{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T18:18:03Z","timestamp":1776536283085,"version":"3.51.2"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1109\/lra.2021.3060403","type":"journal-article","created":{"date-parts":[[2021,2,20]],"date-time":"2021-02-20T10:05:08Z","timestamp":1613815508000},"page":"3623-3630","source":"Crossref","is-referenced-by-count":19,"title":["Learning Functionally Decomposed Hierarchies for Continuous Control Tasks With Path Planning"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3511-8565","authenticated-orcid":false,"given":"Sammy","family":"Christen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4095-0970","authenticated-orcid":false,"given":"Lukas","family":"Jendele","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9836-9011","authenticated-orcid":false,"given":"Emre","family":"Aksan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5068-3474","authenticated-orcid":false,"given":"Otmar","family":"Hilliges","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"0","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-009-9110-3"},{"key":"ref31","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","first-page":"14 814","article-title":"Planning with goal-conditioned policies","author":"nasiriany","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","article-title":"Openai Gym","author":"brockman","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref10","article-title":"Learning multi-level hierarchies with hindsight","author":"levy","year":"0","journal-title":"Proc 7th Int Conf Learn Representations"},{"key":"ref11","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","article-title":"Near-optimal representation learning for hierarchical reinforcement learning","author":"nachum","year":"0","journal-title":"Proc 7th Int Conf Learn Representations (ICLR)"},{"key":"ref13","first-page":"1","article-title":"Driving policy transfer via modularity and abstraction","volume":"87","author":"m\u00fcller","year":"0","journal-title":"Proc 2nd Conf Robot Learn"},{"key":"ref14","first-page":"271","article-title":"Feudal reinforcement learning","volume":"5","author":"dayan","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref15","article-title":"Value propagation networks","author":"nardelli","year":"0","journal-title":"Proc 7th Int Conf Learn Representations"},{"key":"ref16","first-page":"293","article-title":"Rapidly-exploring random trees: A new tool for path planning","year":"0","journal-title":"Proc Algo Comput Robot New Directions"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.155375"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref19","article-title":"Exploiting hierarchy for learning and transfer in KL-regularized RL","author":"tirumala","year":"0","journal-title":"CoRR"},{"key":"ref28","author":"bertsekas","year":"0","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794065"},{"key":"ref27","first-page":"4739","article-title":"Universal planning networks: Learning generalizable representations for visuomotor control","volume":"80","author":"srinivas","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061308"},{"key":"ref6","first-page":"119","article-title":"State abstraction for programmable reinforcement learning agents","author":"andre","year":"0","journal-title":"Proc Amer Assoc Artif Intell"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref8","first-page":"1726","article-title":"The option-critic architecture","volume":"31","author":"bacon","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref7","article-title":"Meta learning shared hierarchies","author":"frans","year":"0","journal-title":"Proc 6th Int Conf Learn Representations (ICLR)"},{"key":"ref2","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref9","first-page":"3540","article-title":"FeUdal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Int Conf Learn Represent (ICLR)"},{"key":"ref20","first-page":"4159","article-title":"Hierarchically decoupled imitation for morphological transfer","volume":"119","author":"hejna","year":"0","journal-title":"Proc 37th Int Conf Mach Learn Ser Proc Mach Learn Res"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref21","first-page":"895","article-title":"Building portable options: Skill transfer in reinforcement learning","author":"konidaris","year":"0","journal-title":"Proc 20th Int Joint Conf Artif Intell ser IJCAI’07"},{"key":"ref24","first-page":"15\ufffd246","article-title":"Search on the replay buffer: Bridging planning and reinforcement learning","author":"eysenbach","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","article-title":"Benchmarking model-based reinforcement learning","author":"wang","year":"0","journal-title":"CoRR"},{"key":"ref26","first-page":"6118","article-title":"Value prediction network","author":"oh","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/700"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9285111\/09357915.pdf?arnumber=9357915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:16Z","timestamp":1652194456000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9357915\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4]]},"references-count":35,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3060403","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4]]}}}