{"id":"https://openalex.org/W2087104403","doi":"https://doi.org/10.1109/icsmc.2012.6378111","title":"Adaptive state aggregation for reinforcement learning","display_name":"Adaptive state aggregation for reinforcement learning","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W2087104403","doi":"https://doi.org/10.1109/icsmc.2012.6378111","mag":"2087104403"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2012.6378111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2012.6378111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"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/A5061189209","display_name":"Kao\u2010Shing Hwang","orcid":"https://orcid.org/0000-0001-9234-4836"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kao-Shing Hwang","raw_affiliation_strings":["Department of Electrical Engineering, National Sun Yat-Sen University, Kaohsiung, Taiwan","Department of Electrical Engineering, National Sun Yat-Sen University, Kaohsiung, Taiwan, ROC#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Sun Yat-Sen University, Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I142974352"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Sun Yat-Sen University, Kaohsiung, Taiwan, ROC#TAB#","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731680","display_name":"Yu-Jen Chen","orcid":"https://orcid.org/0000-0003-0288-0796"},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Jen Chen","raw_affiliation_strings":["Department of Electrical Engineering, National Chung Cheng University, Chiayi, Taiwan","Department of Electrical Engineering, National Chung Cheng University, Chiayi Taiwan, ROC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chung Cheng University, Chiayi, Taiwan","institution_ids":["https://openalex.org/I148099254"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Chung Cheng University, Chiayi Taiwan, ROC","institution_ids":["https://openalex.org/I148099254"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001081733","display_name":"Wei\u2010Cheng Jiang","orcid":"https://orcid.org/0000-0003-4432-8801"},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Cheng Jiang","raw_affiliation_strings":["Department of Electrical Engineering, National Chung Cheng University, Chiayi, Taiwan","Department of Electrical Engineering, National Chung Cheng University, Chiayi Taiwan, ROC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chung Cheng University, Chiayi, Taiwan","institution_ids":["https://openalex.org/I148099254"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Chung Cheng University, Chiayi Taiwan, ROC","institution_ids":["https://openalex.org/I148099254"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5203,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62438971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"4","issue":null,"first_page":"2452","last_page":"2456"},"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":0.9984999895095825,"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":0.9876000285148621,"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":0.9085311889648438},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.7586287260055542},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7245108485221863},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.6161342859268188},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.6013457775115967},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.5401924848556519},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5078971982002258},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.5069513320922852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49147188663482666},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.47889915108680725},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4644169211387634},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4569341540336609},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.44400155544281006},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.44360747933387756},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40101003646850586},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3257898986339569},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18719449639320374},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17681258916854858},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1038961112499237},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09489983320236206}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9085311889648438},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.7586287260055542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245108485221863},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.6161342859268188},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.6013457775115967},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.5401924848556519},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5078971982002258},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.5069513320922852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49147188663482666},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.47889915108680725},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4644169211387634},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4569341540336609},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.44400155544281006},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.44360747933387756},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40101003646850586},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3257898986339569},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18719449639320374},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17681258916854858},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1038961112499237},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09489983320236206},{"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2012.6378111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2012.6378111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W94571269","https://openalex.org/W1592847719","https://openalex.org/W1625390266","https://openalex.org/W2021247827","https://openalex.org/W2060422862","https://openalex.org/W2097082695","https://openalex.org/W2107726111","https://openalex.org/W4214717370","https://openalex.org/W6603851545","https://openalex.org/W6636578284"],"related_works":["https://openalex.org/W2571592646","https://openalex.org/W4247855592","https://openalex.org/W2567165815","https://openalex.org/W2740304877","https://openalex.org/W2978000411","https://openalex.org/W2153039919","https://openalex.org/W2765689447","https://openalex.org/W2190656493","https://openalex.org/W4206173588","https://openalex.org/W2331527865"],"abstract_inverted_index":{"State":[0],"partition":[1,24],"is":[2,26,97],"an":[3,21],"important":[4],"issue":[5],"in":[6],"reinforcement":[7,56,60],"learning,":[8],"because":[9],"it":[10],"has":[11,109],"a":[12,78],"significant":[13],"effect":[14],"on":[15],"the":[16,30,45,50,55,59,63,68,73,87,90,102,115,120],"performance.":[17],"In":[18],"this":[19],"paper,":[20],"adaptive":[22],"state":[23,31,46,64],"method":[25,43,117],"presented":[27],"for":[28,106],"discretizing":[29],"space":[32,47,65],"adaptively":[33],"and":[34,89],"makes":[35],"use":[36],"of":[37],"decision":[38,69],"trees":[39],"effectively.":[40],"The":[41],"proposed":[42,99,116],"splits":[44],"according":[48,85],"to":[49,71,86,100,112],"temporal":[51],"difference":[52],"generated":[53],"by":[54,67],"learning.":[57],"Consequently,":[58],"learning":[61],"uses":[62],"partitioned":[66],"tree":[70],"learn":[72],"policy":[74],"simultaneously.":[75],"For":[76],"avoiding":[77],"trivial":[79],"partition,":[80],"sibling":[81],"nodes":[82],"are":[83],"pruned":[84],"Activity":[88],"Reliability.":[91],"A":[92,104],"Monte-Carlo":[93],"Tree":[94],"Search":[95],"(MCTS)":[96],"also":[98],"explore":[101],"policy.":[103],"simulation":[105],"approaching":[107],"goal":[108],"been":[110],"conducted":[111],"demonstrate":[113],"that":[114],"can":[118],"achieve":[119],"design":[121],"goal.":[122]},"counts_by_year":[{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}