{"id":"https://openalex.org/W4387185416","doi":"https://doi.org/10.3233/faia230586","title":"IPERS: Individual Prioritized Experience Replay with Subgoals for Sparse Reward Multi-Agent Reinforcement Learning","display_name":"IPERS: Individual Prioritized Experience Replay with Subgoals for Sparse Reward Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387185416","doi":"https://doi.org/10.3233/faia230586"},"language":"en","primary_location":{"id":"doi:10.3233/faia230586","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230586","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230586","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/FAIA230586","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027931296","display_name":"Zaipeng Xie","orcid":"https://orcid.org/0000-0003-1637-1511"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]},{"id":"https://openalex.org/I4210155611","display_name":"Ministry of Water Resources of the People's Republic of China","ror":"https://ror.org/04e698d63","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210155611"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zaipeng Xie","raw_affiliation_strings":["College of Computer and Information, Hohai University, Nanjing, China","Key Laboratory of Water Big Data Technology of Ministry of Water Resources, Hohai University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer and Information, Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]},{"raw_affiliation_string":"Key Laboratory of Water Big Data Technology of Ministry of Water Resources, Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411","https://openalex.org/I4210155611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459689","display_name":"Yufeng Zhang","orcid":"https://orcid.org/0000-0002-7089-3831"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufeng Zhang","raw_affiliation_strings":["College of Computer and Information, Hohai University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer and Information, Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111047960","display_name":"Chentai Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chentai Qiao","raw_affiliation_strings":["College of Computer and Information, Hohai University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer and Information, Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027713037","display_name":"Sitong Shen","orcid":"https://orcid.org/0009-0003-4841-8414"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sitong Shen","raw_affiliation_strings":["College of Computer and Information, Hohai University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer and Information, Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027931296"],"corresponding_institution_ids":["https://openalex.org/I163340411","https://openalex.org/I4210155611"],"apc_list":null,"apc_paid":null,"fwci":1.7691,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87364173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"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":0.9907000064849854,"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":0.9907000064849854,"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/T11542","display_name":"Behavioral Health and Interventions","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied 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":0.9793000221252441,"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":0.8773341178894043},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7034223079681396},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6688646078109741},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5521678328514099},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5251297950744629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4085843861103058},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12258058786392212}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8773341178894043},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7034223079681396},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6688646078109741},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5521678328514099},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5251297950744629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4085843861103058},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12258058786392212},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230586","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230586","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230586","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/faia230586","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230586","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230586","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387185416.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W2201581102","https://openalex.org/W2623431351","https://openalex.org/W2747213132","https://openalex.org/W2772721022","https://openalex.org/W2786928559","https://openalex.org/W2788994997","https://openalex.org/W2807741983","https://openalex.org/W2883207481","https://openalex.org/W2900928600","https://openalex.org/W2946606218","https://openalex.org/W2949963774","https://openalex.org/W2963243556","https://openalex.org/W2963321092","https://openalex.org/W2963762747","https://openalex.org/W2964048876","https://openalex.org/W2997502221","https://openalex.org/W2998202787","https://openalex.org/W3004640943","https://openalex.org/W3034941755","https://openalex.org/W3092478740","https://openalex.org/W3111843786","https://openalex.org/W3156295478","https://openalex.org/W3164972322","https://openalex.org/W3170511602","https://openalex.org/W3173049816","https://openalex.org/W3198701155","https://openalex.org/W3211037481","https://openalex.org/W3213280251","https://openalex.org/W3214679404","https://openalex.org/W4283378306","https://openalex.org/W4283697246","https://openalex.org/W4285436760","https://openalex.org/W4286982463","https://openalex.org/W4287758406","https://openalex.org/W4289753142","https://openalex.org/W4292122892","https://openalex.org/W4299802797","https://openalex.org/W4306680355","https://openalex.org/W4312240273","https://openalex.org/W4312862010","https://openalex.org/W4318241708"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1],"learning":[2,118],"commonly":[3],"uses":[4],"a":[5],"global":[6,19,87],"team":[7,45],"reward":[8,20,34],"signal":[9],"to":[10,38,142,156],"represent":[11],"overall":[12,56],"collaborative":[13,123],"performance.":[14],"Value":[15],"decomposition":[16,79],"breaks":[17],"this":[18],"into":[21,102],"estimated":[22],"individual":[23,89],"value":[24],"functions":[25],"per":[26],"agent,":[27],"enabling":[28],"efficient":[29],"training.":[30],"However,":[31],"in":[32,121,132,149],"sparse":[33,126],"environments,":[35],"agents":[36],"struggle":[37],"assess":[39],"if":[40],"their":[41],"actions":[42],"achieve":[43],"the":[44,51,134],"goal,":[46],"slowing":[47],"convergence.":[48],"This":[49,116],"impedes":[50],"algorithm\u2019s":[52],"convergence":[53,153],"rate":[54,151],"and":[55,80,88,108,136,146,152],"efficacy.":[57],"We":[58],"present":[59],"IPERS,":[60],"an":[61],"Individual":[62],"Prioritized":[63],"Experience":[64],"Replay":[65],"algorithm":[66],"with":[67,105,125],"Subgoals":[68,92],"for":[69],"Sparse":[70],"Reward":[71],"Multi-Agent":[72],"Reinforcement":[73],"Learning.":[74],"IPERS":[75,131],"integrates":[76],"joint":[77],"action":[78],"prioritized":[81],"experience":[82],"replay,":[83],"maintaining":[84],"invariance":[85],"between":[86],"loss":[90],"gradients.":[91],"serve":[93],"as":[94],"intermediate":[95],"goals":[96],"that":[97,113],"break":[98],"down":[99],"complex":[100],"tasks":[101,145],"simpler":[103],"steps":[104],"dense":[106],"feedback":[107],"provide":[109],"helpful":[110],"intrinsic":[111],"rewards":[112],"guide":[114],"agents.":[115],"facilitates":[117],"coordinated":[119],"policies":[120],"challenging":[122],"environments":[124,138],"rewards.":[127],"Experimental":[128],"evaluations":[129],"of":[130],"both":[133],"SMAC":[135],"GRF":[137],"demonstrate":[139],"rapid":[140],"adaptation":[141],"diverse":[143],"multi-agent":[144],"significant":[147],"improvements":[148],"win":[150],"performance":[154],"relative":[155],"state-of-the-art":[157],"algorithms.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-30T23:08:21.542490","created_date":"2025-10-10T00:00:00"}