{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T02:44:13Z","timestamp":1775529853812,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Denso International America, Inc."}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/lra.2022.3190100","type":"journal-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:25:07Z","timestamp":1657653907000},"page":"10216-10223","source":"Crossref","is-referenced-by-count":37,"title":["Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7335-5553","authenticated-orcid":false,"given":"Jinning","family":"Li","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7536-9983","authenticated-orcid":false,"given":"Chen","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0206-6639","authenticated-orcid":false,"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1474-1200","authenticated-orcid":false,"given":"Wei","family":"Zhan","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"},{"key":"ref2","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2020"},{"key":"ref3","first-page":"1455","article-title":"Dealing with the unknown: Pessimistic offline reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Li","year":"2022"},{"key":"ref4","first-page":"907","article-title":"S4RL: Surprisingly simple self-supervision for offline reinforcement learning in robotics","volume-title":"Proc. 5th Conf. Robot Learn.","author":"Sinha","year":"2022"},{"key":"ref5","first-page":"417","article-title":"A workflow for offline model-free robotic reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Kumar","year":"2022"},{"key":"ref6","first-page":"2162","article-title":"Chaining behaviors from data with model-free reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Singh","year":"2021"},{"key":"ref7","first-page":"118","article-title":"The MAXQ method for hierarchical reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"98","author":"Dietterich","year":"1998"},{"key":"ref8","first-page":"3307","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Nachum","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561195"},{"key":"ref10","first-page":"14843","article-title":"Planning with goal-conditioned policies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nasiriany","year":"2019"},{"key":"ref11","first-page":"1094","article-title":"Learning to achieve goals","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Kaelbling","year":"1993"},{"key":"ref12","first-page":"1312","article-title":"Universal value function approximators","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Schaul","year":"2015"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139643"},{"key":"ref14","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Berkenkamp","year":"2017"},{"key":"ref15","first-page":"5055","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Andrychowicz","year":"2017"},{"key":"ref16","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn","year":"2015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2019.0317"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00172"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1115\/DSCC2020-3328"},{"key":"ref20","first-page":"15246","article-title":"Search on the replay buffer: Bridging planning and reinforcement learning","volume":"32","author":"Eysenbach","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3094821"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.061"},{"key":"ref23","first-page":"1025","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Gupta","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196935"},{"key":"ref25","article-title":"Opal: Offline primitive discovery for accelerating offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ajay","year":"2021"},{"key":"ref26","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","volume":"32","author":"Janner","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref27","first-page":"15324","article-title":"Goal-conditioned imitation learning","volume-title":"Proc. Adv. Neural Inf. Processing Syst.","author":"Ding","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref29","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","author":"Dosovitskiy","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref32","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2022.3185139"},{"key":"ref34","volume-title":"Model Predictive Control","author":"Camacho","year":"2013"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9831196\/09826807.pdf?arnumber=9826807","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T01:54:27Z","timestamp":1706061267000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9826807\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":35,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3190100","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}