{"id":"https://openalex.org/W4414360392","doi":"https://doi.org/10.24963/ijcai.2025/590","title":"Approximated Behavioral Metric-based State Projection for Federated Reinforcement Learning","display_name":"Approximated Behavioral Metric-based State Projection for Federated Reinforcement Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360392","doi":"https://doi.org/10.24963/ijcai.2025/590"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/590","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/590","pdf_url":"https://www.ijcai.org/proceedings/2025/0590.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2025/0590.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zengxia Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengxia Guo","raw_affiliation_strings":["China University of Petroleum-Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017743551","display_name":"Bo An","orcid":"https://orcid.org/0000-0002-7064-7438"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohui An","raw_affiliation_strings":["China University of Petroleum-Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026597679","display_name":"Zhongqi Lu","orcid":"https://orcid.org/0000-0003-3242-0918"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongqi Lu","raw_affiliation_strings":["China University of Petroleum-Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing","institution_ids":["https://openalex.org/I204553293"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204553293"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33240101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5298","last_page":"5306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.8955000042915344,"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"}},"topics":[{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.8955000042915344,"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"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.8813999891281128,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8118000030517578,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7943000197410583},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.79339998960495},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.609000027179718},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5673999786376953},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5253000259399414},{"id":"https://openalex.org/keywords/state-information","display_name":"State information","score":0.44999998807907104},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4345000088214874}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7943000197410583},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.79339998960495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113999724388123},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.609000027179718},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5673999786376953},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C2985963534","wikidata":"https://www.wikidata.org/wiki/Q7603704","display_name":"State information","level":3,"score":0.44999998807907104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4426000118255615},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C2776854237","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information sharing","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3522999882698059},{"id":"https://openalex.org/C2777036070","wikidata":"https://www.wikidata.org/wiki/Q18393452","display_name":"Random projection","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C65557600","wikidata":"https://www.wikidata.org/wiki/Q7249451","display_name":"Projection method","level":3,"score":0.3359000086784363},{"id":"https://openalex.org/C2983203078","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Information gain","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30660000443458557},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.3034999966621399}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/590","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/590","pdf_url":"https://www.ijcai.org/proceedings/2025/0590.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2025/590","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/590","pdf_url":"https://www.ijcai.org/proceedings/2025/0590.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5982588113","display_name":null,"funder_award_id":"2462024XKQY003","funder_id":"https://openalex.org/F4320321547","funder_display_name":"China University of Petroleum, Beijing"}],"funders":[{"id":"https://openalex.org/F4320321547","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12"},{"id":"https://openalex.org/F4320326291","display_name":"Science Foundation of China University of Petroleum, Beijing","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414360392.pdf","grobid_xml":"https://content.openalex.org/works/W4414360392.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0],"reinforcement":[1],"learning":[2],"(FRL)":[3],"methods":[4],"usually":[5],"share":[6],"the":[7,33,46,79,108],"encrypted":[8],"local":[9],"state":[10,37],"or":[11],"policy":[12],"information":[13,98],"and":[14,50,77],"help":[15],"each":[16,75,101],"client":[17,76],"to":[18,44,65,112],"learn":[19,66],"from":[20],"others":[21],"while":[22],"preserving":[23],"everyone's":[24],"privacy.":[25],"In":[26],"this":[27],"work,":[28],"we":[29],"propose":[30],"that":[31],"sharing":[32],"approximated":[34],"behavior":[35],"metric-based":[36],"projection":[38,70,82],"function":[39,71],"is":[40],"a":[41,62,67,85],"promising":[42],"way":[43],"enhance":[45],"performance":[47],"of":[48,56,72,81],"FRL":[49,63],"concurrently":[51],"provides":[52,97],"an":[53],"effective":[54],"protection":[55],"sensitive":[57,93],"information.":[58],"We":[59,103],"introduce":[60],"FedRAG,":[61],"framework":[64],"computationally":[68],"practical":[69],"states":[73],"for":[74,100],"aggregating":[78],"parameters":[80],"functions":[83],"at":[84],"central":[86],"server.":[87],"The":[88],"FedRAG":[89],"approach":[90],"shares":[91],"no":[92],"task-specific":[94],"information,":[95],"yet":[96],"gain":[99],"client.":[102],"conduct":[104],"extensive":[105],"experiments":[106],"on":[107],"DeepMind":[109],"Control":[110],"Suite":[111],"demonstrate":[113],"insightful":[114],"results.":[115]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}