{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T12:38:39Z","timestamp":1742647119827,"version":"3.37.3"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T00:00:00Z","timestamp":1737417600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T00:00:00Z","timestamp":1737417600000},"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":[],"published-print":{"date-parts":[[2025,1,21]]},"DOI":"10.1109\/sii59315.2025.10870944","type":"proceedings-article","created":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T18:17:07Z","timestamp":1739384227000},"page":"1556-1562","source":"Crossref","is-referenced-by-count":1,"title":["Task-priority Intermediated Hierarchical Distributed Policies: Reinforcement Learning of Adaptive Multi-robot Cooperative Transport"],"prefix":"10.1109","author":[{"given":"Yusei","family":"Naito","sequence":"first","affiliation":[{"name":"Toyota Motor Corporation,R-Frontier Division, Frontier Research Center,Aichi,Japan,471-8571"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohiko","family":"Jimbo","sequence":"additional","affiliation":[{"name":"Toyota Central R&D LABS., Inc.,Aichi,Japan,480-1192"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tadashi","family":"Odashima","sequence":"additional","affiliation":[{"name":"Toyota Motor Corporation,R-Frontier Division, Frontier Research Center,Aichi,Japan,471-8571"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takamitsu","family":"Matsubara","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology (NAIST),Graduate School of Information Science,Nara,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3341105.3373980"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2018.00059"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943253"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92790-5_16"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636344"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.431"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911404579"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202278"},{"key":"ref9","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Lowe"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561274"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref13","first-page":"3307","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Nachum"},{"key":"ref14","first-page":"24611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3270034"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160216"},{"article-title":"Isaac gym: High performance GPU based physics simulation for robot learning","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Makoviychuk","key":"ref18"}],"event":{"name":"2025 IEEE\/SICE International Symposium on System Integration (SII)","start":{"date-parts":[[2025,1,21]]},"location":"Munich, Germany","end":{"date-parts":[[2025,1,24]]}},"container-title":["2025 IEEE\/SICE International Symposium on System Integration (SII)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10870372\/10870581\/10870944.pdf?arnumber=10870944","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T19:50:02Z","timestamp":1740081002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10870944\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,21]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/sii59315.2025.10870944","relation":{},"subject":[],"published":{"date-parts":[[2025,1,21]]}}}