{"id":"https://openalex.org/W1499896011","doi":"https://doi.org/10.1109/icsmc.2005.1571635","title":"Learning Policies for Abstract State Spaces","display_name":"Learning Policies for Abstract State Spaces","publication_year":2006,"publication_date":"2006-01-18","ids":{"openalex":"https://openalex.org/W1499896011","doi":"https://doi.org/10.1109/icsmc.2005.1571635","mag":"1499896011"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2005.1571635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2005.1571635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Systems, Man and Cybernetics","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/A5021553848","display_name":"Stephan Timmer","orcid":null},"institutions":[{"id":"https://openalex.org/I170658231","display_name":"Osnabr\u00fcck University","ror":"https://ror.org/04qmmjx98","country_code":"DE","type":"education","lineage":["https://openalex.org/I170658231"]},{"id":"https://openalex.org/I4210159638","display_name":"Hochschule Osnabr\u00fcck","ror":"https://ror.org/059vymd37","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210159638"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"S. Timmer","raw_affiliation_strings":["Neuroinformatics, University of Osnabr\u00fcck, Osnabruck, Germany","Neuroinformatics, Osnabrueck Univ., Germany"],"affiliations":[{"raw_affiliation_string":"Neuroinformatics, University of Osnabr\u00fcck, Osnabruck, Germany","institution_ids":["https://openalex.org/I170658231","https://openalex.org/I4210159638"]},{"raw_affiliation_string":"Neuroinformatics, Osnabrueck Univ., Germany","institution_ids":["https://openalex.org/I170658231"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041323275","display_name":"Martin Riedmiller","orcid":"https://orcid.org/0000-0002-8465-5690"},"institutions":[{"id":"https://openalex.org/I4210159638","display_name":"Hochschule Osnabr\u00fcck","ror":"https://ror.org/059vymd37","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210159638"]},{"id":"https://openalex.org/I170658231","display_name":"Osnabr\u00fcck University","ror":"https://ror.org/04qmmjx98","country_code":"DE","type":"education","lineage":["https://openalex.org/I170658231"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"M. Riedmiller","raw_affiliation_strings":["Neuroinformatics, University of Osnabr\u00fcck, Osnabruck, Germany","Neuroinformatics, Osnabrueck Univ., Germany"],"affiliations":[{"raw_affiliation_string":"Neuroinformatics, University of Osnabr\u00fcck, Osnabruck, Germany","institution_ids":["https://openalex.org/I170658231","https://openalex.org/I4210159638"]},{"raw_affiliation_string":"Neuroinformatics, Osnabrueck Univ., Germany","institution_ids":["https://openalex.org/I170658231"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021553848"],"corresponding_institution_ids":["https://openalex.org/I170658231","https://openalex.org/I4210159638"],"apc_list":null,"apc_paid":null,"fwci":0.9175,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77563895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"3179","last_page":"3184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9914000034332275,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9914000034332275,"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"}},{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9811999797821045,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9574999809265137,"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/partition","display_name":"Partition (number theory)","score":0.7209280729293823},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7136625647544861},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.6258461475372314},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5969793200492859},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5493648648262024},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5275753736495972},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4865192770957947},{"id":"https://openalex.org/keywords/partition-of-unity","display_name":"Partition of unity","score":0.43244698643684387},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41912198066711426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4019739031791687},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3280363082885742},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32566189765930176},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2595488131046295},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2093624770641327},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0661429762840271}],"concepts":[{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.7209280729293823},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7136625647544861},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.6258461475372314},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5969793200492859},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5493648648262024},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5275753736495972},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4865192770957947},{"id":"https://openalex.org/C102205669","wikidata":"https://www.wikidata.org/wiki/Q191690","display_name":"Partition of unity","level":3,"score":0.43244698643684387},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41912198066711426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4019739031791687},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3280363082885742},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32566189765930176},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2595488131046295},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2093624770641327},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0661429762840271},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icsmc.2005.1571635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2005.1571635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Systems, Man and Cybernetics","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.896","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ni.uos.de/fileadmin/user_upload/publications/timmer_smc05.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W136800639","https://openalex.org/W1552830313","https://openalex.org/W1688218840","https://openalex.org/W1754881896","https://openalex.org/W1966195676","https://openalex.org/W4231226883","https://openalex.org/W6605472423","https://openalex.org/W6637513772","https://openalex.org/W6637806891","https://openalex.org/W6812527618"],"related_works":["https://openalex.org/W2785634710","https://openalex.org/W2963813038","https://openalex.org/W4307127933","https://openalex.org/W4301020713","https://openalex.org/W4316650854","https://openalex.org/W1984215587","https://openalex.org/W2381320429","https://openalex.org/W3086381881","https://openalex.org/W2593957634","https://openalex.org/W2352690124"],"abstract_inverted_index":{"Applying":[0],"Q-learning":[1],"to":[2,62],"multidimensional,":[3],"real-valued":[4],"state":[5,26,47],"spaces":[6,48],"is":[7,28,39],"time-consuming":[8],"in":[9],"most":[10],"cases.":[11],"In":[12],"this":[13],"article,":[14],"we":[15,70,81],"deal":[16],"with":[17],"the":[18,25,74],"assumption":[19],"that":[20],"a":[21,55,66,83,90,97],"coarse":[22],"partition":[23],"of":[24],"space":[27],"sufficient":[29],"for":[30,45,68,89,96],"learning":[31,75],"good":[32],"or":[33],"even":[34],"optimal":[35],"policies.":[36],"An":[37],"algorithm":[38],"presented":[40],"which":[41],"constructs":[42],"proper":[43],"policies":[44],"abstract":[46],"using":[49],"an":[50,59],"incremental":[51],"procedure":[52],"without":[53],"approximating":[54],"Q-function.":[56],"By":[57],"combining":[58],"approach":[60],"similar":[61],"dynamic":[63],"programming":[64],"and":[65],"search":[67],"policies,":[69],"can":[71],"speed":[72],"up":[73],"process.":[76],"To":[77],"provide":[78],"empirical":[79],"evidence,":[80],"use":[82],"cart-pole":[84],"system.":[85],"Experiments":[86],"were":[87],"conducted":[88],"simulated":[91],"environment":[92],"as":[93,95],"well":[94],"real":[98],"plant.":[99]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
