{"id":"https://openalex.org/W4387172276","doi":"https://doi.org/10.3233/faia230298","title":"Selective Learning for Sample-Efficient Training in Multi-Agent Sparse Reward Tasks","display_name":"Selective Learning for Sample-Efficient Training in Multi-Agent Sparse Reward Tasks","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387172276","doi":"https://doi.org/10.3233/faia230298"},"language":"en","primary_location":{"id":"doi:10.3233/faia230298","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230298","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230298","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/FAIA230298","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073200323","display_name":"Xinning Chen","orcid":"https://orcid.org/0009-0009-9376-0503"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinning Chen","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362298","display_name":"Xuan Liu","orcid":"https://orcid.org/0000-0002-1652-2466"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Liu","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088834123","display_name":"Yanwen Ba","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwen Ba","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005250767","display_name":"Shigeng Zhang","orcid":"https://orcid.org/0000-0001-5351-7239"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shigeng Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088885490","display_name":"Bo Ding","orcid":"https://orcid.org/0000-0002-1236-8318"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ding","raw_affiliation_strings":["School of Computer Science, National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kenli Li","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.339,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93478771,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":95},"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/T13283","display_name":"Mental Health Research Topics","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13283","display_name":"Mental Health Research Topics","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.9524000287055969,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13219","display_name":"Mind wandering and attention","score":0.9455999732017517,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6194878816604614},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6129040122032166},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5249918699264526},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5120638012886047},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4824657738208771},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4434022307395935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39707714319229126},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3963485658168793},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1477142870426178}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6194878816604614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6129040122032166},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5249918699264526},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5120638012886047},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4824657738208771},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4434022307395935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39707714319229126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3963485658168793},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1477142870426178},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230298","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230298","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230298","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/faia230298","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230298","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230298","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":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.5}],"awards":[{"id":"https://openalex.org/G2168745299","display_name":null,"funder_award_id":"2022YFC3400404","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2186398520","display_name":null,"funder_award_id":"2023JJ30702","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G6834628323","display_name":null,"funder_award_id":"62172154","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G868285772","display_name":null,"funder_award_id":"62172154","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387172276.pdf"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1777239053","https://openalex.org/W2098774185","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2419612459","https://openalex.org/W2434014514","https://openalex.org/W2481567506","https://openalex.org/W2561776174","https://openalex.org/W2591957724","https://openalex.org/W2614839826","https://openalex.org/W2617547828","https://openalex.org/W2623431351","https://openalex.org/W2785315072","https://openalex.org/W2794643322","https://openalex.org/W2795158776","https://openalex.org/W2796054047","https://openalex.org/W2803155336","https://openalex.org/W2804380964","https://openalex.org/W2807741983","https://openalex.org/W2883057932","https://openalex.org/W2894976951","https://openalex.org/W2904455790","https://openalex.org/W2908261578","https://openalex.org/W2909462654","https://openalex.org/W2910787482","https://openalex.org/W2912104459","https://openalex.org/W2946606218","https://openalex.org/W2946764808","https://openalex.org/W2949475445","https://openalex.org/W2949963774","https://openalex.org/W2952465248","https://openalex.org/W2963276097","https://openalex.org/W2963277051","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2964097858","https://openalex.org/W2964937097","https://openalex.org/W2966477753","https://openalex.org/W2991479173","https://openalex.org/W2998367975","https://openalex.org/W3042045548","https://openalex.org/W3048454540","https://openalex.org/W3117812535","https://openalex.org/W3131329114","https://openalex.org/W3170118067","https://openalex.org/W3170511602","https://openalex.org/W3174718176","https://openalex.org/W3215181478","https://openalex.org/W4225623725","https://openalex.org/W4285605699","https://openalex.org/W4287708298","https://openalex.org/W4295598622","https://openalex.org/W4297703537","https://openalex.org/W4299802797"],"related_works":["https://openalex.org/W4296209631","https://openalex.org/W2000444236","https://openalex.org/W2384475851","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2561617217","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2353602216"],"abstract_inverted_index":{"Learning":[0,103],"effective":[1,98,146],"strategies":[2],"in":[3,13,20,70,83,183],"sparse":[4,71,187],"reward":[5,72],"tasks":[6,94,185],"is":[7,60],"one":[8],"of":[9,27,57,81,126],"the":[10,24,31,79,129,159],"fundamental":[11],"challenges":[12],"reinforcement":[14],"learning.":[15],"This":[16,87],"becomes":[17],"extremely":[18],"difficult":[19],"multi-agent":[21,46,85,92],"environments,":[22],"as":[23,62],"concurrent":[25],"learning":[26,52],"multiple":[28],"agents":[29,127,143,155],"induces":[30],"non-stationarity":[32,160],"problem":[33],"and":[34,95,140],"sharply":[35],"increased":[36],"joint":[37],"state":[38],"space.":[39],"Existing":[40],"works":[41],"have":[42],"attempted":[43],"to":[44,78,105,122,144,156],"promote":[45],"cooperation":[47],"through":[48],"experience":[49],"sharing.":[50],"However,":[51],"from":[53,113,128,153],"a":[54,66,118],"large":[55],"collection":[56],"shared":[58,141],"experiences":[59,112],"inefficient":[61],"there":[63],"are":[64,138],"only":[65],"few":[67],"high-value":[68,124],"states":[69],"tasks,":[73],"which":[74,134],"may":[75],"instead":[76],"lead":[77],"curse":[80],"dimensionality":[82],"large-scale":[84,167],"systems.":[86],"paper":[88],"focuses":[89],"on":[90,133],"sparse-reward":[91],"cooperative":[93,184],"proposes":[96],"an":[97],"experience-sharing":[99],"method,":[100],"Multi-Agent":[101],"Selective":[102],"(MASL),":[104],"boost":[106],"sample-efficient":[107],"training":[108,165],"by":[109],"reusing":[110],"valuable":[111],"other":[114,154],"agents.":[115,168],"MASL":[116,149,173],"adopts":[117],"retrogression-based":[119],"selection":[120],"method":[121],"identify":[123],"traces":[125,137],"team":[130],"rewards,":[131],"based":[132],"some":[135],"recall":[136],"generated":[139],"among":[142],"motivate":[145],"exploration.":[147],"Moreover,":[148],"selectively":[150],"considers":[151],"information":[152],"cope":[157],"with":[158,179,186],"issue":[161],"while":[162],"enabling":[163],"efficient":[164],"for":[166],"Experimental":[169],"results":[170],"show":[171],"that":[172],"significantly":[174],"improves":[175],"sample":[176],"efficiency":[177],"compared":[178],"state-of-the-art":[180],"MARL":[181],"algorithms":[182],"rewards.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}