{"id":"https://openalex.org/W2116901014","doi":"https://doi.org/10.1109/ia.2009.4927511","title":"A strategy for converging dynamic action policies","display_name":"A strategy for converging dynamic action policies","publication_year":2009,"publication_date":"2009-03-01","ids":{"openalex":"https://openalex.org/W2116901014","doi":"https://doi.org/10.1109/ia.2009.4927511","mag":"2116901014"},"language":"en","primary_location":{"id":"doi:10.1109/ia.2009.4927511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ia.2009.4927511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Intelligent Agents","raw_type":"proceedings-article"},"type":"article","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/A5008491503","display_name":"Richardson Ribeiro","orcid":"https://orcid.org/0000-0002-5630-5204"},"institutions":[{"id":"https://openalex.org/I4210136792","display_name":"Universidade do Contestado","ror":"https://ror.org/03qbgfe05","country_code":"BR","type":"education","lineage":["https://openalex.org/I4210136792"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Richardson Ribeiro","raw_affiliation_strings":["Graduate Program in Computer Science (PPGIa), University of Contestado, Mafra, Santa Catarina, Brazil","University of Contestado - UnC, Av Nereu Ramos, 1071, CEP 89300-000, Mafra, Santa Catarina - Brazil"],"affiliations":[{"raw_affiliation_string":"Graduate Program in Computer Science (PPGIa), University of Contestado, Mafra, Santa Catarina, Brazil","institution_ids":["https://openalex.org/I4210136792"]},{"raw_affiliation_string":"University of Contestado - UnC, Av Nereu Ramos, 1071, CEP 89300-000, Mafra, Santa Catarina - Brazil","institution_ids":["https://openalex.org/I4210136792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003807083","display_name":"Andr\u00e9 Pinz Borges","orcid":"https://orcid.org/0000-0002-1716-8614"},"institutions":[{"id":"https://openalex.org/I176838256","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Paran\u00e1","ror":"https://ror.org/02x1vjk79","country_code":"BR","type":"education","lineage":["https://openalex.org/I176838256"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Andre P. Borges","raw_affiliation_strings":["Graduate Program in Computer Science (PPGIa), Pontifical Catholic University of Paran\u00e1, Curitiba, Parana, Brazil","Pontifical Catholic University of Paran\u00e1 - PUCPR, Graduate Program in Computer Science (PPGIa), Rua Imaculada Concei\u00e7\u00e3o, 1155, CEP 80215-901, Curitiba, Brazil"],"affiliations":[{"raw_affiliation_string":"Graduate Program in Computer Science (PPGIa), Pontifical Catholic University of Paran\u00e1, Curitiba, Parana, Brazil","institution_ids":["https://openalex.org/I176838256"]},{"raw_affiliation_string":"Pontifical Catholic University of Paran\u00e1 - PUCPR, Graduate Program in Computer Science (PPGIa), Rua Imaculada Concei\u00e7\u00e3o, 1155, CEP 80215-901, Curitiba, Brazil","institution_ids":["https://openalex.org/I176838256"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074262951","display_name":"Alessandro L. Koerich","orcid":"https://orcid.org/0000-0001-5879-7014"},"institutions":[{"id":"https://openalex.org/I176838256","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Paran\u00e1","ror":"https://ror.org/02x1vjk79","country_code":"BR","type":"education","lineage":["https://openalex.org/I176838256"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Alessandro L. Koerich","raw_affiliation_strings":["Graduate Program in Computer Science (PPGIa), Pontifical Catholic University of Paran\u00e1, Curitiba, Parana, Brazil","Pontifical Catholic University of Paran\u00e1 - PUCPR, Graduate Program in Computer Science (PPGIa), Rua Imaculada Concei\u00e7\u00e3o, 1155, CEP 80215-901, Curitiba, Brazil"],"affiliations":[{"raw_affiliation_string":"Graduate Program in Computer Science (PPGIa), Pontifical Catholic University of Paran\u00e1, Curitiba, Parana, Brazil","institution_ids":["https://openalex.org/I176838256"]},{"raw_affiliation_string":"Pontifical Catholic University of Paran\u00e1 - PUCPR, Graduate Program in Computer Science (PPGIa), Rua Imaculada Concei\u00e7\u00e3o, 1155, CEP 80215-901, Curitiba, Brazil","institution_ids":["https://openalex.org/I176838256"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082099991","display_name":"Edson Em\u00edlio Scalabrin","orcid":"https://orcid.org/0000-0002-3918-1799"},"institutions":[{"id":"https://openalex.org/I176838256","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Paran\u00e1","ror":"https://ror.org/02x1vjk79","country_code":"BR","type":"education","lineage":["https://openalex.org/I176838256"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Edson E. Scalabrin","raw_affiliation_strings":["Graduate Program in Computer Science (PPGIa), Pontifical Catholic University of Paran\u00e1, Curitiba, Parana, Brazil","Pontifical Catholic University of Paran\u00e1 - PUCPR, Graduate Program in Computer Science (PPGIa), Rua Imaculada Concei\u00e7\u00e3o, 1155, CEP 80215-901, Curitiba, Brazil"],"affiliations":[{"raw_affiliation_string":"Graduate Program in Computer Science (PPGIa), Pontifical Catholic University of Paran\u00e1, Curitiba, Parana, Brazil","institution_ids":["https://openalex.org/I176838256"]},{"raw_affiliation_string":"Pontifical Catholic University of Paran\u00e1 - PUCPR, Graduate Program in Computer Science (PPGIa), Rua Imaculada Concei\u00e7\u00e3o, 1155, CEP 80215-901, Curitiba, Brazil","institution_ids":["https://openalex.org/I176838256"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035426257","display_name":"Fabr\u00edcio Enembreck","orcid":"https://orcid.org/0000-0002-1418-3245"},"institutions":[{"id":"https://openalex.org/I176838256","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Paran\u00e1","ror":"https://ror.org/02x1vjk79","country_code":"BR","type":"education","lineage":["https://openalex.org/I176838256"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Fabricio Enembreck","raw_affiliation_strings":["Graduate Program in Computer Science (PPGIa), Pontifical Catholic University of Paran\u00e1, Curitiba, Parana, Brazil","Pontifical Catholic University of Paran\u00e1 - PUCPR, Graduate Program in Computer Science (PPGIa), Rua Imaculada Concei\u00e7\u00e3o, 1155, CEP 80215-901, Curitiba, Brazil"],"affiliations":[{"raw_affiliation_string":"Graduate Program in Computer Science (PPGIa), Pontifical Catholic University of Paran\u00e1, Curitiba, Parana, Brazil","institution_ids":["https://openalex.org/I176838256"]},{"raw_affiliation_string":"Pontifical Catholic University of Paran\u00e1 - PUCPR, Graduate Program in Computer Science (PPGIa), Rua Imaculada Concei\u00e7\u00e3o, 1155, CEP 80215-901, Curitiba, Brazil","institution_ids":["https://openalex.org/I176838256"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008491503"],"corresponding_institution_ids":["https://openalex.org/I4210136792"],"apc_list":null,"apc_paid":null,"fwci":1.8065,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.87863656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"112","issue":null,"first_page":"136","last_page":"143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9923999905586243,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9857000112533569,"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/convergence","display_name":"Convergence (economics)","score":0.7635105848312378},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7448084354400635},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.708758533000946},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6241365075111389},{"id":"https://openalex.org/keywords/adaptive-strategies","display_name":"Adaptive strategies","score":0.48018160462379456},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.45679357647895813},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4466248154640198},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41292035579681396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17578083276748657},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10696613788604736},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08443456888198853},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.07517486810684204}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7635105848312378},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7448084354400635},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.708758533000946},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6241365075111389},{"id":"https://openalex.org/C167393769","wikidata":"https://www.wikidata.org/wiki/Q4680768","display_name":"Adaptive strategies","level":2,"score":0.48018160462379456},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.45679357647895813},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4466248154640198},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41292035579681396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17578083276748657},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10696613788604736},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08443456888198853},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.07517486810684204},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ia.2009.4927511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ia.2009.4927511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Intelligent Agents","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.158.1256","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.1256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ppgia.pucpr.br/~alekoe/Papers/ALEKOE-ISIA2009.pdf","raw_type":"text"},{"id":"pmh:oai:espace2.etsmtl.ca:9853","is_oa":false,"landing_page_url":"https://espace2.etsmtl.ca/id/eprint/9853/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402392","display_name":"Espace \u00c9TS (ETS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1341030882","host_organization_name":"Educational Testing Service","host_organization_lineage":["https://openalex.org/I1341030882"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Compte rendu de conf\u00e9rence"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1630246448","https://openalex.org/W1759988108","https://openalex.org/W1982237571","https://openalex.org/W2077556203","https://openalex.org/W2089561656","https://openalex.org/W2100370041","https://openalex.org/W2107726111","https://openalex.org/W2109910161","https://openalex.org/W2115524942","https://openalex.org/W2116600741","https://openalex.org/W2121863487","https://openalex.org/W2122500383","https://openalex.org/W2127116163","https://openalex.org/W2131600418","https://openalex.org/W2158150115","https://openalex.org/W2160308170","https://openalex.org/W2162536458","https://openalex.org/W2164114810","https://openalex.org/W2165792602","https://openalex.org/W2693300019","https://openalex.org/W2787259794","https://openalex.org/W4214717370","https://openalex.org/W6636830790","https://openalex.org/W6637979363","https://openalex.org/W6672734911","https://openalex.org/W6677356797","https://openalex.org/W6682972110","https://openalex.org/W6684499351","https://openalex.org/W6740407201"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2384475851","https://openalex.org/W2000444236","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2353602216","https://openalex.org/W2024136090"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"propose":[4],"a":[5,40,56],"novel":[6],"strategy":[7,29,99],"for":[8,21,55,72],"converging":[9],"dynamic":[10,44,89],"policies":[11,67,93],"generated":[12],"by":[13],"adaptive":[14],"agents,":[15],"which":[16],"receive":[17],"and":[18],"accumulate":[19],"rewards":[20],"their":[22],"actions.":[23],"The":[24],"goal":[25],"of":[26,36,107],"the":[27,34,52,60,64,83,97,105,108],"proposed":[28,98],"is":[30,48,100],"to":[31,39,50,59,102],"speed":[32,103],"up":[33,104],"convergence":[35,106],"such":[37],"agents":[38],"good":[41,53,112],"policy":[42],"in":[43,63,70,74,82],"environments.":[45],"Since":[46],"it":[47],"difficult":[49],"have":[51,94],"value":[54],"state":[57],"due":[58],"continuous":[61],"changing":[62],"environment,":[65],"previous":[66],"are":[68],"kept":[69],"memory":[71],"reuse":[73],"future":[75],"policies,":[76],"avoiding":[77],"delays":[78],"or":[79],"unexpected":[80],"speedups":[81],"agent's":[84],"learning.":[85],"Experimental":[86],"results":[87],"on":[88],"environments":[90],"with":[91],"different":[92],"shown":[95],"that":[96],"able":[101],"agent":[109],"while":[110],"achieving":[111],"action":[113],"policies.":[114]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
