{"id":"https://openalex.org/W4387185467","doi":"https://doi.org/10.3233/faia230291","title":"Expert-Free Online Transfer Learning in Multi-Agent Reinforcement Learning","display_name":"Expert-Free Online Transfer Learning in Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387185467","doi":"https://doi.org/10.3233/faia230291"},"language":"en","primary_location":{"id":"doi:10.3233/faia230291","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230291","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230291","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230291","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5105633952","display_name":"Alberto Castagna","orcid":null},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Alberto Castagna","raw_affiliation_strings":["School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059738292","display_name":"Ivana Duspari\u0107","orcid":"https://orcid.org/0000-0003-0621-5400"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Ivana Dusparic","raw_affiliation_strings":["School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5105633952"],"corresponding_institution_ids":["https://openalex.org/I205274468"],"apc_list":null,"apc_paid":null,"fwci":0.5238,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6866768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9839000105857849,"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":0.9839000105857849,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9817000031471252,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9121000170707703,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8247838616371155},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7775154113769531},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.7062122225761414},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6710959672927856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6539047360420227},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.601384162902832},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5866379737854004},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.5067499279975891},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.4327295422554016},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.13245812058448792},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11638829112052917}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8247838616371155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7775154113769531},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7062122225761414},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6710959672927856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6539047360420227},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.601384162902832},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5866379737854004},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.5067499279975891},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.4327295422554016},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.13245812058448792},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11638829112052917},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230291","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230291","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230291","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230291","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230291","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230291","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2322257346","display_name":null,"funder_award_id":"18/CRT/622","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G2394637485","display_name":null,"funder_award_id":"18/CRT/6223","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G4915346836","display_name":null,"funder_award_id":"18/CRT/6","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387185467.pdf","grobid_xml":"https://content.openalex.org/works/W4387185467.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W139596442","https://openalex.org/W1515851193","https://openalex.org/W1529399279","https://openalex.org/W1969685488","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2253991908","https://openalex.org/W2607198029","https://openalex.org/W2620645529","https://openalex.org/W2739657930","https://openalex.org/W2740302738","https://openalex.org/W2756826236","https://openalex.org/W2837981523","https://openalex.org/W2899205164","https://openalex.org/W2906669385","https://openalex.org/W2944481713","https://openalex.org/W2951799221","https://openalex.org/W2963099939","https://openalex.org/W2963616477","https://openalex.org/W2964067469","https://openalex.org/W2976108375","https://openalex.org/W2978894944","https://openalex.org/W2996868001","https://openalex.org/W3008141518","https://openalex.org/W3013348603","https://openalex.org/W3022445573","https://openalex.org/W3037582147","https://openalex.org/W3103078407","https://openalex.org/W3109234674","https://openalex.org/W3121342653","https://openalex.org/W3210485068","https://openalex.org/W3214964808","https://openalex.org/W4280521017","https://openalex.org/W4323072986","https://openalex.org/W4387185467","https://openalex.org/W4394667800"],"related_works":["https://openalex.org/W4288040045","https://openalex.org/W4308262314","https://openalex.org/W4308233397","https://openalex.org/W4225907548","https://openalex.org/W4319083788","https://openalex.org/W4382286161","https://openalex.org/W4386213806","https://openalex.org/W2983785000","https://openalex.org/W2960456850","https://openalex.org/W3021430260"],"abstract_inverted_index":{"Transfer":[0,71],"learning":[1,30,82],"in":[2,14,64,83,158],"Reinforcement":[3],"Learning":[4,72],"(RL)":[5],"has":[6],"been":[7],"widely":[8],"studied":[9],"to":[10,28,58,97,182,204],"overcome":[11],"training":[12,36],"challenges":[13],"Deep-RL,":[15],"i.e.,":[16],"exploration":[17],"cost,":[18],"data":[19],"availability":[20],"and":[21,91,95,111,149,154,168],"convergence":[22],"time,":[23],"by":[24,48],"bootstrapping":[25],"external":[26,192],"knowledge":[27,96],"enhance":[29],"phase.":[31],"While":[32],"this":[33,65],"overcomes":[34],"the":[35,46,49,205,208],"issues":[37],"on":[38,108],"a":[39,42,56,146,163],"novice":[40],"agent,":[41],"good":[43],"understanding":[44],"of":[45,113,132,184,207],"task":[47,209],"expert":[50,88,156,190],"agent":[51,89,94],"is":[52],"required":[53],"for":[54],"such":[55],"transfer":[57,81,92,105],"be":[59,98],"effective.":[60],"As":[61],"an":[62,74,130,201],"alternative,":[63],"paper":[66],"we":[67,119],"propose":[68,121],"Expert-Free":[69],"Online":[70],"(EF-OnTL),":[73],"algorithm":[75],"that":[76,134,176,183],"enables":[77],"expert-free":[78],"real-time":[79],"dynamic":[80],"multi-agent":[84],"system.":[85],"No":[86],"dedicated":[87],"exists,":[90],"source":[93],"transferred":[99],"are":[100],"dynamically":[101],"selected":[102],"at":[103],"each":[104],"step":[106],"based":[107],"agents\u2019":[109],"performance":[110,181],"level":[112],"uncertainty.":[114],"To":[115],"improve":[116],"uncertainty":[117,136],"estimation,":[118],"also":[120],"State":[122],"Action":[123],"Reward":[124],"Next-State":[125],"Random":[126],"Network":[127],"Distillation":[128],"(sars-RND),":[129],"extension":[131],"RND":[133],"estimates":[135],"from":[137],"RL":[138],"agent-environment":[139],"interaction.":[140],"We":[141],"demonstrate":[142],"EF-OnTL":[143,177,197],"effectiveness":[144],"against":[145],"no-transfer":[147,199],"scenario":[148],"state-of-the-art":[150],"advice-based":[151,185],"baselines,":[152],"with":[153,200],"without":[155],"agents,":[157,191],"three":[159],"benchmark":[160],"tasks:":[161],"Cart-Pole,":[162],"grid-based":[164],"Multi-Team":[165],"Predator-Prey":[166],"(MT-PP)":[167],"Half":[169],"Field":[170],"Offense":[171],"(HFO).":[172],"Our":[173],"results":[174],"show":[175],"achieves":[178],"overall":[179],"comparable":[180],"approaches,":[186],"while":[187],"not":[188],"requiring":[189],"input,":[193],"nor":[194],"threshold":[195],"tuning.":[196],"outperforms":[198],"improvement":[202],"related":[203],"complexity":[206],"addressed.":[210]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}