{"id":"https://openalex.org/W2115450028","doi":null,"title":"Nonparametric Model-Based Reinforcement Learning","display_name":"Nonparametric Model-Based Reinforcement Learning","publication_year":1997,"publication_date":"1997-12-01","ids":{"openalex":"https://openalex.org/W2115450028","mag":"2115450028"},"language":"en","primary_location":{"id":"mag:2115450028","doi":null,"is_oa":false,"landing_page_url":"http://papers.nips.cc/paper/1476-nonparametric-model-based-reinforcement-learning.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Neural Information Processing Systems","raw_type":null},"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/A5055330939","display_name":"Christopher G. Atkeson","orcid":"https://orcid.org/0000-0003-4265-8452","observed_orcids":["https://orcid.org/0000-0003-4265-8452"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christopher G. Atkeson","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, Atlanta, GA and ATR Human Information Processing, Kyoto, Japan#TAB#"],"raw_orcid":"https://orcid.org/0000-0003-4265-8452","affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, Atlanta, GA and ATR Human Information Processing, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5055330939"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.4396,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.65543808,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"10","issue":null,"first_page":"1008","last_page":"1014"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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":0.0,"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/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.9940000176429749},{"id":"https://openalex.org/keywords/nonparametric-models","display_name":"nonparametric models","score":0.878000020980835},{"id":"https://openalex.org/keywords/model-learning","display_name":"model learning","score":0.796999990940094},{"id":"https://openalex.org/keywords/trajectory-optimization","display_name":"trajectory optimization","score":0.7710000276565552},{"id":"https://openalex.org/keywords/trajectory-planning","display_name":"trajectory planning","score":0.9729999899864197}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8573811054229736},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.775359034538269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7320431470870972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6215449571609497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6086858510971069},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.5233680009841919},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.5225540995597839},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.49423912167549133},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.42773425579071045},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3800724744796753},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14705300331115723},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.10832712054252625},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0670473575592041},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2115450028","doi":null,"is_oa":false,"landing_page_url":"http://papers.nips.cc/paper/1476-nonparametric-model-based-reinforcement-learning.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W658381347","https://openalex.org/W1491843047","https://openalex.org/W1540685400","https://openalex.org/W1595634327","https://openalex.org/W1597173708","https://openalex.org/W1689445748","https://openalex.org/W1980035368","https://openalex.org/W1987706689","https://openalex.org/W1990005421","https://openalex.org/W2009533501","https://openalex.org/W2013232999","https://openalex.org/W2086637623","https://openalex.org/W2105038027","https://openalex.org/W2107726111","https://openalex.org/W2148112459","https://openalex.org/W2170120409","https://openalex.org/W2796837256"],"related_works":["https://openalex.org/W50377150","https://openalex.org/W3007008575","https://openalex.org/W7098453715","https://openalex.org/W4390414273","https://openalex.org/W4287750003","https://openalex.org/W2903077796","https://openalex.org/W2998562709","https://openalex.org/W2138839127","https://openalex.org/W2970202659","https://openalex.org/W2331785277"],"abstract_inverted_index":{"This":[0],"paper":[1,23],"describes":[2],"some":[3],"of":[4,7,61],"the":[5,48,58,68,82,89],"interactions":[6],"model":[8,50,70],"learning":[9],"algorithms":[10,13],"and":[11],"planning":[12],"we":[14],"have":[15,52],"found":[16],"in":[17,57],"exploring":[18],"model-based":[19],"reinforcement":[20],"learning.":[21,62],"The":[22],"focuses":[24],"on":[25],"how":[26],"local":[27],"trajectory":[28,41],"optimizers":[29],"can":[30],"be":[31],"used":[32],"effectively":[33],"with":[34,47,71,88],"learned":[35,49,69,90],"non-parametric":[36],"models.":[37],"We":[38],"find":[39],"that":[40,43,65],"planners":[42,64],"are":[44],"fully":[45,86],"consistent":[46,87],"often":[51,77],"difficulty":[53],"finding":[54],"reasonable":[55],"plans":[56],"early":[59],"stages":[60],"Trajectory":[63],"balance":[66],"obeying":[67],"minimizing":[72],"cost":[73],"(or":[74],"maximizing":[75],"reward)":[76],"do":[78],"better,":[79],"even":[80],"if":[81],"plan":[83],"is":[84],"not":[85],"model.":[91]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}