{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T20:19:27Z","timestamp":1777407567240,"version":"3.51.4"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"JST SPRING","award":["JPMJSP2124"],"award-info":[{"award-number":["JPMJSP2124"]}]},{"name":"JST SPRING","award":["JSPS JP22H00545"],"award-info":[{"award-number":["JSPS JP22H00545"]}]},{"name":"JST SPRING","award":["JP22H05002"],"award-info":[{"award-number":["JP22H05002"]}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001863","name":"NEDO (New Energy and Industrial Technology Development Organization) in Japan","doi-asserted-by":"publisher","award":["JPNP20006"],"award-info":[{"award-number":["JPNP20006"]}],"id":[{"id":"10.13039\/501100001863","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3324039","type":"journal-article","created":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T17:47:56Z","timestamp":1697132876000},"page":"126979-126994","source":"Crossref","is-referenced-by-count":4,"title":["A Hierarchical Robot Learning Framework for Manipulator Reactive Motion Generation via Multi-Agent Reinforcement Learning and Riemannian Motion Policies"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5037-4324","authenticated-orcid":false,"given":"Yuliu","family":"Wang","sequence":"first","affiliation":[{"name":"Intelligent and Mechanical Interaction Systems Program, University of Tsukuba, Ibaraki, Tsukuba, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6778-8838","authenticated-orcid":false,"given":"Ryusuke","family":"Sagawa","sequence":"additional","affiliation":[{"name":"Intelligent and Mechanical Interaction Systems Program, University of Tsukuba, Ibaraki, Tsukuba, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0433-9832","authenticated-orcid":false,"given":"Yusuke","family":"Yoshiyasu","sequence":"additional","affiliation":[{"name":"Computer Vision Research Team, Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology, Ibaraki, Tsukuba, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Kalashnikov"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844730"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10339-011-0404-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2006.345351"},{"key":"ref5","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636477"},{"key":"ref8","first-page":"270","article-title":"GPU-accelerated robotic simulation for distributed reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Liang"},{"key":"ref9","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref10","article-title":"Deep implicit coordination graphs for multi-agent reinforcement learning","author":"Li","year":"2020","journal-title":"arXiv:2006.11438"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/BIOROB.2016.7523669"},{"key":"ref12","first-page":"1","article-title":"Multi-agent reinforcement learning: A survey","volume-title":"Proc. 9th Int. Conf. Control, Autom., Robot. Vis.","author":"Lucian"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1095\/biolreprod56.2.328"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.01955"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9216774"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref17","article-title":"Temporal difference models: Model-free deep RL for model-based control","author":"Pong","year":"2018","journal-title":"arXiv:1802.09081"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/s23073762"},{"key":"ref19","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref20","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref21","first-page":"204","article-title":"Riemannian motion policy fusion through learnable Lyapunov function reshaping","volume-title":"Proc. Conf. Robot Learn.","author":"Mukadam"},{"key":"ref22","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2013.0480"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref25","article-title":"Riemannian motion policies","author":"Ratliff","year":"2018","journal-title":"arXiv:1801.02854"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7471613"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3319619.3321894"},{"key":"ref28","first-page":"395","article-title":"Hierarchical reinforcement learning for spoken dialogue systems","volume-title":"Proc. 41st Annu. Meeting Assoc. Comput. Linguistics","author":"Cuayhuitl"},{"issue":"1","key":"ref29","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968488"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161374"},{"issue":"10","key":"ref33","first-page":"442","article-title":"Hierarchically organized behavior and its neural foundations: A reinforcement learning perspective","volume":"12","author":"Botvinick","year":"2008","journal-title":"Trends Cognit. Sci."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3053422"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.092"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2017.05.026"},{"key":"ref37","first-page":"2040","article-title":"Learning vision-based reactive policies for obstacle avoidance","volume-title":"Proc. Conf. Robot Learn.","author":"Aljalbout"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3143196"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s00359-015-1023-6"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197343"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636097"},{"key":"ref42","first-page":"1457","article-title":"Learning reactive motion policies in multiple task spaces from human demonstrations","volume-title":"Proc. Conf. Robot Learn.","author":"Rana"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICARM54641.2022.9959550"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2022.799893"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/s21051571"},{"key":"ref46","article-title":"A review of safe reinforcement learning: Methods, theory and applications","author":"Gu","year":"2022","journal-title":"arXiv:2205.10330"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10283841.pdf?arnumber=10283841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T09:24:31Z","timestamp":1709371471000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10283841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3324039","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}