{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:39:36Z","timestamp":1757608776398,"version":"3.44.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127727","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"4287-4293","source":"Crossref","is-referenced-by-count":0,"title":["HARP: Human-Assisted Regrouping With Permutation Invariant Critic for Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Huawen","family":"Hu","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Xi&#x0027;an,China,710072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enze","family":"Shi","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Xi&#x0027;an,China,710072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenxi","family":"Yue","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Xi&#x0027;an,China,710072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuocun","family":"Yang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Xi&#x0027;an,China,710072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihao","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Georgia,Athens,GA,USA,30602"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiwei","family":"Li","sequence":"additional","affiliation":[{"name":"University of Georgia,Athens,GA,USA,30602"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyang","family":"Zhong","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Xi&#x0027;an,China,710072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Xi&#x0027;an,China,710072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianming","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Georgia,Athens,GA,USA,30602"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Xi&#x0027;an,China,710072"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160919"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611322"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160558"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161310"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610965"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.anbehav.2006.10.008"},{"key":"ref7","first-page":"24018","article-title":"Vast: Value function factorization with variable agent subteams","volume":"34","author":"Phan","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/820"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3733592"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10945"},{"key":"ref11","first-page":"63222","article-title":"Breadcrumbs to the goal: goal-conditioned exploration from human-in-the-loop feedback","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Torne","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610505"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610595"},{"key":"ref14","article-title":"Battlesnake challenge: A multi-agent reinforcement learning playground with human-in-theloop","author":"Chung","year":"2020","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.15348"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127485"},{"key":"ref17","article-title":"The StarCraft Multi-Agent Challenge","volume":"abs\/1902.04043","author":"Samvelyan","year":"2019","journal-title":"CoRR"},{"key":"ref18","first-page":"9876","article-title":"Roma: Multi-agent reinforcement learning with emergent roles","volume-title":"International Conference on Machine Learning","author":"Wang","year":"2020"},{"key":"ref19","article-title":"Rode: Learning roles to decompose multi-agent tasks","author":"Wang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref20","first-page":"5711","article-title":"Self-organized group for cooperative multi-agent reinforcement learning","volume":"35","author":"Shao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","article-title":"Automatic grouping for efficient cooperative multi-agent reinforcement learning","volume":"36","author":"Zang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/434"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2008.4640845"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-018-0839-z"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6036"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611425"},{"volume-title":"Introducing OpenAI o1-preview","year":"2024","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref29","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems","author":"Sunehag","year":"2018"},{"key":"ref30","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"International conference on machine learning","author":"Son","year":"2019"},{"key":"ref31","first-page":"590","article-title":"Pic: permutation invariant critic for multi-agent deep reinforcement learning","volume-title":"Conference on Robot Learning","author":"Liu","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3254460"},{"key":"ref33","article-title":"Dt\/mars-cyclegan: Improved object detection for mars phenotyping robot","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3314762"},{"key":"ref35","first-page":"212","article-title":"i-sim2real: Reinforcement learning of robotic policies in tight humanrobot interaction loops","volume-title":"Conference on Robot Learning","author":"Abeyruwan","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jai.2024.12.003"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127727.pdf?arnumber=11127727","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:14:38Z","timestamp":1756880078000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127727\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127727","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}