{"id":"https://openalex.org/W2113744550","doi":"https://doi.org/10.1109/ijcnn.2004.1380880","title":"Hybrid model for multiagent reinforcement learning","display_name":"Hybrid model for multiagent reinforcement learning","publication_year":2005,"publication_date":"2005-01-31","ids":{"openalex":"https://openalex.org/W2113744550","doi":"https://doi.org/10.1109/ijcnn.2004.1380880","mag":"2113744550"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2004.1380880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2004.1380880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","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/A5065253727","display_name":"Ville K\u00f6n\u00f6nen","orcid":null},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"V. Kononen","raw_affiliation_strings":["Neural Networks Research Centre, Helsinki University of Technology, Finland","Neural Networks Res. Center, Helsinki Univ. of Technol., Finland"],"affiliations":[{"raw_affiliation_string":"Neural Networks Research Centre, Helsinki University of Technology, Finland","institution_ids":["https://openalex.org/I133731052"]},{"raw_affiliation_string":"Neural Networks Res. Center, Helsinki Univ. of Technol., Finland","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5065253727"],"corresponding_institution_ids":["https://openalex.org/I133731052"],"apc_list":null,"apc_paid":null,"fwci":0.4388,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7442311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"1793","last_page":"1798"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.987500011920929,"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":0.9242753386497498},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7280596494674683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5722711086273193},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5248556137084961},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.5206857919692993},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5168672204017639},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.49776721000671387},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4681563377380371},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4491897225379944},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4464888274669647},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.44501838088035583},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43260592222213745},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.41424083709716797},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39570391178131104},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34561651945114136},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16137298941612244},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14622873067855835},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06410139799118042}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9242753386497498},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7280596494674683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5722711086273193},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5248556137084961},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.5206857919692993},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5168672204017639},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.49776721000671387},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4681563377380371},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4491897225379944},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4464888274669647},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.44501838088035583},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43260592222213745},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.41424083709716797},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39570391178131104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34561651945114136},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16137298941612244},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14622873067855835},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06410139799118042},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2004.1380880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2004.1380880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1502765764","https://openalex.org/W1513468570","https://openalex.org/W1519783625","https://openalex.org/W1542941925","https://openalex.org/W1589560630","https://openalex.org/W2121863487","https://openalex.org/W2145067550","https://openalex.org/W2164637474","https://openalex.org/W4214717370","https://openalex.org/W6630520071","https://openalex.org/W6631168379","https://openalex.org/W6681342480","https://openalex.org/W6684470913"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W4308702637","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2156021013","https://openalex.org/W2903299703","https://openalex.org/W2101748387","https://openalex.org/W3105579180","https://openalex.org/W1574958246"],"abstract_inverted_index":{"In":[0],"This":[1],"work":[2],"we":[3,55],"propose":[4],"a":[5,57,71],"new":[6],"method":[7,24,39,69],"for":[8,40],"reducing":[9],"space":[10],"and":[11,42,47,65],"computational":[12],"requirements":[13],"of":[14,61],"multiagent":[15,44,62],"reinforcement":[16,45,63],"learning":[17,46,64],"based":[18],"on":[19],"Markov":[20],"games.":[21],"The":[22],"proposed":[23,68],"estimates":[25],"value":[26],"functions":[27],"by":[28],"using":[29],"two":[30],"Q-value":[31],"tables":[32],"or":[33],"function":[34],"approximators.":[35],"We":[36],"formulate":[37],"the":[38,67],"symmetric":[41],"asymmetric":[43],"also":[48],"discuss":[49],"some":[50],"numerical":[51],"approximation":[52],"techniques.":[53],"Additionally,":[54],"present":[56],"brief":[58],"literature":[59],"survey":[60],"test":[66],"with":[70],"simple":[72],"example":[73],"application.":[74]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}