{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T02:00:50Z","timestamp":1760061650169,"version":"3.37.3"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["CCF-2048094","CNS-1932620","CCF-1837131"],"award-info":[{"award-number":["CCF-2048094","CNS-1932620","CCF-1837131"]}]},{"name":"Toyota R&D"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1109\/lra.2022.3226072","type":"journal-article","created":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T20:44:05Z","timestamp":1669927445000},"page":"336-343","source":"Crossref","is-referenced-by-count":4,"title":["Learning Performance Graphs From Demonstrations via Task-Based Evaluations"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0010-9789","authenticated-orcid":false,"given":"Aniruddh G.","family":"Puranic","sequence":"first","affiliation":[{"name":"Computer Science Department, University of Southern California, Los Angeles, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4683-5540","authenticated-orcid":false,"given":"Jyotirmoy V.","family":"Deshmukh","sequence":"additional","affiliation":[{"name":"Computer Science Department, University of Southern California, Los Angeles, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1081-250X","authenticated-orcid":false,"given":"Stefanos","family":"Nikolaidis","sequence":"additional","affiliation":[{"name":"Computer Science Department, University of Southern California, Los Angeles, CA, USA"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11229-021-03141-4"},{"key":"ref38","first-page":"7799","article-title":"On the expressivity of Markov reward","author":"abel","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref31","first-page":"1040","article-title":"Learning from demonstration","author":"schaal","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref30","first-page":"12","article-title":"Robot learning from demonstration","author":"atkeson","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304190"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460811"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96145-3_38"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354078"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5631"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30206-3_12"},{"key":"ref12","first-page":"2228","article-title":"Learning from demonstrations using signal temporal logic","author":"puranic","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"6250","DOI":"10.1109\/LRA.2021.3092676","article-title":"Learning from demonstrations using signal temporal logic","volume":"6","author":"puranic","year":"0","journal-title":"IEEE Robot Autom Lett"},{"article-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","year":"2010","author":"ziebart","key":"ref14"},{"key":"ref15","first-page":"429","article-title":"Learning from demonstration for shaping through inverse reinforcement learning","author":"suay","year":"0","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"ref16","article-title":"Learning robust rewards with adverserial inverse reinforcement learning","author":"fu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10459-010-9222-y"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3171221.3171264"},{"article-title":"Learning performance graphs from demonstrations via task-based evaluations - supplemental material","year":"2022","author":"puranic","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012487302797"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3189441"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2013.08.044"},{"key":"ref3","first-page":"610","article-title":"The utility of explainable AI in Ad Hoc human-machine teaming","author":"paleja","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3064220"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1950.tb00463.x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ ARXIV.1606.06565"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1809.06305"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206234"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3433637"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7799279"},{"journal-title":"Human-AI Teaming State of the Art and Research Needs","year":"2022","key":"ref1"},{"key":"ref20","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ ARXIV.1707.06347"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340956"},{"key":"ref42","first-page":"457","article-title":"Score-based inverse reinforcement learning","author":"asri","year":"0","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"ref24","first-page":"1","article-title":"CARLA: An open urban driving simulator","author":"dosovitskiy","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref41","article-title":"Explainable reinforcement learning via reward decomposition","author":"juozapaitis","year":"0","journal-title":"Proc IJCAI\/ECAI Workshop Explainable Artif Intell"},{"key":"ref23","article-title":"Distributed distributional deterministic policy gradients","author":"barth-maron","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"journal-title":"Machine Learning A Probabilistic Perspective","year":"2012","author":"murphy","key":"ref26"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1177\/02783649211041652","article-title":"Learning reward functions from diverse sources of human feedback: Optimally integrating demonstrations and preferences","volume":"41","author":"biyik","year":"2022","journal-title":"Int J Robot Res"},{"key":"ref25","first-page":"1","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/9963768\/9968087-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9963768\/09968087.pdf?arnumber=9968087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:18:39Z","timestamp":1672082319000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9968087\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":43,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3226072","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2023,1]]}}}