{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:28:22Z","timestamp":1777501702703,"version":"3.51.4"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Wallenberg AI, Autonomous Systems, and Software Program"},{"name":"Alice Wallenberg Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1109\/lra.2021.3071062","type":"journal-article","created":{"date-parts":[[2021,4,5]],"date-time":"2021-04-05T20:38:49Z","timestamp":1617655129000},"page":"5097-5104","source":"Crossref","is-referenced-by-count":21,"title":["Planning-Augmented Hierarchical Reinforcement Learning"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1772-7930","authenticated-orcid":false,"given":"Robert","family":"Gieselmann","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian T.","family":"Pokorny","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Rapidly-exploring random trees: A new tool for path planning","author":"lavalle","year":"1998"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386390"},{"key":"ref31","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref30","article-title":"Hindsight experience replay","author":"andrychowicz","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","article-title":"Agx dynamics - real-time multi-body simulation","year":"2021"},{"key":"ref34","first-page":"2016","article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"coumans","year":"0"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461096"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2931199"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/700"},{"key":"ref13","first-page":"2947","article-title":"Gated path planning networks","author":"lee","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref14","first-page":"4732","article-title":"Universal planning networks: Learning generalizable representations for visuomotor control","author":"srinivas","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.020"},{"key":"ref16","first-page":"1942","article-title":"Mapping state space using landmarks for universal goal reaching","volume":"32","author":"huang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","article-title":"Planning with goal-conditioned policies","author":"nasiriany","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref19","article-title":"Semi-parametric topological memory for navigation","author":"savinov","year":"0","journal-title":"Int Conf Learn Representations"},{"key":"ref28","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref27","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"ref6","article-title":"Hierarchical reinforcement learning with hindsight","author":"levy","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref29","first-page":"603","article-title":"Hrl4in: Hierarchical reinforcement learning for interactive navigation with mobile manipulators","author":"li","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref5","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206505"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref2","first-page":"2377","volume":"48","author":"osband","year":"2016","journal-title":"Generalization and exploration via randomized value functions"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569436"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref20","article-title":"Dynamics learning with cascaded variational inference for multi-step manipulation","author":"fang","year":"0","journal-title":"Proc CoRL"},{"key":"ref22","article-title":"Plan2vec: Unsupervised representation learning by latent plans","author":"yang","year":"2020"},{"key":"ref21","article-title":"Hallucinative topological memory for zero-shot visual planning","author":"liu","year":"2020"},{"key":"ref24","article-title":"Sparse graphical memory for robust planning","author":"laskin","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","first-page":"5619","article-title":"Latent space roadmap for visual action planning of deformable and rigid object manipulation","author":"lippi","year":"0","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref26","first-page":"449","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref25","first-page":"1094","article-title":"Learning to achieve goals","author":"kaelbling","year":"0","journal-title":"Proc Int Joint Conf Artif Intell"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9399748\/09395248.pdf?arnumber=9395248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:58Z","timestamp":1652194438000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9395248\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":35,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3071062","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7]]}}}