{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T13:58:22Z","timestamp":1776866302188,"version":"3.51.2"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CDT in Robotics and Autonomous Systems at Heriot-Watt University and The University of Edinburgh","award":["EP\/L016834\/1."],"award-info":[{"award-number":["EP\/L016834\/1."]}]},{"name":"Alan Turing Institute sponsored project on Safe AI for Surgical Assistance"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1109\/lra.2020.2972794","type":"journal-article","created":{"date-parts":[[2020,2,11]],"date-time":"2020-02-11T02:00:05Z","timestamp":1581386405000},"page":"2658-2665","source":"Crossref","is-referenced-by-count":11,"title":["Composing Diverse Policies for Temporally Extended Tasks"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7292-5182","authenticated-orcid":false,"given":"Daniel","family":"Angelov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yordan","family":"Hristov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7426-1498","authenticated-orcid":false,"given":"Michael","family":"Burke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subramanian","family":"Ramamoorthy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1696","article-title":"Task-agnostic dynamics priors for deep reinforcement learning","volume":"97","author":"du","year":"2019","journal-title":"Proceedings 36th Int Conf Mach Learn"},{"key":"ref38","first-page":"2450","article-title":"Recurrent world models facilitate policy evolution","author":"ha","year":"2018","journal-title":"Adv in Neural Info Proc Syst"},{"key":"ref33","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"2019","journal-title":"ICML"},{"key":"ref32","article-title":"When waiting is not an option: Learning options with a deliberation cost","author":"harb","year":"0","journal-title":"Thirty-Second AAAI Conf Artif Intell"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460635"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"1174","DOI":"10.1016\/j.ifacol.2015.09.127","article-title":"Controller verification and parametrization subject to quantitative and qualitative requirements","volume":"48","author":"rumschinski","year":"2015","journal-title":"IFAC-PapersOnLine"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918770733"},{"key":"ref35","first-page":"181","article-title":"Reward functions for accelerated learning","author":"mataric","year":"1994","journal-title":"Machine Learning Proceedings"},{"key":"ref34","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/027836498400300101"},{"key":"ref40","article-title":"Learning with options that terminate off-policy","author":"harutyunyan","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/02783649922066079"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912442972"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/4-431-31381-8_23"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref15","first-page":"2170","article-title":"Deepmdp: Learning continuous latent space models for representation learning","author":"gelada","year":"2019","journal-title":"ICML"},{"key":"ref16","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016"},{"key":"ref17","first-page":"9105","article-title":"Learning safe policies with expert guidance","author":"huang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","first-page":"1341","article-title":"Using causal analysis to learn specifications from task demonstrations","author":"angelov","year":"2019","journal-title":"Proc 4th Int Conf Auton Agents Multiagent Syst (AAMAS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116836"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/02783649922066385"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(72)90051-3"},{"key":"ref3","first-page":"14","article-title":"Manipulator grasping and pushing operations","author":"mason","year":"1982"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref29","first-page":"29","article-title":"Learning to solve problems by searching for macro-operators","author":"korf","year":"1983"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910369189"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/027836498600500303"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460696"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(89)90002-2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630673"},{"key":"ref20","first-page":"769","article-title":"Hierarchical apprenticeship learning with application to quadruped locomotion","author":"kolter","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793506"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022140919877"},{"key":"ref21","first-page":"9329","article-title":"Exploring the limitations of behavior cloning for autonomous driving","author":"codevilla","year":"0","journal-title":"Proc IEEE Int Conf Comput Vision"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794074"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844730"},{"key":"ref23","article-title":"A survey of inverse reinforcement learning: Challenges, methods and progress","author":"arora","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.002"},{"key":"ref26","article-title":"Made-Up Minds: A Constructivist Approach to Artificial Intelligence","author":"drescher","year":"1989"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.004"},{"key":"ref25","article-title":"Eligibility traces for off-policy policy evaluation","author":"precup","year":"0","journal-title":"Proc 17th Int Conf Mach Learn"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8932682\/08989819.pdf?arnumber=8989819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:32:49Z","timestamp":1651080769000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8989819\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4]]},"references-count":45,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2020.2972794","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4]]}}}