{"id":"https://openalex.org/W1886088309","doi":"https://doi.org/10.1007/978-3-540-74690-4_24","title":"Reinforcement Learning for Cooperative Actions in a Partially Observable Multi-agent System","display_name":"Reinforcement Learning for Cooperative Actions in a Partially Observable Multi-agent System","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W1886088309","doi":"https://doi.org/10.1007/978-3-540-74690-4_24","mag":"1886088309"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-74690-4_24","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-74690-4_24","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","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/A5100913560","display_name":"Yuki Taniguchi","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Taniguchi","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Takayama 8916-5, Ikoma, 630-0192, Japan","[Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Takayama 8916-5, Ikoma, 630-0192, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"[Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Japan]","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103376816","display_name":"Takeshi Mori","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Mori","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Takayama 8916-5, Ikoma, 630-0192, Japan","[Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Takayama 8916-5, Ikoma, 630-0192, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"[Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Japan]","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072540019","display_name":"Shin Ishii","orcid":"https://orcid.org/0000-0001-9385-8230"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shin Ishii","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Takayama 8916-5, Ikoma, 630-0192, Japan","[Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Takayama 8916-5, Ikoma, 630-0192, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"[Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Japan]","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.2226,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.44167846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"107","issue":"92","first_page":"229","last_page":"238"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9776999950408936,"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":0.9121999740600586,"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":0.8770495057106018},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8212741613388062},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.7134553790092468},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5451769232749939},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5379410982131958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5303616523742676},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5290666222572327},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5179364085197449},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.506622850894928},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4808824360370636},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.46854934096336365},{"id":"https://openalex.org/keywords/state-variable","display_name":"State variable","score":0.4518255591392517},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.3043747544288635},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23526588082313538},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14550158381462097},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07753413915634155}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8770495057106018},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212741613388062},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.7134553790092468},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5451769232749939},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5379410982131958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5303616523742676},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5290666222572327},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5179364085197449},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.506622850894928},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4808824360370636},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.46854934096336365},{"id":"https://openalex.org/C129537906","wikidata":"https://www.wikidata.org/wiki/Q7603913","display_name":"State variable","level":2,"score":0.4518255591392517},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.3043747544288635},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23526588082313538},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14550158381462097},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07753413915634155},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-540-74690-4_24","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-74690-4_24","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"mag:2940223825","is_oa":false,"landing_page_url":"https://www.ieice.org/ken/paper/20070615eAVe/eng/","pdf_url":null,"source":{"id":"https://openalex.org/S4306512848","display_name":"IEICE Technical Report; IEICE Tech. Rep.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEICE Technical Report; IEICE Tech. Rep.","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1530089576","https://openalex.org/W1542941925","https://openalex.org/W1557073320","https://openalex.org/W2113889826","https://openalex.org/W2119717200","https://openalex.org/W2147492008","https://openalex.org/W2168359464","https://openalex.org/W2169294731","https://openalex.org/W2169572888","https://openalex.org/W2492794003","https://openalex.org/W3103182070","https://openalex.org/W7035811936"],"related_works":["https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W1589140671","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247","https://openalex.org/W131709709"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}