{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:24:18Z","timestamp":1787012658170,"version":"3.56.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"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":["62025304"],"award-info":[{"award-number":["62025304"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62273054"],"award-info":[{"award-number":["62273054"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/lra.2024.3390588","type":"journal-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T13:39:43Z","timestamp":1713361183000},"page":"5377-5384","source":"Crossref","is-referenced-by-count":17,"title":["Heterogeneous Embodied Multi-Agent Collaboration"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6447-2926","authenticated-orcid":false,"given":"Xinzhu","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9816-0103","authenticated-orcid":false,"given":"Di","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0034-9037","authenticated-orcid":false,"given":"Xinyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, the School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4042-6044","authenticated-orcid":false,"given":"Huaping","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00691"},{"key":"ref2","article-title":"Visual semantic navigation using scene priors","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Yang","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00586"},{"key":"ref6","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Omidshafiei","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref8","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal","year":"2019"},{"key":"ref9","first-page":"11853","article-title":"Learning implicit credit assignment for cooperative multi-agent reinforcement learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Zhou","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00685"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_28"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_29"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145964"},{"key":"ref14","article-title":"Collaborative visual navigation","author":"Wang","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_39"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.032"},{"key":"ref17","article-title":"Heterogeneous multi-agent reinforcement learning for unknown environment mapping","author":"Wakilpoor","year":"2020"},{"issue":"129","key":"ref18","first-page":"1","article-title":"On the approximation of cooperative heterogeneous multi-agent reinforcement learning (MARL) using mean field control (MFC)","volume":"23","author":"Mondal","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.044"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_28"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_21"},{"key":"ref22","article-title":"CH-MARL: A multimodal benchmark for cooperative, heterogeneous multi-agent reinforcement learning","author":"Sharma","year":"2022"},{"key":"ref23","first-page":"5982","article-title":"ProcTHOR: Large-scale embodied AI using procedural generation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Deitke","year":"2022"},{"key":"ref24","first-page":"517","article-title":"Learning hierarchical relationships for object-goal navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Pal","year":"2021"},{"key":"ref25","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Fried","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2972281"},{"key":"ref27","article-title":"Learning to explore using active neural slam","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Chaplot","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1108\/RIA-11-2022-0269"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.368"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10148-y"},{"key":"ref33","article-title":"Cooperative task and motion planning for multi-arm assembly systems","author":"Chen","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01565"},{"key":"ref36","first-page":"1538","article-title":"Tarmac: Targeted multi-agent communication","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Das","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00416"},{"key":"ref38","article-title":"AI2-THOR: An interactive 3D environment for visual AI","author":"Kolve","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf","year":"2017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"issue":"1","key":"ref44","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref45","article-title":"Tom2c: Target-oriented multi-agent communication and cooperation with theory of mind","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Wang","year":"2022"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10504377\/10504634.pdf?arnumber=10504634","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T15:04:24Z","timestamp":1714748664000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10504634\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":45,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3390588","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}