{"id":"https://openalex.org/W4416748895","doi":"https://doi.org/10.1109/iros60139.2025.11246087","title":"Symmetry-Guided Multi-Agent Inverse Reinforcement Learning","display_name":"Symmetry-Guided Multi-Agent Inverse Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748895","doi":"https://doi.org/10.1109/iros60139.2025.11246087"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5014464986","display_name":"Yongkai Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongkai Tian","raw_affiliation_strings":["Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101491985","display_name":"Yue Qi","orcid":"https://orcid.org/0000-0001-9304-1933"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yirong Qi","raw_affiliation_strings":["Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052005561","display_name":"Xin Yu","orcid":"https://orcid.org/0000-0003-0543-5567"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Yu","raw_affiliation_strings":["Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084470003","display_name":"Wenjun Wu","orcid":"https://orcid.org/0000-0002-2528-4893"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Wu","raw_affiliation_strings":["Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028701003","display_name":"Jie Luo","orcid":"https://orcid.org/0000-0002-4157-9931"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Luo","raw_affiliation_strings":["Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87761438,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7989","last_page":"7996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8090999722480774,"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":0.8090999722480774,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.10379999876022339,"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"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.007300000172108412,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7853000164031982},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5253000259399414},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.439300000667572},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.38760000467300415},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.34689998626708984}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7853000164031982},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7085000276565552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6274999976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5333999991416931},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2973000109195709}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":19,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W2015410655","https://openalex.org/W2051228319","https://openalex.org/W2124394479","https://openalex.org/W2498529546","https://openalex.org/W2789386227","https://openalex.org/W2994446013","https://openalex.org/W3163993681","https://openalex.org/W4206309409","https://openalex.org/W4323365454","https://openalex.org/W4327571609","https://openalex.org/W4383567286","https://openalex.org/W4387172174","https://openalex.org/W4393156884","https://openalex.org/W4400770903","https://openalex.org/W4401413807","https://openalex.org/W4403487523","https://openalex.org/W4405785078","https://openalex.org/W4413925740"],"related_works":[],"abstract_inverted_index":{"In":[0],"robotic":[1,69],"systems,":[2,74,105],"the":[3,10,58,77,100,114,152,165],"performance":[4],"of":[5,12,52,64,80,116,154,167],"reinforcement":[6,95],"learning":[7,96],"depends":[8],"on":[9,49],"rationality":[11],"predefined":[13],"reward":[14,19,39,59,119],"functions.":[15,120],"However,":[16],"manually":[17],"designed":[18],"functions":[20,40],"often":[21],"lead":[22],"to":[23,27,55],"policy":[24],"failures":[25],"due":[26],"inaccuracies.":[28],"Inverse":[29],"Reinforcement":[30],"Learning":[31],"(IRL)":[32],"addresses":[33],"this":[34,106,123,155],"problem":[35],"by":[36,99],"inferring":[37],"implicit":[38],"from":[41,146],"expert":[42,53,66],"demonstrations.":[43],"Nevertheless,":[44],"existing":[45,134],"methods":[46],"rely":[47],"heavily":[48],"large":[50],"amounts":[51],"demonstrations":[54,67],"accurately":[56],"recover":[57],"function.":[60],"The":[61],"high":[62],"cost":[63],"collecting":[65],"in":[68,72,92,103,159],"applications,":[70],"particularly":[71],"multi-robot":[73,161],"severely":[75],"hinders":[76],"practical":[78],"deployment":[79],"IRL.":[81],"Consequently,":[82],"improving":[83],"sample":[84,142],"efficiency":[85],"has":[86,163],"emerged":[87],"as":[88],"a":[89,127],"critical":[90],"challenge":[91],"multi-agent":[93,104,135],"inverse":[94],"(MIRL).":[97],"Inspired":[98],"symmetry":[101,112,132],"inherent":[102],"work":[107],"theoretically":[108],"demonstrates":[109],"that":[110,130],"leveraging":[111],"enables":[113],"recovery":[115],"more":[117],"accurate":[118],"Building":[121],"upon":[122],"insight,":[124],"we":[125],"propose":[126],"universal":[128],"framework":[129],"integrates":[131],"into":[133],"adversarial":[136],"IRL":[137],"algorithms,":[138],"thereby":[139],"significantly":[140],"enhancing":[141],"efficiency.":[143],"Experimental":[144],"results":[145],"multiple":[147],"challenging":[148],"tasks":[149],"have":[150],"demonstrated":[151],"effectiveness":[153],"framework.":[156],"Further":[157],"validation":[158],"physical":[160],"systems":[162],"shown":[164],"practicality":[166],"our":[168],"method.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}