{"id":"https://openalex.org/W2069796595","doi":"https://doi.org/10.4304/jsw.9.3.634-640","title":"Statistics Based Q-learning Algorithm for Multi-Agent System and Application in RoboCup","display_name":"Statistics Based Q-learning Algorithm for Multi-Agent System and Application in RoboCup","publication_year":2014,"publication_date":"2014-03-01","ids":{"openalex":"https://openalex.org/W2069796595","doi":"https://doi.org/10.4304/jsw.9.3.634-640","mag":"2069796595"},"language":"en","primary_location":{"id":"doi:10.4304/jsw.9.3.634-640","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.9.3.634-640","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","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/A5100934663","display_name":"Ya Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ya Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090846161","display_name":"Zhonghua Huang","orcid":"https://orcid.org/0000-0002-2627-411X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhonghua Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10172038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.98580002784729,"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":0.98580002784729,"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":0.9818000197410583,"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/T14011","display_name":"Elevator Systems and Control","score":0.9794999957084656,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9041032791137695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5580915808677673},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4902651607990265},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4497249126434326},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35298049449920654},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.16034486889839172}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9041032791137695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5580915808677673},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4902651607990265},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4497249126434326},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35298049449920654},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.16034486889839172}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4304/jsw.9.3.634-640","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.9.3.634-640","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","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":11,"referenced_works":["https://openalex.org/W1505888104","https://openalex.org/W1589901344","https://openalex.org/W1989168966","https://openalex.org/W2006303459","https://openalex.org/W2039492169","https://openalex.org/W2111895255","https://openalex.org/W2116935710","https://openalex.org/W2117546097","https://openalex.org/W2125631327","https://openalex.org/W2136125635","https://openalex.org/W2150149497"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4286629047","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4313488044","https://openalex.org/W3107602296","https://openalex.org/W3209574120","https://openalex.org/W4312192474"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"statistic":[3],"learning":[4,55,63,98],"based":[5],"Q-learning":[6,68],"algorithm":[7,58,82,91],"for":[8],"Multi-Agent":[9],"System,":[10],"the":[11,23,35,41,49,54,62,66,81,86,93],"agent":[12],"can":[13,59],"learn":[14],"other":[15,39],"agents\u2019":[16],"action":[17,51],"policies":[18,37,46],"through":[19],"observing":[20],"and":[21],"counting":[22],"joint":[24,43],"action,":[25],"a":[26],"concise":[27],"but":[28],"useful":[29],"hypothesis":[30],"is":[31,70],"adopted":[32],"to":[33,53,75],"denote":[34],"optimal":[36,50],"of":[38,45,80,89],"agents,":[40],"full":[42],"probability":[44],"distribution":[47],"guarantees":[48],"choice":[52],"agent.":[56],"The":[57,78],"also":[60],"improve":[61],"speed":[64],"because":[65],"conventional":[67],"space":[69],"cut":[71],"from":[72],"exponential":[73],"one":[74],"linear":[76],"one.":[77],"convergence":[79],"has":[83],"been":[84],"proved;":[85],"successful":[87],"application":[88],"this":[90],"in":[92],"RoboCup":[94],"shows":[95],"its":[96],"good":[97],"performance.":[99]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}