T17:35:04Z","timestamp":1726076104000},"page":"209-216","source":"Crossref","is-referenced-by-count":11,"title":["High-Level Human Intention Learning for Cooperative Decision-Making"],"prefix":"10.1109","author":[{"given":"Yuxin","family":"Lin","sequence":"first","affiliation":[{"name":"Northeastern University,Department of Electrical and Computer Engineering"}]},{"given":"Seyede Fatemeh","family":"Ghoreishi","sequence":"additional","affiliation":[{"name":"Northeastern University,Department of Civil and Environmental Engineering and Khoury College of Computer Sciences"}]},{"given":"Tian","family":"Lan","sequence":"additional","affiliation":[{"name":"George Washington University,Department of Electrical and Computer Engineering"}]},{"given":"Mahdi","family":"Imani","sequence":"additional","affiliation":[{"name":"Northeastern University,Department of Electrical and Computer Engineering"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3040","article-title":"Social influence as intrinsic motivation for multi-agent deep reinforcement learning","volume-title":"International conference on machine learning","author":"Jaques"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0018720820960865"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147613"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0018720816644364"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.biosystemseng.2018.12.005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1108\/IR-04-2021-0077"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1049\/2024\/7966713"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1061\/9780784485514.035"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-019-00523-0"},{"key":"ref10","article-title":"A survey of robot learning from demonstrations for human-robot collaboration","author":"Lee","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-020-01183-3"},{"key":"ref12","article-title":"Collaborative AI teaming in unknown environments via active goal deduction","author":"Zhang","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/ACC60939.2024.10644975"},{"key":"ref14","first-page":"212","article-title":"i-sim2real: Reinforcement learning of robotic policies in tight human-robot interaction loops","volume-title":"Conference on Robot Learning","author":"Abeyruwan"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref16","article-title":"Maximum entropy deep inverse reinforcement learning","author":"Wulfmeier","year":"2015"},{"key":"ref17","article-title":"Way off-policy batch deep reinforcement learning of implicit human preferences in dialog","author":"Jaques","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref19","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2016.2558539"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3358261"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-85613-7_29"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2021.102137"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.018.2200514"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972874"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3069172"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071958"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593766"},{"key":"ref29","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3353742"},{"key":"ref31","first-page":"8156","article-title":"Bayesian control of large MDPs with unknown dynamics in data-poor environments","author":"Imani","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.11.005"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-020-09947-4"},{"key":"ref34","first-page":"922","article-title":"Posterior sampling-based online learning for the stochastic shortest path model","volume-title":"Uncertainty in Artificial Intelligence","author":"Jafarnia-Jahromi","year":"2023"},{"key":"ref35","article-title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","volume-title":"International Conference on Learning Representations","author":"Zintgraf"},{"key":"ref36","first-page":"1189","article-title":"Bayesian reinforcement learning for single-episode missions in partially unknown environments","volume-title":"Conference on Robot Learning","author":"Budd"}],"event":{"name":"2024 IEEE Conference on Control Technology and Applications (CCTA)","location":"Newcastle upon Tyne, United Kingdom","start":{"date-parts":[[2024,8,21]]},"end":{"date-parts":[[2024,8,23]]}},"container-title":["2024 IEEE Conference on Control Technology and Applications (CCTA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10666388\/10666504\/10666622.pdf?arnumber=10666622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T17:42:13Z","timestamp":1726162933000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10666622\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,21]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/ccta60707.2024.10666622","relation":{},"subject":[],"published":{"date-parts":[[2024,8,21]]}}}