{"id":"https://openalex.org/W2374550006","doi":"https://doi.org/10.5220/0005832300540061","title":"A Hybrid Interaction Model for Multi-Agent Reinforcement Learning","display_name":"A Hybrid Interaction Model for Multi-Agent Reinforcement Learning","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2374550006","doi":"https://doi.org/10.5220/0005832300540061","mag":"2374550006"},"language":"en","primary_location":{"id":"doi:10.5220/0005832300540061","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005832300540061","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0005832300540061","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030200528","display_name":"Douglas M. Guisi","orcid":null},"institutions":[{"id":"https://openalex.org/I1283613182","display_name":"Universidade Tecnol\u00f3gica Federal do Paran\u00e1","ror":"https://ror.org/002v2kq79","country_code":"BR","type":"education","lineage":["https://openalex.org/I1283613182"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Douglas M. Guisi","raw_affiliation_strings":["Federal University of Technology-Paran\u00e1, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Technology-Paran\u00e1, Brazil","institution_ids":["https://openalex.org/I1283613182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008491503","display_name":"Richardson Ribeiro","orcid":"https://orcid.org/0000-0002-5630-5204"},"institutions":[{"id":"https://openalex.org/I1283613182","display_name":"Universidade Tecnol\u00f3gica Federal do Paran\u00e1","ror":"https://ror.org/002v2kq79","country_code":"BR","type":"education","lineage":["https://openalex.org/I1283613182"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Richardson Ribeiro","raw_affiliation_strings":["Federal University of Technology-Paran\u00e1, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Technology-Paran\u00e1, Brazil","institution_ids":["https://openalex.org/I1283613182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039827669","display_name":"Marcelo Teixeira","orcid":"https://orcid.org/0000-0002-1008-7838"},"institutions":[{"id":"https://openalex.org/I1283613182","display_name":"Universidade Tecnol\u00f3gica Federal do Paran\u00e1","ror":"https://ror.org/002v2kq79","country_code":"BR","type":"education","lineage":["https://openalex.org/I1283613182"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcelo Teixeira","raw_affiliation_strings":["Federal University of Technology-Paran\u00e1, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Technology-Paran\u00e1, Brazil","institution_ids":["https://openalex.org/I1283613182"]}]},{"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/I1283613182","display_name":"Universidade Tecnol\u00f3gica Federal do Paran\u00e1","ror":"https://ror.org/002v2kq79","country_code":"BR","type":"education","lineage":["https://openalex.org/I1283613182"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 P. Borges","raw_affiliation_strings":["Federal University of Technology-Paran\u00e1, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Technology-Paran\u00e1, Brazil","institution_ids":["https://openalex.org/I1283613182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052190642","display_name":"Eden Ricardo Dosciatti","orcid":null},"institutions":[{"id":"https://openalex.org/I1283613182","display_name":"Universidade Tecnol\u00f3gica Federal do Paran\u00e1","ror":"https://ror.org/002v2kq79","country_code":"BR","type":"education","lineage":["https://openalex.org/I1283613182"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Eden R. Dosciatti","raw_affiliation_strings":["Federal University of Technology-Paran\u00e1, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Technology-Paran\u00e1, Brazil","institution_ids":["https://openalex.org/I1283613182"]}]},{"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":"Fabr\u00edcio Enembreck","raw_affiliation_strings":["Pontifical Catholic University-Paran\u00e1, Brazil"],"affiliations":[{"raw_affiliation_string":"Pontifical Catholic University-Paran\u00e1, Brazil","institution_ids":["https://openalex.org/I176838256"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5030200528"],"corresponding_institution_ids":["https://openalex.org/I1283613182"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01811127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"54","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9785000085830688,"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":0.9380000233650208,"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":0.8848644495010376},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7523114085197449},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7070444822311401},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.47107091546058655},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4503726065158844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4342806339263916}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8848644495010376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523114085197449},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7070444822311401},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47107091546058655},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4503726065158844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4342806339263916},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0005832300540061","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005832300540061","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Enterprise Information Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0005832300540061","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005832300540061","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W171723243","https://openalex.org/W1515308897","https://openalex.org/W1540725368","https://openalex.org/W1570469988","https://openalex.org/W1759988108","https://openalex.org/W1984087082","https://openalex.org/W2025406794","https://openalex.org/W2098280298","https://openalex.org/W2107726111","https://openalex.org/W2121863487","https://openalex.org/W2131376880","https://openalex.org/W2147492008","https://openalex.org/W2152576222","https://openalex.org/W2189058185","https://openalex.org/W2250340166","https://openalex.org/W2276827050","https://openalex.org/W2971274224"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"The":[0,21],"main":[1],"contribution":[2],"of":[3,12,29,44,78,92,115,120],"this":[4],"paper":[5],"is":[6],"to":[7,37,66,123],"implement":[8],"a":[9,67],"hybrid":[10,102],"method":[11,74,103],"coordination":[13,91],"from":[14],"the":[15,27,61,76,90,101,106,118],"combination\r\n\r\nof":[16],"interaction":[17,22],"models":[18,23],"developed":[19],"previously.":[20],"are":[24],"based":[25],"on":[26],"sharing":[28],"rewards":[30],"for\r\n\r\nlearning":[31],"with":[32,87],"multiple":[33],"agents":[34,93],"in":[35,54,94,112],"order":[36],"discover":[38],"interactively":[39],"good":[40],"quality":[41],"policies.":[42],"Exchange":[43],"rewards\r\n\r\namong":[45],"agents,":[46],"when":[47],"not":[48],"occur":[49],"properly,":[50],"can":[51,104],"cause":[52,58],"delays":[53],"learning":[55,96],"or":[56],"even":[57],"unexpected":[59],"behavior,\r\n\r\nmaking":[60],"cooperation":[62],"inefficient":[63],"and":[64],"converging":[65],"non-satisfactory":[68],"policy.":[69],"From":[70],"these":[71],"concepts,":[72],"the\r\n\r\nhybrid":[73],"uses":[75],"characteristics":[77],"each":[79],"model,":[80],"reducing":[81],"possible":[82],"conflicts":[83],"between":[84],"different":[85],"policy\r\n\r\nactions":[86],"rewards,":[88],"improving":[89],"reinforcement":[95,124],"problems.":[97],"Experimental\r\n\r\nresults":[98],"show":[99],"that":[100],"accelerate":[105],"convergence,":[107],"rapidly":[108],"gaining":[109],"optimal":[110],"policies\r\n\r\neven":[111],"large":[113],"spaces":[114],"states,":[116],"exceeding":[117],"results":[119],"classical":[121],"approaches":[122],"learning.":[125]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}