{"id":"https://openalex.org/W4389077465","doi":"https://doi.org/10.1109/icmlc58545.2023.10328010","title":"Federated Reinforcement Learning for Sharing Experiences Between Multiple Workers","display_name":"Federated Reinforcement Learning for Sharing Experiences Between Multiple Workers","publication_year":2023,"publication_date":"2023-07-09","ids":{"openalex":"https://openalex.org/W4389077465","doi":"https://doi.org/10.1109/icmlc58545.2023.10328010"},"language":"en","primary_location":{"id":"doi:10.1109/icmlc58545.2023.10328010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc58545.2023.10328010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Machine Learning and Cybernetics (ICMLC)","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/A5112116231","display_name":"Wenliang Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenliang Feng","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China,518060"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China,518060","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349055","display_name":"Han Liu","orcid":"https://orcid.org/0000-0002-7731-8258"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Liu","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China,518060"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China,518060","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114858844","display_name":"Xiaogang Peng","orcid":"https://orcid.org/0009-0009-7918-8694"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaogang Peng","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China,518060"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China,518060","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":1.0889,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80367941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"440","last_page":"445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.9876000285148621,"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":0.9790999889373779,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9324121475219727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7826845645904541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5889502763748169},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5771979689598083},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5184228420257568},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46194300055503845},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.45627492666244507},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34653592109680176},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1491711437702179}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9324121475219727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7826845645904541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5889502763748169},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5771979689598083},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5184228420257568},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46194300055503845},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.45627492666244507},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34653592109680176},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1491711437702179},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmlc58545.2023.10328010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc58545.2023.10328010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Machine Learning and Cybernetics (ICMLC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4399999976158142,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G655638088","display_name":null,"funder_award_id":"62106147","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2904246096","https://openalex.org/W2911450448","https://openalex.org/W2963802910","https://openalex.org/W2968937098","https://openalex.org/W2994967560","https://openalex.org/W3005294098","https://openalex.org/W3016207298","https://openalex.org/W3105018016","https://openalex.org/W3161868942","https://openalex.org/W3165469371","https://openalex.org/W3167995857","https://openalex.org/W3205598877","https://openalex.org/W4200635426","https://openalex.org/W4212774754","https://openalex.org/W4214717370","https://openalex.org/W4285243594","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6739455066","https://openalex.org/W6773268965","https://openalex.org/W6779265984","https://openalex.org/W6810897048","https://openalex.org/W6840065948"],"related_works":["https://openalex.org/W2371091044","https://openalex.org/W2171010636","https://openalex.org/W87513465","https://openalex.org/W1966803121","https://openalex.org/W2391666574","https://openalex.org/W2786230833","https://openalex.org/W3203256658","https://openalex.org/W2352650970","https://openalex.org/W1544514152","https://openalex.org/W1493952344"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,24,52,78,86,119],"has":[2],"been":[3],"successfully":[4],"applied":[5,98],"in":[6,20,35,106],"various":[7],"fields,":[8],"such":[9,32],"as":[10],"games":[11],"and":[12,38,88,103,109],"robots.":[13],"However,":[14],"there":[15],"are":[16],"still":[17],"some":[18],"issues":[19],"the":[21,67,71,85,90,100,110,118],"traditional":[22],"reinforcement":[23,51],"paradigm":[25],"that":[26,54,113],"involves":[27],"one":[28],"agent":[29,74],"per":[30],"environment,":[31],"low":[33],"efficiency":[34],"data":[36,60],"generation":[37],"insufficient":[39],"amount":[40],"of":[41,64,92,117],"training":[42,63],"data.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"propose":[48],"a":[49,114],"federated":[50],"framework":[53,69,96],"utilizes":[55],"multiple":[56],"agents":[57,82],"to":[58,75,99],"generate":[59],"for":[61,83],"simultaneous":[62],"models.":[65],"Specifically,":[66],"proposed":[68,95],"allows":[70],"best":[72],"performing":[73],"share":[76],"its":[77],"experience":[79],"with":[80],"other":[81],"improving":[84],"performance":[87,120],"protecting":[89],"privacy":[91],"agents.":[93],"The":[94],"is":[97],"Cart-pole,":[101],"Acrobot":[102],"LunarLander":[104],"environments":[105],"OpenAI":[107],"Gym,":[108],"results":[111],"show":[112],"significant":[115],"improvement":[116],"can":[121],"be":[122],"achieved":[123],"by":[124],"adopting":[125],"our":[126],"framework.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}