{"id":"https://openalex.org/W98006832","doi":null,"title":"Reinforcement Learning and Function Approximation.","display_name":"Reinforcement Learning and Function Approximation.","publication_year":2005,"publication_date":"2005-12-01","ids":{"openalex":"https://openalex.org/W98006832","mag":"98006832"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.490.3079","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.490.3079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aaai.org/Papers/FLAIRS/2005/Flairs05-075.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5045500422","display_name":"Marina Irodova","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marina Irodova","raw_affiliation_strings":["University of Illinois at Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078127997","display_name":"Robert H. Sloan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert H. Sloan","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Chicago,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Chicago,#TAB#","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I39422238"],"apc_list":null,"apc_paid":null,"fwci":0.6682,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.73340952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"455","last_page":"460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0015999999595806003,"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/T12072","display_name":"Machine Learning and Algorithms","score":9.999999747378752e-05,"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/relational-reinforcement-learning","display_name":"relational reinforcement learning","score":0.9380000233650208},{"id":"https://openalex.org/keywords/function-approximation","display_name":"function approximation","score":0.9490000009536743},{"id":"https://openalex.org/keywords/planning","display_name":"planning","score":0.41200000047683716},{"id":"https://openalex.org/keywords/structural-learning","display_name":"structural learning","score":0.6159999966621399},{"id":"https://openalex.org/keywords/relational-representation","display_name":"relational representation","score":0.5389999747276306},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.47600001096725464}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9364691972732544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7130428552627563},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.64119553565979},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.6109268665313721},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5915935039520264},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5468844175338745},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5017149448394775},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4972539246082306},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4587993025779724},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4545125961303711},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.436208039522171},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42662110924720764},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.4253385663032532},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4220349192619324},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.413216769695282},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17361962795257568},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.1663202941417694},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15294203162193298},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.08267709612846375},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06280425190925598},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.490.3079","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.490.3079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aaai.org/Papers/FLAIRS/2005/Flairs05-075.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.81.7833","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.81.7833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uic.edu/~sloan/my-papers/FLAIRS05-to-appear.pdf","raw_type":"text"},{"id":"mag:98006832","doi":null,"is_oa":false,"landing_page_url":"https://www.aaai.org/Papers/FLAIRS/2005/Flairs05-075.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306421048","display_name":"The Florida AI Research Society","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"The Florida AI Research Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1525999779","https://openalex.org/W1545262042","https://openalex.org/W1555244713","https://openalex.org/W1816257748","https://openalex.org/W2107726111","https://openalex.org/W2109722166","https://openalex.org/W2122410182","https://openalex.org/W2145805610","https://openalex.org/W2158548602","https://openalex.org/W2169982856","https://openalex.org/W2521075165","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3020831056"],"related_works":["https://openalex.org/W1993907735","https://openalex.org/W3020831056","https://openalex.org/W7098090319","https://openalex.org/W30507863","https://openalex.org/W7095367389","https://openalex.org/W7100943048","https://openalex.org/W7099986400","https://openalex.org/W38340148","https://openalex.org/W4253865213","https://openalex.org/W7099236363"],"abstract_inverted_index":{"Relational":[0],"reinforcement":[1,22,89],"learning":[2,6,23,26,54,61,90,98],"combines":[3],"traditional":[4],"rein-forcement":[5],"with":[7,100,130],"a":[8,12,25,63,74,84,119],"strong":[9],"emphasis":[10],"on":[11,24,118,128],"relational":[13,21,138],"(rather":[14],"than":[15,136],"attribute-value)":[16],"representation.":[17],"Earlier":[18],"work":[19],"used":[20],"version":[27,36],"of":[28,46,121],"the":[29,38,44,137],"classic":[30],"Blocks":[31],"World":[32],"planning":[33],"problem":[34,111],"(a":[35],"where":[37],"learner":[39],"does":[40],"not":[41],"know":[42],"what":[43],"result":[45],"taking":[47],"an":[48],"action":[49],"will":[50],"be).":[51],"\u201cStructural":[52],"\u201d":[53],"results":[55],"have":[56],"been":[57],"obtained,":[58],"such":[59],"as":[60],"in":[62,73],"mixed":[64],"3\u20135":[65],"block":[66,78],"environment":[67],"and":[68,124],"being":[69],"able":[70],"to":[71,88,107],"perform":[72],"3":[75],"or":[76],"10":[77],"environment.":[79],"Here":[80],"we":[81,115],"instead":[82],"take":[83],"function":[85],"approximation":[86],"approach":[87],"for":[91,141],"this":[92],"same":[93],"problem.":[94],"We":[95],"obtain":[96],"similar":[97],"accuracies,":[99],"much":[101,109],"better":[102],"running":[103],"times,":[104],"allowing":[105],"us":[106],"consider":[108],"larger":[110],"sizes.":[112],"For":[113],"in-stance,":[114],"can":[116],"train":[117],"mix":[120],"3\u20137":[122],"blocks":[123],"then":[125],"per-form":[126],"well":[127],"worlds":[129],"100\u2013800":[131],"blocks\u2014using":[132],"less":[133],"run-ning":[134],"time":[135],"method":[139],"required":[140],"3\u201310":[142],"blocks.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}