{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T13:49:58Z","timestamp":1778075398501,"version":"3.51.4"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"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":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636297","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"6739-6746","source":"Crossref","is-referenced-by-count":14,"title":["Behavior Self-Organization Supports Task Inference for Continual Robot Learning"],"prefix":"10.1109","author":[{"given":"Muhammad","family":"Burhan Hafez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref38","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"ICLRE"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2019.8850713"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2538961"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.05.008"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.082"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(02)00078-3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref35","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref34","first-page":"2661","article-title":"Zero-shot task generalization with multi-task deep reinforcement learning","author":"oh","year":"2017","journal-title":"ICML"},{"key":"ref10","first-page":"24","article-title":"On-policy robot imitation learning from a converging supervisor","author":"balakrishna","year":"2020","journal-title":"CoRL"},{"key":"ref40","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"OSDI"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref12","article-title":"Single episode policy transfer in reinforcement learning","author":"yang","year":"2019","journal-title":"ICLRE"},{"key":"ref13","first-page":"5400","article-title":"Evolved policy gradients","author":"houthooft","year":"2018","journal-title":"NeurIPS"},{"key":"ref14","first-page":"1440","article-title":"Learning context-aware task reasoning for efficient meta reinforcement learning","author":"wang","year":"2020","journal-title":"AAMAS"},{"key":"ref15","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","author":"rakelly","year":"2019","journal-title":"ICML PMLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1111\/1467-7687.00135"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0278-2626(03)00208-2"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1111\/cogs.12446"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/0926-6410(95)00038-0"},{"key":"ref28","first-page":"5691","article-title":"A meta-MDP approach to exploration for lifelong reinforcement learning","author":"garcia","year":"2019","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref3","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00653"},{"key":"ref6","article-title":"A simple neural attentive meta-learner","author":"mishra","year":"2018","journal-title":"ICLRE"},{"key":"ref29","article-title":"Policy distillation","author":"rusu","year":"2016","journal-title":"ICLRE"},{"key":"ref5","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"ICML"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341571"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref9","first-page":"6818","article-title":"Imitation learning from imperfect demonstration","author":"wu","year":"2019","journal-title":"ICML"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(04)00181-3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1080\/02640410600946860"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1152\/physrev.00009.2013"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1037\/a0017473"},{"key":"ref42","article-title":"Coppeliasim (formerly V-REP): a versatile and scalable robot simulation framework","author":"rohmer","year":"2013","journal-title":"IROS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1037\/a0037200"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2017.8172289"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jecp.2017.04.018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462901"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2015.00562"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Prague, Czech Republic","start":{"date-parts":[[2021,9,27]]},"end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09636297.pdf?arnumber=9636297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:54:38Z","timestamp":1652201678000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636297\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636297","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}