{"id":"https://openalex.org/W4413924999","doi":"https://doi.org/10.1109/icra55743.2025.11127727","title":"HARP: Human-Assisted Regrouping With Permutation Invariant Critic for Multi-Agent Reinforcement Learning","display_name":"HARP: Human-Assisted Regrouping With Permutation Invariant Critic for Multi-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413924999","doi":"https://doi.org/10.1109/icra55743.2025.11127727"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127727","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007913722","display_name":"Huawen Hu","orcid":"https://orcid.org/0000-0002-6009-7516"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huawen Hu","raw_affiliation_strings":["Northwestern Polytechnical University,Xi&#x0027;an,China,710072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi&#x0027;an,China,710072","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045408151","display_name":"Enze Shi","orcid":"https://orcid.org/0000-0002-7416-8733"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enze Shi","raw_affiliation_strings":["Northwestern Polytechnical University,Xi&#x0027;an,China,710072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi&#x0027;an,China,710072","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026015955","display_name":"Chenxi Yue","orcid":"https://orcid.org/0009-0008-8106-5338"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxi Yue","raw_affiliation_strings":["Northwestern Polytechnical University,Xi&#x0027;an,China,710072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi&#x0027;an,China,710072","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuocun Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuocun Yang","raw_affiliation_strings":["Northwestern Polytechnical University,Xi&#x0027;an,China,710072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi&#x0027;an,China,710072","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037769489","display_name":"Zihao Wu","orcid":"https://orcid.org/0000-0002-4389-2980"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zihao Wu","raw_affiliation_strings":["University of Georgia,Athens,GA,USA,30602"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Georgia,Athens,GA,USA,30602","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108094923","display_name":"Yiwei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiwei Li","raw_affiliation_strings":["University of Georgia,Athens,GA,USA,30602"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Georgia,Athens,GA,USA,30602","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080757911","display_name":"Tianyang Zhong","orcid":"https://orcid.org/0009-0002-4124-1129"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyang Zhong","raw_affiliation_strings":["Northwestern Polytechnical University,Xi&#x0027;an,China,710072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi&#x0027;an,China,710072","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665425","display_name":"Tuo Zhang","orcid":"https://orcid.org/0000-0002-6075-3384"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tuo Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Xi&#x0027;an,China,710072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi&#x0027;an,China,710072","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100647156","display_name":"Tianming Liu","orcid":"https://orcid.org/0000-0002-8132-9048"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianming Liu","raw_affiliation_strings":["University of Georgia,Athens,GA,USA,30602"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Georgia,Athens,GA,USA,30602","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100748676","display_name":"Shu Zhang","orcid":"https://orcid.org/0000-0002-5873-634X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Xi&#x0027;an,China,710072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi&#x0027;an,China,710072","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5007913722"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11407097,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4287","last_page":"4293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7569000124931335,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7569000124931335,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/harp","display_name":"HARP","score":0.9082542061805725},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7252125144004822},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6295415163040161},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5679242014884949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4878840446472168},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.4465571641921997},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.4201304316520691},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16367051005363464},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.10338452458381653},{"id":"https://openalex.org/keywords/art-history","display_name":"Art history","score":0.0746980607509613}],"concepts":[{"id":"https://openalex.org/C2776030095","wikidata":"https://www.wikidata.org/wiki/Q5628954","display_name":"HARP","level":2,"score":0.9082542061805725},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7252125144004822},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6295415163040161},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5679242014884949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4878840446472168},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.4465571641921997},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.4201304316520691},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16367051005363464},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.10338452458381653},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.0746980607509613},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127727","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2110064869","https://openalex.org/W2130069391","https://openalex.org/W2604847142","https://openalex.org/W2747213132","https://openalex.org/W2799745602","https://openalex.org/W2877093712","https://openalex.org/W2996868001","https://openalex.org/W4323644252","https://openalex.org/W4383108558","https://openalex.org/W4383108566","https://openalex.org/W4383172036","https://openalex.org/W4386702654","https://openalex.org/W4391399751","https://openalex.org/W4392515548","https://openalex.org/W4401024731","https://openalex.org/W4401414533","https://openalex.org/W4401414913","https://openalex.org/W4401417008","https://openalex.org/W4401417103","https://openalex.org/W4401417401","https://openalex.org/W4405910844","https://openalex.org/W4410040027"],"related_works":["https://openalex.org/W2091083843","https://openalex.org/W424580262","https://openalex.org/W2597835809","https://openalex.org/W4300904561","https://openalex.org/W619121476","https://openalex.org/W2807944126","https://openalex.org/W4248186805","https://openalex.org/W605528597","https://openalex.org/W4206233823","https://openalex.org/W2494202692"],"abstract_inverted_index":{"Human-in-the-loop":[0],"reinforcement":[1,58],"learning":[2,9,59],"integrates":[3,66],"human":[4,30,39,72,104],"expertise":[5],"to":[6,80,94,113,122,134],"accelerate":[7],"agent":[8,68],"and":[10,14,27,41,77,106,115,140],"provide":[11],"critical":[12],"guidance":[13,83,137],"feedback":[15],"in":[16],"complex":[17],"fields.":[18],"However,":[19],"many":[20],"existing":[21],"approaches":[22],"focus":[23],"on":[24],"single-agent":[25],"tasks":[26],"require":[28],"continuous":[29],"involvement":[31],"during":[32,74],"the":[33,38,108],"training":[34],"process,":[35],"significantly":[36],"increasing":[37],"workload":[40],"limiting":[42],"scalability.":[43],"In":[44,126],"this":[45],"paper,":[46],"we":[47],"propose":[48],"HARP":[49,65],"(HumanAssisted":[50],"Regrouping":[51],"with":[52,70,84],"Permutation":[53,109],"Invariant":[54,110],"Critic),":[55],"a":[56],"multi-agent":[57],"framework":[60],"designed":[61],"for":[62],"group-oriented":[63],"tasks.":[64],"automatic":[67],"regrouping":[69],"strategic":[71],"assistance":[73,105],"deployment,":[75],"enabling":[76],"allowing":[78,119],"non-experts":[79,139],"offer":[81],"effective":[82],"minimal":[85],"intervention.":[86],"During":[87],"training,":[88],"agents":[89],"dynamically":[90],"adjust":[91],"their":[92],"groupings":[93],"optimize":[95],"collaborative":[96],"task":[97],"completion.":[98],"When":[99],"deployed,":[100],"they":[101],"actively":[102],"seek":[103],"utilize":[107],"Group":[111],"Critic":[112],"evaluate":[114],"refine":[116],"human-proposed":[117],"groupings,":[118],"non-expert":[120],"users":[121],"contribute":[123],"valuable":[124],"suggestions.":[125],"multiple":[127],"collaboration":[128],"scenarios,":[129],"our":[130],"approach":[131],"is":[132],"able":[133],"leverage":[135],"limited":[136],"from":[138],"enhance":[141],"performance.":[142],"The":[143],"project":[144],"can":[145],"be":[146],"found":[147],"at":[148],"https://github.com/huawen-hu/HARP.":[149]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
