{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:51:35Z","timestamp":1730267495270,"version":"3.28.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"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":[[2023,7,18]]},"DOI":"10.1109\/indin51400.2023.10218251","type":"proceedings-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T13:36:36Z","timestamp":1692711396000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["EValueAction: a proposal for policy evaluation in simulation to support interactive imitation learning"],"prefix":"10.1109","author":[{"given":"Fiorella","family":"Sibona","sequence":"first","affiliation":[{"name":"Politecnico di Torino,Dipartimento di Elettronica e Telecomunicazioni (DET),Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jelle","family":"Luijkx","sequence":"additional","affiliation":[{"name":"Delft University of Technology,Cognitive Robotics department (CoR),The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bas van der","family":"Heijden","sequence":"additional","affiliation":[{"name":"Delft University of Technology,Cognitive Robotics department (CoR),The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laura","family":"Ferranti","sequence":"additional","affiliation":[{"name":"Delft University of Technology,Cognitive Robotics department (CoR),The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marina","family":"Indri","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Dipartimento di Elettronica e Telecomunicazioni (DET),Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"16118","article-title":"Generalizable imitation learning from observation via inferring goal proximity","volume":"34","author":"lee","year":"2021","journal-title":"Advances in neural information processing systems"},{"journal-title":"Theory and Application of Reward Shaping in Reinforcement Learning","year":"2004","author":"laud","key":"ref35"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.777363"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref15","article-title":"What matters in learning from offline human demonstrations for robot manipulation","author":"mandlekar","year":"2021","journal-title":"arXiv preprint arXiv 2108 03490"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref14","article-title":"Guided optimal control for long-term non-prehensile planar manipulation","author":"xue","year":"2022","journal-title":"arXiv preprint arXiv 2212 12814"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636710"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-022-08652-z"},{"key":"ref11","first-page":"1896","article-title":"Acnmp: Skill transfer and task extrapolation through learning from demonstration and reinforcement learning via representation sharing","author":"akbulut","year":"2021","journal-title":"Conference on Robot Learning"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref33"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3150013"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3165531"},{"key":"ref2","first-page":"1","article-title":"The ASSISTANT project: AI for high level decisions in manufacturing","author":"casta\u00f1\u00e9","year":"2022","journal-title":"International Journal of Production Research"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/s21051571"},{"key":"ref17","first-page":"12340","article-title":"Confidence-aware imitation learning from demonstrations with varying optimality","volume":"34","author":"zhang","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref39","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"makoviychuk","year":"2021","journal-title":"arXiv preprint arXiv 2108 10721"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191950"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1561\/2300000053"},{"key":"ref19","article-title":"Generalizing to new tasks via one-shot compositional subgoals","author":"bian","year":"2022","journal-title":"arXiv preprint arXiv 2205 07716"},{"key":"ref18","article-title":"Team: a parameter-free algorithm to teach collaborative robots motions from user demonstrations","author":"panchetti","year":"2022","journal-title":"arXiv preprint arXiv 2209 06940"},{"key":"ref24","article-title":"Partnr: Pick and place ambiguity resolving by trustworthy interactive learning","author":"luijkx","year":"2022","journal-title":"arXiv preprint arXiv 2211 08304"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-08118-z"},{"key":"ref26","article-title":"Query-efficient imitation learning for end-to-end autonomous driving","author":"zhang","year":"2016","journal-title":"arXiv preprint arXiv 1605 06636"},{"key":"ref25","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR53236.2021.9659470"},{"key":"ref42","first-page":"856","article-title":"Modular meta-learning","author":"alet","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref41","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1561\/2300000072"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982222"},{"key":"ref28","article-title":"Thriftydagger: Budget-aware novelty and risk gating for interactive imitation learning","author":"hoque","year":"2021","journal-title":"arXiv preprint arXiv 2109 08742"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49439.2021.9551469"},{"key":"ref29","article-title":"Generalizable human-robot collaborative assembly using imitation learning and force control","author":"jha","year":"2022","journal-title":"arXiv preprint arXiv 2212 01434"},{"key":"ref8","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","author":"jang","year":"2022","journal-title":"Conference on Robot Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3056367"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2021.102169"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jii.2021.100257"},{"year":"0","key":"ref3","article-title":"NVIDIA Omniverse"},{"key":"ref6","first-page":"1764","article-title":"Back to reality for imitation learning","author":"johns","year":"2022","journal-title":"Conference on Robot Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/09544089211051595"},{"key":"ref40","article-title":"Brax--a differentiable physics engine for large scale rigid body simulation","author":"freeman","year":"2021","journal-title":"arXiv preprint arXiv 2106 13112"}],"event":{"name":"2023 IEEE 21st International Conference on Industrial Informatics (INDIN)","start":{"date-parts":[[2023,7,18]]},"location":"Lemgo, Germany","end":{"date-parts":[[2023,7,20]]}},"container-title":["2023 IEEE 21st International Conference on Industrial Informatics (INDIN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10217218\/10217836\/10218251.pdf?arnumber=10218251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T13:54:16Z","timestamp":1694440456000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10218251\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/indin51400.2023.10218251","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]}}}