{"id":"https://openalex.org/W2008809493","doi":"https://doi.org/10.1109/tcyb.2013.2253094","title":"Heuristically-Accelerated Multiagent Reinforcement Learning","display_name":"Heuristically-Accelerated Multiagent Reinforcement Learning","publication_year":2013,"publication_date":"2013-04-15","ids":{"openalex":"https://openalex.org/W2008809493","doi":"https://doi.org/10.1109/tcyb.2013.2253094","mag":"2008809493","pmid":"https://pubmed.ncbi.nlm.nih.gov/23757547"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2013.2253094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2013.2253094","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repositorio.fei.edu.br/handle/FEI/1242","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073156082","display_name":"Reinaldo A. C. Bianchi","orcid":"https://orcid.org/0000-0001-9097-827X"},"institutions":[{"id":"https://openalex.org/I139221136","display_name":"Centro Universit\u00e1rio FEI","ror":"https://ror.org/007kf5222","country_code":"BR","type":"education","lineage":["https://openalex.org/I139221136"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Reinaldo A. C. Bianchi","raw_affiliation_strings":["Department of Electrical Engineering, Centro Universit&#x00E1;rio da FEI, S&#x00E3;o Bernardo do Campo, Brazil","Dept. of Electr. Eng., Centro Univ. da FEI, Sao Bernardo do Campo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Centro Universit&#x00E1;rio da FEI, S&#x00E3;o Bernardo do Campo, Brazil","institution_ids":["https://openalex.org/I139221136"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Centro Univ. da FEI, Sao Bernardo do Campo, Brazil","institution_ids":["https://openalex.org/I139221136"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019284663","display_name":"Murilo Fernandes Martins","orcid":null},"institutions":[{"id":"https://openalex.org/I139221136","display_name":"Centro Universit\u00e1rio FEI","ror":"https://ror.org/007kf5222","country_code":"BR","type":"education","lineage":["https://openalex.org/I139221136"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Murilo F. Martins","raw_affiliation_strings":["Department of Electrical Engineering, Centro Universit&#x00E1;rio da FEI, S&#x00E3;o Bernardo do Campo, Brazil","Dept. of Electr. Eng., Centro Univ. da FEI, Sao Bernardo do Campo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Centro Universit&#x00E1;rio da FEI, S&#x00E3;o Bernardo do Campo, Brazil","institution_ids":["https://openalex.org/I139221136"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Centro Univ. da FEI, Sao Bernardo do Campo, Brazil","institution_ids":["https://openalex.org/I139221136"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068086847","display_name":"Carlos H. C. Ribeiro","orcid":"https://orcid.org/0000-0002-5760-8426"},"institutions":[{"id":"https://openalex.org/I107428990","display_name":"Instituto Tecnol\u00f3gico de Aeron\u00e1utica","ror":"https://ror.org/05vh67662","country_code":"BR","type":"education","lineage":["https://openalex.org/I107428990"]},{"id":"https://openalex.org/I4210123805","display_name":"Instituto de Aeron\u00e1utica e Espa\u00e7o","ror":"https://ror.org/025n1fp68","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210123805"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Carlos H. C. Ribeiro","raw_affiliation_strings":["Computer Science Division, Technological Institute of Aeronautics, S&#x00E3;o Jos&#x00E9; dos Campos, Brazil","Comput. Sci. Div., Technol. Inst. of Aeronaut., Sa\u0303o Jose\u0301 dos Campos, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Division, Technological Institute of Aeronautics, S&#x00E3;o Jos&#x00E9; dos Campos, Brazil","institution_ids":["https://openalex.org/I107428990","https://openalex.org/I4210123805"]},{"raw_affiliation_string":"Comput. Sci. Div., Technol. Inst. of Aeronaut., Sa\u0303o Jose\u0301 dos Campos, Brazil","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069264027","display_name":"Anna Helena Reali Costa","orcid":"https://orcid.org/0000-0001-7309-4528"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]},{"id":"https://openalex.org/I4210129339","display_name":"Funda\u00e7\u00e3o Escola de Sociologia e Pol\u00edtica de S\u00e3o Paulo","ror":"https://ror.org/036rdqh43","country_code":"BR","type":"nonprofit","lineage":["https://openalex.org/I4210129339"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Anna H. R. Costa","raw_affiliation_strings":["Escola Polit&#x00E9;cnica, Universidade of S&#x00E3;o Paulo, S&#x00E3;o Paulo, Brazil","Escola Politec., Univ. of Sao Paulo, Sao Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Escola Polit&#x00E9;cnica, Universidade of S&#x00E3;o Paulo, S&#x00E3;o Paulo, Brazil","institution_ids":["https://openalex.org/I4210129339"]},{"raw_affiliation_string":"Escola Politec., Univ. of Sao Paulo, Sao Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":8.2375,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.97033111,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"44","issue":"2","first_page":"252","last_page":"265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9664000272750854,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9383000135421753,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8775811195373535},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7560769319534302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7304917573928833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6280596852302551},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6025305390357971},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.5819385051727295},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5699466466903687},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5622544288635254},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5310348272323608},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.523625910282135},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.48105669021606445},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4765239953994751},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45018067955970764},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3881864845752716},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15844106674194336}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8775811195373535},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7560769319534302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7304917573928833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6280596852302551},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6025305390357971},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.5819385051727295},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5699466466903687},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5622544288635254},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5310348272323608},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.523625910282135},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.48105669021606445},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4765239953994751},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45018067955970764},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3881864845752716},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15844106674194336},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D032701","descriptor_name":"Biomimetics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D032701","descriptor_name":"Biomimetics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D032701","descriptor_name":"Biomimetics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1109/tcyb.2013.2253094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2013.2253094","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},{"id":"pmh:oai:repositorio.fei.edu.br:FEI/1242","is_oa":true,"landing_page_url":"https://repositorio.fei.edu.br/handle/FEI/1242","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"reponame:Biblioteca Digital de Teses e Disserta\u00e7\u00f5es da FEI","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmid:23757547","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23757547","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:repositorio.fei.edu.br:FEI/1242","is_oa":true,"landing_page_url":"https://repositorio.fei.edu.br/handle/FEI/1242","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"reponame:Biblioteca Digital de Teses e Disserta\u00e7\u00f5es da FEI","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W361876","https://openalex.org/W29099680","https://openalex.org/W32198084","https://openalex.org/W32403112","https://openalex.org/W56117469","https://openalex.org/W139877375","https://openalex.org/W968045710","https://openalex.org/W1519783625","https://openalex.org/W1542941925","https://openalex.org/W1548889916","https://openalex.org/W1562327279","https://openalex.org/W1580572138","https://openalex.org/W1587589241","https://openalex.org/W1595605666","https://openalex.org/W1598756869","https://openalex.org/W1626977535","https://openalex.org/W1835254890","https://openalex.org/W2056584142","https://openalex.org/W2065821056","https://openalex.org/W2098432798","https://openalex.org/W2099618002","https://openalex.org/W2107544712","https://openalex.org/W2107726111","https://openalex.org/W2120327309","https://openalex.org/W2120846115","https://openalex.org/W2147492008","https://openalex.org/W2151340488","https://openalex.org/W2151844511","https://openalex.org/W2163808368","https://openalex.org/W2164637474","https://openalex.org/W2183728818","https://openalex.org/W2187328218","https://openalex.org/W2623293810","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W4240247511","https://openalex.org/W4255047891","https://openalex.org/W6600018571","https://openalex.org/W6601161420","https://openalex.org/W6631168379","https://openalex.org/W6634770748","https://openalex.org/W6635376945","https://openalex.org/W6636868823","https://openalex.org/W6682249872","https://openalex.org/W6684470913","https://openalex.org/W6684489938","https://openalex.org/W6686054324","https://openalex.org/W6686728135"],"related_works":["https://openalex.org/W2163808368","https://openalex.org/W2373283138","https://openalex.org/W1595605666","https://openalex.org/W2165127677","https://openalex.org/W1502099479","https://openalex.org/W72858603","https://openalex.org/W2140318223","https://openalex.org/W1509664945","https://openalex.org/W130947223","https://openalex.org/W29099680"],"abstract_inverted_index":{"This":[0,51],"paper":[1],"presents":[2],"a":[3,39,78,101],"novel":[4],"class":[5,91],"of":[6,18,46,85,136],"algorithms,":[7],"called":[8],"Heuristically-Accelerated":[9],"Multiagent":[10],"Reinforcement":[11],"Learning":[12],"(HAMRL),":[13],"which":[14,42,59],"allows":[15],"the":[16,31,44,76,83,89,117,134,137],"use":[17],"heuristics":[19,120],"to":[20],"speed":[21],"up":[22],"well-known":[23],"multiagent":[24],"reinforcement":[25],"learning":[26],"(RL)":[27],"algorithms":[28,35,87],"such":[29],"as":[30],"Minimax-Q.":[32],"Such":[33],"HAMRL":[34,90,138],"are":[36],"characterized":[37],"by":[38],"heuristic":[40],"function,":[41],"suggests":[43],"selection":[45,57,126],"particular":[47],"actions":[48],"over":[49,139],"others.":[50],"function":[52],"represents":[53],"an":[54],"initial":[55],"action":[56,125],"policy,":[58],"can":[60,121],"be":[61],"handcrafted,":[62],"extracted":[63],"from":[64,72,88],"previous":[65],"experience":[66],"in":[67,107,128],"distinct":[68,109],"domains,":[69],"or":[70],"learnt":[71],"observation.":[73],"To":[74],"validate":[75],"proposal,":[77],"thorough":[79],"theoretical":[80],"analysis":[81],"proving":[82],"convergence":[84],"four":[86],"(HAMMQ,":[92],"HAMQ(\u03bb),":[93],"HAMQS,":[94],"and":[95],"HAMS)":[96],"is":[97],"presented.":[98],"In":[99],"addition,":[100],"comprehensive":[102],"systematical":[103],"evaluation":[104],"was":[105],"conducted":[106],"two":[108],"adversarial":[110],"domains.":[111],"The":[112],"results":[113],"show":[114],"that":[115],"even":[116],"most":[118],"straightforward":[119],"produce":[122],"virtually":[123],"optimal":[124],"policies":[127],"much":[129],"fewer":[130],"episodes,":[131],"significantly":[132],"improving":[133],"performance":[135],"vanilla":[140],"RL":[141],"algorithms.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":7}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
