{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T22:41:46Z","timestamp":1761172906928,"version":"build-2065373602"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62263025"],"award-info":[{"award-number":["62263025"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,15]]},"DOI":"10.1109\/spml66318.2025.11199827","type":"proceedings-article","created":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T17:07:16Z","timestamp":1761066436000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Agent Reinforcement Learning for Path Planning with Various Random and Fixed Obstacle Configurations"],"prefix":"10.1109","author":[{"given":"Jinglong","family":"Liu","sequence":"first","affiliation":[{"name":"School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xitai","family":"Na","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenda","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tuo","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenduo","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingdi","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Inner Mongolia University,Inner Mongolia,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-97672-9_40"},{"key":"ref2","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning[C]","volume-title":"International conference on machine learning","author":"Yang","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref4","article-title":"Optimistic Multi-Agent Policy Gradient for Cooperative Tasks[J]","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488669"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4171"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.001"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/63"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3089120"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2021.3081996"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340876"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560748"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974648"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11771-022-4924-x"},{"key":"ref17","article-title":"Hyar: Addressing discrete-continuous action reinforcement learning via hybrid action representation[J]","author":"Li","year":"2021","journal-title":"arXiv preprint"},{"key":"ref18","first-page":"2720927221","article-title":"Is bang-bang control all you need? solving continuous control with bernoulli policies[J]","volume":"34","author":"Seyde","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.108089"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2021.3081996"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2023.3298292"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811643"},{"key":"ref23","first-page":"1394","article-title":"The emergence of adversarial communication in multi-agent reinforcement learning[C]","volume-title":"Conference on Robot Learning","author":"Blumenkamp","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s12204-024-2755-7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062803"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s12204-023-2653-4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3203072"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017643"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511546877"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.001"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"}],"event":{"name":"2025 IEEE 8th International Conference on Signal Processing and Machine Learning (SPML)","start":{"date-parts":[[2025,7,15]]},"location":"Hohhot, China","end":{"date-parts":[[2025,7,17]]}},"container-title":["2025 IEEE 8th International Conference on Signal Processing and Machine Learning (SPML)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11199749\/11199750\/11199827.pdf?arnumber=11199827","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T05:36:50Z","timestamp":1761111410000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11199827\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,15]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/spml66318.2025.11199827","relation":{},"subject":[],"published":{"date-parts":[[2025,7,15]]}}}