{"id":"https://openalex.org/W4416250776","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227302","title":"Byzantine-Resilient Decentralized Parallel Policy Gradient","display_name":"Byzantine-Resilient Decentralized Parallel Policy Gradient","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250776","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227302"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227302","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5101999069","display_name":"Qifeng Lin","orcid":"https://orcid.org/0000-0003-0523-8811"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qifeng Lin","raw_affiliation_strings":["Sun Yat-Sen University"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100741261","display_name":"Yi Huang","orcid":"https://orcid.org/0000-0001-7774-1024"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Huang","raw_affiliation_strings":["Sun Yat-Sen University"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029820392","display_name":"Qing Ling","orcid":"https://orcid.org/0000-0003-4222-5964"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing Ling","raw_affiliation_strings":["Sun Yat-Sen University"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101999069"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19430882,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7013000249862671,"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":0.7013000249862671,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.034299999475479126,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.033799998462200165,"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/inefficiency","display_name":"Inefficiency","score":0.7231000065803528},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.64410001039505},{"id":"https://openalex.org/keywords/decentralised-system","display_name":"Decentralised system","score":0.5306000113487244},{"id":"https://openalex.org/keywords/information-exchange","display_name":"Information exchange","score":0.33970001339912415},{"id":"https://openalex.org/keywords/byzantine-fault-tolerance","display_name":"Byzantine fault tolerance","score":0.31310001015663147},{"id":"https://openalex.org/keywords/data-exchange","display_name":"Data exchange","score":0.31040000915527344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573999762535095},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.7231000065803528},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.64410001039505},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6243000030517578},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.5306000113487244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34290000796318054},{"id":"https://openalex.org/C189693848","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information exchange","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C168021876","wikidata":"https://www.wikidata.org/wiki/Q1353446","display_name":"Byzantine fault tolerance","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C15845906","wikidata":"https://www.wikidata.org/wiki/Q1172338","display_name":"Data exchange","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3050000071525574},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.2847000062465668},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28209999203681946},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2752000093460083},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.2599000036716461}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227302","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":28,"referenced_works":["https://openalex.org/W1981437899","https://openalex.org/W2074796812","https://openalex.org/W2091565802","https://openalex.org/W2101517602","https://openalex.org/W2144446635","https://openalex.org/W2152083440","https://openalex.org/W2962856794","https://openalex.org/W2994803162","https://openalex.org/W3041260350","https://openalex.org/W3089075644","https://openalex.org/W3119097918","https://openalex.org/W3119186746","https://openalex.org/W3126790783","https://openalex.org/W3163894240","https://openalex.org/W3202150208","https://openalex.org/W3209083247","https://openalex.org/W4221100794","https://openalex.org/W4224940954","https://openalex.org/W4252654521","https://openalex.org/W4312661392","https://openalex.org/W4317553819","https://openalex.org/W4376478835","https://openalex.org/W4385894359","https://openalex.org/W4393147123","https://openalex.org/W4399451134","https://openalex.org/W4399485132","https://openalex.org/W4402351363","https://openalex.org/W4402352370"],"related_works":[],"abstract_inverted_index":{"Parallel":[0],"reinforcement":[1],"learning":[2,65,100],"(RL)":[3],"is":[4],"an":[5],"important":[6],"approach":[7],"to":[8,26,90,139],"dealing":[9],"with":[10,121],"the":[11,38,62,94,114,133,141,144],"challenge":[12],"of":[13,96,143],"data":[14],"inefficiency":[15],"in":[16,78,119],"RL.":[17],"The":[18],"existing":[19],"distributed":[20],"framework":[21],"requires":[22],"a":[23,48,68,126],"central":[24],"server":[25],"collect":[27],"messages":[28,89],"from":[29,37],"multiple":[30],"agents":[31,63,83],"for":[32,71,93],"cooperation,":[33],"and":[34,147],"thus":[35],"suffers":[36],"communication":[39],"bottleneck.":[40],"To":[41],"address":[42],"this":[43],"issue,":[44],"we":[45,103,135],"first":[46],"develop":[47],"decentralized":[49,55,107],"parallel":[50,56,108],"RL":[51],"algorithm,":[52],"named":[53],"as":[54],"policy":[57,109],"gradient":[58,110],"(DP-PG),":[59],"within":[60],"which":[61],"exchange":[64],"parameters":[66],"via":[67],"peer-to-peer":[69],"network":[70],"cooperation.":[72],"However,":[73],"Byzantine":[74],"attacks":[75],"are":[76],"ubiquitous":[77],"multi-agent":[79],"systems,":[80],"where":[81],"malicious":[82],"could":[84],"send":[85],"random":[86],"or":[87,98],"well-designed":[88],"their":[91],"neighbors":[92],"sake":[95],"hindering":[97],"destroying":[99],"processes.":[101],"Therefore,":[102],"further":[104],"propose":[105],"Byzantine-resilient":[106],"(BRDP-PG)":[111],"that":[112],"replaces":[113],"vulnerable":[115],"weighted":[116],"mean":[117,124],"aggregation":[118,128],"DP-PG":[120,146],"coordinate":[122],"trimmed":[123],"(CTM),":[125],"robust":[127],"rule.":[129],"Last":[130],"but":[131],"not":[132],"least,":[134],"conduct":[136],"numerical":[137],"experiments":[138],"confirm":[140],"effectiveness":[142],"proposed":[145],"BRDP-PG.":[148]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}