{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T20:40:21Z","timestamp":1782938421467,"version":"3.54.5"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100019923","name":"DEVCOM Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-19-S-0001"],"award-info":[{"award-number":["W911NF-19-S-0001"]}],"id":[{"id":"10.13039\/100019923","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Robotics and Intelligent Machines at Georgia Tech"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/lra.2026.3700381","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:57:26Z","timestamp":1780603046000},"page":"9431-9438","source":"Crossref","is-referenced-by-count":0,"title":["MO-Playground: Massively Parallelized Multi-Objective Reinforcement Learning for Robotics"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7661-4736","authenticated-orcid":false,"given":"Neil","family":"Janwani","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5263-0598","authenticated-orcid":false,"given":"Ellen","family":"Novoseller","sequence":"additional","affiliation":[{"name":"DEVCOM Army Research Laboratory, Adelphi, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3921-8723","authenticated-orcid":false,"given":"Vernon J.","family":"Lawhern","sequence":"additional","affiliation":[{"name":"DEVCOM Army Research Laboratory, Adelphi, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7363-6809","authenticated-orcid":false,"given":"Maegan","family":"Tucker","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref2","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Rudin","year":"2022"},{"key":"ref3","article-title":"BeyondMimic: From motion tracking to versatile humanoid control via guided diffusion","author":"Liao","year":"2025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-022-09552-y"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref6","article-title":"Navigait: Navigating dynamically feasible gait libraries using deep reinforcement learning","volume-title":"Proc. Int. Conf. Robot. Automat.","author":"Janwani","year":"2026"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196661"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560840"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28886"},{"key":"ref10","first-page":"417","article-title":"Do you want your autonomous car to drive like you?","volume-title":"Proc. ACM\/IEEE Int. Conf. Hum.-Robot Interaction","author":"Basu","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611634"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1028"},{"key":"ref13","first-page":"10607","article-title":"Prediction-guided multi-objective reinforcement learning for continuous robot control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730656"},{"key":"ref15","article-title":"PD-MORL: Preference-driven multi-objective reinforcement learning algorithm","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Basaklar","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/544"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i18.34068"},{"key":"ref18","article-title":"JAX: Composable transformations of python NumPy programs","author":"Bradbury","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.020"},{"key":"ref20","article-title":"Hypernetworks","volume-title":"Proc. Int. Conf. Learn.","author":"Ha","year":"2017"},{"key":"ref21","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref22","article-title":"Brax - A differentiable physics engine for large scale rigid body simulation","author":"Freeman","year":"2021"},{"key":"ref23","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3620620"},{"key":"ref25","article-title":"OpenAI Gym","author":"Brockman","year":"2016"},{"key":"ref26","article-title":"Gymnasium: A Standard interface for reinforcement learning environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"38","author":"Towers","year":"2026"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2024.3388550"},{"key":"ref28","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda","year":"1999"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpa.2020.100022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref31","first-page":"35590","article-title":"Studying the interplay between the actor and critic representations in reinforcement learning","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Garcin","year":"2025"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2990567"},{"key":"ref33","article-title":"BRUCE: Bipedal robot unit with compliance enhanced","author":"Robotics","year":"2022"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11570239\/11551332.pdf?arnumber=11551332","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T19:37:58Z","timestamp":1782934678000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11551332\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":33,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3700381","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}