{"id":"https://openalex.org/W2139789552","doi":"https://doi.org/10.1109/cimca.2005.1631339","title":"K-Cluster Algorithm for Automatic Discovery of Subgoals in Reinforcement Learning","display_name":"K-Cluster Algorithm for Automatic Discovery of Subgoals in Reinforcement Learning","publication_year":2006,"publication_date":"2006-05-25","ids":{"openalex":"https://openalex.org/W2139789552","doi":"https://doi.org/10.1109/cimca.2005.1631339","mag":"2139789552"},"language":"en","primary_location":{"id":"doi:10.1109/cimca.2005.1631339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cimca.2005.1631339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06)","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/A5070843481","display_name":"Wang Ben-nian","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ben-Nian Wang","raw_affiliation_strings":["National Laboratory for Novel Software Technology, Nanjing University, China","National Lab. for Novel Software Technol., Nanjing Univ"],"affiliations":[{"raw_affiliation_string":"National Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"National Lab. for Novel Software Technol., Nanjing Univ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101489328","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-3568-222X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["National Laboratory for Novel Software Technology, Nanjing University, China","National Lab. for Novel Software Technol., Nanjing Univ"],"affiliations":[{"raw_affiliation_string":"National Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"National Lab. for Novel Software Technol., Nanjing Univ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043605963","display_name":"Zhao-Qian Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao-Qian Chen","raw_affiliation_strings":["National Laboratory for Novel Software Technology, Nanjing University, China","National Lab. for Novel Software Technol., Nanjing Univ"],"affiliations":[{"raw_affiliation_string":"National Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"National Lab. for Novel Software Technol., Nanjing Univ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112250453","display_name":"Junyuan Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun-Yuan Xie","raw_affiliation_strings":["National Laboratory for Novel Software Technology, Nanjing University, China","National Lab. for Novel Software Technol., Nanjing Univ"],"affiliations":[{"raw_affiliation_string":"National Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"National Lab. for Novel Software Technol., Nanjing Univ","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002901852","display_name":"Shifu Chen","orcid":"https://orcid.org/0000-0001-5799-653X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi-Fu Chen","raw_affiliation_strings":["National Laboratory for Novel Software Technology, Nanjing University, China","National Lab. for Novel Software Technol., Nanjing Univ"],"affiliations":[{"raw_affiliation_string":"National Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"National Lab. for Novel Software Technol., Nanjing Univ","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070843481"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13126584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"658","last_page":"662"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9890000224113464,"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":0.9843000173568726,"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":0.8156425952911377},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7484841346740723},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6518694758415222},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5903657078742981},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5633439421653748},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45641544461250305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4323524236679077},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38728153705596924},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.053225189447402954}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8156425952911377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7484841346740723},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6518694758415222},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5903657078742981},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5633439421653748},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45641544461250305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4323524236679077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38728153705596924},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.053225189447402954},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cimca.2005.1631339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cimca.2005.1631339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06)","raw_type":"proceedings-article"}],"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/W60146956","https://openalex.org/W1550667913","https://openalex.org/W1556824961","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2141559645","https://openalex.org/W2143435603","https://openalex.org/W2154318594","https://openalex.org/W2158548602","https://openalex.org/W6602475252","https://openalex.org/W6680976742","https://openalex.org/W6683033130","https://openalex.org/W6683443546"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Options":[0],"have":[1],"proven":[2],"to":[3,6,24],"be":[4],"useful":[5,16],"accelerate":[7],"agent's":[8],"learning":[9,13,74],"in":[10,37,50],"many":[11],"reinforcement":[12,73],"tasks,":[14],"determining":[15],"subgoals":[17,34,44,62],"is":[18,35],"a":[19],"key":[20],"step":[21],"for":[22,30],"agent":[23],"create":[25],"options.":[26],"A":[27],"K-cluster":[28,58],"algorithm":[29,41,59,69,77,85],"automatic":[31],"discovery":[32],"of":[33],"presented":[36],"this":[38,76],"paper.":[39],"This":[40],"can":[42,60],"extract":[43],"from":[45],"the":[46,57,66,72,79,82],"trajectories":[47],"collected":[48],"online":[49],"clustering":[51],"way.":[52],"The":[53],"experiments":[54],"show":[55],"that":[56,71],"find":[61],"more":[63],"efficiently":[64],"than":[65],"diverse":[67,83],"density":[68,84],"and":[70,86],"with":[75,81],"outperforms":[78],"one":[80],"flat":[87],"Q-learning":[88]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
