{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T20:51:27Z","timestamp":1770238287994,"version":"3.49.0"},"reference-count":32,"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\/sii59315.2025.10870902","type":"proceedings-article","created":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T18:17:07Z","timestamp":1739384227000},"page":"1548-1555","source":"Crossref","is-referenced-by-count":6,"title":["Reinforcement Learning of Multi-robot Task Allocation for Multi-object Transportation with Infeasible Tasks"],"prefix":"10.1109","author":[{"given":"Yuma","family":"Shida","sequence":"first","affiliation":[{"name":"Toyota Motor Corporation,R-Frontier Division, Frontier Research Center,Aichi,Japan"}],"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"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takamitsu","family":"Matsubara","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology,Division of Information Science, Graduate School of Science and Technology,Nara,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364904045564"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MRS50823.2021.9620678"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2021.106673"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2022.11.002"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2023.104492"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911404579"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202278"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-4-431-55879-8_24"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2006.876939"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2009.2022423"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2021.11.249"},{"key":"ref13","article-title":"An overview of multi-agent reinforcement learning from game theoretical perspective","author":"Yang","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.431"},{"key":"ref15","first-page":"16509","article-title":"Multi-agent reinforcement learning is a sequence modeling problem","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Wen","year":"2022"},{"key":"ref16","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Lowe","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636344"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IRDS.2002.1041529"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02483-3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-31293-4_19"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1098\/rspb.1998.0299"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(99)00065-2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.1040.0334"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLC.2009.5212216"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2019.06.024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2902846"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943253"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3062457"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92790-5_16"},{"key":"ref32","article-title":"Maddpg algorithm","volume-title":"github","author":"Lowe"}],"event":{"name":"2025 IEEE\/SICE International Symposium on System Integration (SII)","location":"Munich, Germany","start":{"date-parts":[[2025,1,21]]},"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\/10870902.pdf?arnumber=10870902","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T19:49:55Z","timestamp":1740080995000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10870902\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,21]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/sii59315.2025.10870902","relation":{},"subject":[],"published":{"date-parts":[[2025,1,21]]}}}