{"id":"https://openalex.org/W2550023823","doi":"https://doi.org/10.1007/978-3-319-49049-6_33","title":"Communication-Less Cooperative Q-Learning Agents in Maze Problem","display_name":"Communication-Less Cooperative Q-Learning Agents in Maze Problem","publication_year":2016,"publication_date":"2016-11-08","ids":{"openalex":"https://openalex.org/W2550023823","doi":"https://doi.org/10.1007/978-3-319-49049-6_33","mag":"2550023823"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-49049-6_33","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-49049-6_33","pdf_url":null,"source":{"id":"https://openalex.org/S4210171034","display_name":"Proceedings in adaptation, learning and optimization","issn_l":"2363-6084","issn":["2363-6084","2363-6092"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings in Adaptation, Learning and Optimization","raw_type":"book-chapter"},"type":"book-chapter","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/A5037814625","display_name":"Fumito Uwano","orcid":"https://orcid.org/0000-0003-4139-2605"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Fumito Uwano","raw_affiliation_strings":["The University of Electro-Communications, 1-5-1 Chofugaoka Chofu, Tokyo, W6-309, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications, 1-5-1 Chofugaoka Chofu, Tokyo, W6-309, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084452161","display_name":"Keiki Takadama","orcid":"https://orcid.org/0009-0007-0916-5505"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiki Takadama","raw_affiliation_strings":["The University of Electro-Communications, 1-5-1 Chofugaoka Chofu, Tokyo, W6-309, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications, 1-5-1 Chofugaoka Chofu, Tokyo, W6-309, Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5037814625"],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":null,"apc_paid":null,"fwci":0.6773,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71203279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"453","last_page":"467"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T12761","display_name":"Data Stream Mining Techniques","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"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9333999752998352,"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/task","display_name":"Task (project management)","score":0.6953301429748535},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6736476421356201},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6649477481842041},{"id":"https://openalex.org/keywords/certainty","display_name":"Certainty","score":0.6202420592308044},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6009478569030762},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.5514576435089111},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.47058171033859253},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.46068599820137024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4396810829639435},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2371857464313507},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.16431322693824768},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15931165218353271},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1399022340774536},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.09174084663391113}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6953301429748535},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6736476421356201},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6649477481842041},{"id":"https://openalex.org/C7493553","wikidata":"https://www.wikidata.org/wiki/Q1520777","display_name":"Certainty","level":2,"score":0.6202420592308044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6009478569030762},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.5514576435089111},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.47058171033859253},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.46068599820137024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4396810829639435},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2371857464313507},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.16431322693824768},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15931165218353271},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1399022340774536},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.09174084663391113},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-319-49049-6_33","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-49049-6_33","pdf_url":null,"source":{"id":"https://openalex.org/S4210171034","display_name":"Proceedings in adaptation, learning and optimization","issn_l":"2363-6084","issn":["2363-6084","2363-6092"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings in Adaptation, Learning and Optimization","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1537934887","https://openalex.org/W1542094515","https://openalex.org/W1641379095","https://openalex.org/W1963754118","https://openalex.org/W1967567143","https://openalex.org/W2037067712","https://openalex.org/W2087322096","https://openalex.org/W2115192345","https://openalex.org/W2263562440","https://openalex.org/W2407262400","https://openalex.org/W2914656440","https://openalex.org/W3132236529","https://openalex.org/W4285719527","https://openalex.org/W6689723076"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W2154793587","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W2123899227","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W4206669594","https://openalex.org/W20361778","https://openalex.org/W1997088969"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}