{"id":"https://openalex.org/W2032626653","doi":"https://doi.org/10.1007/s10458-009-9104-y","title":"Coordinated learning in multiagent MDPs with infinite state-space","display_name":"Coordinated learning in multiagent MDPs with infinite state-space","publication_year":2009,"publication_date":"2009-08-19","ids":{"openalex":"https://openalex.org/W2032626653","doi":"https://doi.org/10.1007/s10458-009-9104-y","mag":"2032626653"},"language":"en","primary_location":{"id":"doi:10.1007/s10458-009-9104-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10458-009-9104-y","pdf_url":null,"source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-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/A5101616573","display_name":"Francisco S. Melo","orcid":"https://orcid.org/0000-0001-5705-7372"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Francisco S. Melo","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA, 15213, USA","School of Computer Science, Carnegie Mellon University, Pittsburgh, USA 15213"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA, 15213, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, USA 15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082125744","display_name":"Isabel Ribeiro","orcid":"https://orcid.org/0000-0001-6083-0290"},"institutions":[{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]},{"id":"https://openalex.org/I4387152517","display_name":"Instituto Superior T\u00e9cnico","ror":"https://ror.org/03db2by73","country_code":null,"type":"education","lineage":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"M. Isabel Ribeiro","raw_affiliation_strings":["Institute for Systems and Robotics, Instituto Superior T\u00e9cnico, Av. Rovisco Pais, 1, 1049-001, Lisbon, Portugal","Institute for Systems and Robotics, Instituto Superior T\u00e9cnico, Lisbon, Portugal 1049-001"],"affiliations":[{"raw_affiliation_string":"Institute for Systems and Robotics, Instituto Superior T\u00e9cnico, Av. Rovisco Pais, 1, 1049-001, Lisbon, Portugal","institution_ids":["https://openalex.org/I4210166615","https://openalex.org/I4387152517"]},{"raw_affiliation_string":"Institute for Systems and Robotics, Instituto Superior T\u00e9cnico, Lisbon, Portugal 1049-001","institution_ids":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101616573"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":2.7177,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9081711,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"21","issue":"3","first_page":"321","last_page":"367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9915000200271606,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9805999994277954,"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":0.8435491919517517},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7265411615371704},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6595816016197205},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6557305455207825},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6464434266090393},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.6129845380783081},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5544219017028809},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5520496964454651},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.47103220224380493},{"id":"https://openalex.org/keywords/coordination-game","display_name":"Coordination game","score":0.46030643582344055},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.459150493144989},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4431452453136444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42553529143333435},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4225684106349945},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.41445836424827576},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36779123544692993},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3550805449485779},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35040485858917236},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2354145050048828},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21750009059906006},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2067100703716278},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.1443016231060028}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8435491919517517},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7265411615371704},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6595816016197205},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6557305455207825},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6464434266090393},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.6129845380783081},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5544219017028809},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5520496964454651},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.47103220224380493},{"id":"https://openalex.org/C107257861","wikidata":"https://www.wikidata.org/wiki/Q656316","display_name":"Coordination game","level":2,"score":0.46030643582344055},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.459150493144989},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4431452453136444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42553529143333435},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4225684106349945},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.41445836424827576},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36779123544692993},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3550805449485779},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35040485858917236},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2354145050048828},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21750009059906006},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2067100703716278},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.1443016231060028},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10458-009-9104-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10458-009-9104-y","pdf_url":null,"source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W361876","https://openalex.org/W11035765","https://openalex.org/W20073669","https://openalex.org/W316323024","https://openalex.org/W391985582","https://openalex.org/W1484740474","https://openalex.org/W1515108343","https://openalex.org/W1515851193","https://openalex.org/W1519783625","https://openalex.org/W1521003796","https://openalex.org/W1522095564","https://openalex.org/W1542941925","https://openalex.org/W1547105496","https://openalex.org/W1550698229","https://openalex.org/W1556191380","https://openalex.org/W1574700590","https://openalex.org/W1576452626","https://openalex.org/W1586311933","https://openalex.org/W1607392272","https://openalex.org/W1812360833","https://openalex.org/W1835254890","https://openalex.org/W1973039793","https://openalex.org/W1987666271","https://openalex.org/W1995713768","https://openalex.org/W2041367235","https://openalex.org/W2048740076","https://openalex.org/W2059607173","https://openalex.org/W2067050450","https://openalex.org/W2088956500","https://openalex.org/W2089415692","https://openalex.org/W2104602264","https://openalex.org/W2105336508","https://openalex.org/W2107977784","https://openalex.org/W2118318536","https://openalex.org/W2118686230","https://openalex.org/W2118994458","https://openalex.org/W2120327309","https://openalex.org/W2120846115","https://openalex.org/W2121154010","https://openalex.org/W2121863487","https://openalex.org/W2122701159","https://openalex.org/W2125510930","https://openalex.org/W2131600418","https://openalex.org/W2135684466","https://openalex.org/W2138178898","https://openalex.org/W2139418546","https://openalex.org/W2145067550","https://openalex.org/W2147967768","https://openalex.org/W2149254401","https://openalex.org/W2149551746","https://openalex.org/W2150147323","https://openalex.org/W2151661095","https://openalex.org/W2161608691","https://openalex.org/W2167957526","https://openalex.org/W2169982856","https://openalex.org/W2782037066","https://openalex.org/W2787259794","https://openalex.org/W2999905431","https://openalex.org/W3011120880","https://openalex.org/W3198350258","https://openalex.org/W4245296547","https://openalex.org/W6631168379","https://openalex.org/W6638536898","https://openalex.org/W6677834374","https://openalex.org/W6678900246","https://openalex.org/W6680070467","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2955790965","https://openalex.org/W4308702637","https://openalex.org/W2149418961","https://openalex.org/W4289355352","https://openalex.org/W1501190258","https://openalex.org/W2806157618","https://openalex.org/W2808418668","https://openalex.org/W4256087190","https://openalex.org/W4240668504","https://openalex.org/W2011233848"],"abstract_inverted_index":null,"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}