{"id":"https://openalex.org/W2106771422","doi":"https://doi.org/10.1109/icsmc.2004.1401152","title":"Reinforcement learning based on spatial and temporal association of states","display_name":"Reinforcement learning based on spatial and temporal association of states","publication_year":2005,"publication_date":"2005-03-31","ids":{"openalex":"https://openalex.org/W2106771422","doi":"https://doi.org/10.1109/icsmc.2004.1401152","mag":"2106771422"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2004.1401152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2004.1401152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)","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/A5008999201","display_name":"Xiaodong Zhuang","orcid":"https://orcid.org/0000-0001-6508-8507"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiao-Dong Zhuang","raw_affiliation_strings":["Computer Science Department, Ocean University of China, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100541458","display_name":"Qingchun Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing-Chun Meng","raw_affiliation_strings":["Computer Science Department, Ocean University of China, Qingdao, China","State Key Laboratory of Intelligent Technology and System, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and System, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100727286","display_name":"Bo Yin","orcid":"https://orcid.org/0000-0001-6318-0174"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Yin","raw_affiliation_strings":["Computer Science Department, Ocean University of China, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004375304","display_name":"Yun Gao","orcid":"https://orcid.org/0000-0002-2086-5218"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Gao","raw_affiliation_strings":["Computer Science Department, Ocean University of China, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008999201"],"corresponding_institution_ids":["https://openalex.org/I59028903"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13025659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":null,"first_page":"5980","last_page":"5984"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9937999844551086,"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/T10320","display_name":"Neural Networks and Applications","score":0.9922999739646912,"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":0.8423471450805664},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.7124643325805664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6717444062232971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6477203369140625},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.6176308989524841},{"id":"https://openalex.org/keywords/spatial-learning","display_name":"Spatial learning","score":0.5057437419891357},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4913994073867798},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4906660318374634},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4742012619972229},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.46605074405670166},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.45101621747016907},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.44374990463256836},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4307129383087158},{"id":"https://openalex.org/keywords/analogy","display_name":"Analogy","score":0.4242261052131653},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40328249335289},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17258301377296448},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.1369350254535675},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13122200965881348},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08615359663963318},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07685858011245728},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.059954285621643066}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8423471450805664},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.7124643325805664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6717444062232971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6477203369140625},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.6176308989524841},{"id":"https://openalex.org/C2985665543","wikidata":"https://www.wikidata.org/wiki/Q3560550","display_name":"Spatial learning","level":3,"score":0.5057437419891357},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4913994073867798},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4906660318374634},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4742012619972229},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.46605074405670166},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45101621747016907},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.44374990463256836},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4307129383087158},{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.4242261052131653},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40328249335289},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17258301377296448},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.1369350254535675},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13122200965881348},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08615359663963318},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07685858011245728},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.059954285621643066},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2781161787","wikidata":"https://www.wikidata.org/wiki/Q48360","display_name":"Hippocampus","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2004.1401152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2004.1401152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1492518272","https://openalex.org/W1610678877","https://openalex.org/W2107726111","https://openalex.org/W2160371091","https://openalex.org/W2396715201","https://openalex.org/W3020831056","https://openalex.org/W6629536611","https://openalex.org/W6636530465","https://openalex.org/W6683821272","https://openalex.org/W6711916277"],"related_works":["https://openalex.org/W3140225428","https://openalex.org/W235959167","https://openalex.org/W4213341750","https://openalex.org/W2610686804","https://openalex.org/W3148138296","https://openalex.org/W4310801741","https://openalex.org/W2141149254","https://openalex.org/W1987864653","https://openalex.org/W3042291365","https://openalex.org/W2313756439"],"abstract_inverted_index":{"In":[0,75],"this":[1],"paper,":[2],"mechanisms":[3],"in":[4,41,56],"human":[5,42],"learning":[6,12,16,20,70,95],"are":[7],"incorporated":[8],"into":[9],"the":[10,15,26,37,51,57,64,76,78,90],"reinforcement":[11],"to":[13,49,83],"improve":[14],"efficiency.":[17],"A":[18],"new":[19],"method":[21,80,92],"is":[22,34,47,67,81],"presented":[23],"based":[24],"on":[25],"spatial":[27,52],"and":[28,39],"temporal":[29],"association":[30,53],"of":[31,54,63],"states,":[32],"which":[33,87],"inspired":[35],"by":[36],"analogy":[38],"recall":[40],"learning.":[43],"The":[44,60],"fuzzy":[45],"state":[46,58],"proposed":[48,68,79,91],"represent":[50],"states":[55],"space.":[59],"delayed":[61],"optimization":[62],"control":[65],"process":[66],"for":[69],"with":[71],"temporally":[72],"correlated":[73],"states.":[74],"experiment,":[77],"applied":[82],"a":[84],"maze":[85],"problem,":[86],"shows":[88],"that":[89],"has":[93],"improved":[94],"performance.":[96]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}