{"id":"https://openalex.org/W2963672698","doi":"https://doi.org/10.23919/acc.2018.8430925","title":"Nonparametric Stochastic Compositional Gradient Descent for Q-Learning in Continuous Markov Decision Problems","display_name":"Nonparametric Stochastic Compositional Gradient Descent for Q-Learning in Continuous Markov Decision Problems","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2963672698","doi":"https://doi.org/10.23919/acc.2018.8430925","mag":"2963672698"},"language":"en","primary_location":{"id":"doi:10.23919/acc.2018.8430925","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2018.8430925","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Annual American Control Conference (ACC)","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/A5023551962","display_name":"Ekaterina Tolstaya","orcid":"https://orcid.org/0000-0003-0275-9574"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ekaterina Tolstaya","raw_affiliation_strings":["Department of ESE, University of Pennsylvania, Philadelphia, PA"],"affiliations":[{"raw_affiliation_string":"Department of ESE, University of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025896653","display_name":"Alec Koppel","orcid":"https://orcid.org/0000-0003-2447-2873"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alec Koppel","raw_affiliation_strings":["Computational and Information Sciences Directorate, U.S. Army Research Laboratory, Adelphi, MD"],"affiliations":[{"raw_affiliation_string":"Computational and Information Sciences Directorate, U.S. Army Research Laboratory, Adelphi, MD","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013003113","display_name":"Ethan Stump","orcid":"https://orcid.org/0000-0002-0119-2169"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ethan Stump","raw_affiliation_strings":["Computational and Information Sciences Directorate, U.S. Army Research Laboratory, Adelphi, MD"],"affiliations":[{"raw_affiliation_string":"Computational and Information Sciences Directorate, U.S. Army Research Laboratory, Adelphi, MD","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078862959","display_name":"Alejandro Ribeiro","orcid":"https://orcid.org/0000-0003-4230-9906"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alejandro Ribeiro","raw_affiliation_strings":["Department of ESE, University of Pennsylvania, Philadelphia, PA"],"affiliations":[{"raw_affiliation_string":"Department of ESE, University of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023551962"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":2.4433,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91697851,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6608","last_page":"6615"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9994999766349792,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9994999766349792,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9962999820709229,"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/reproducing-kernel-hilbert-space","display_name":"Reproducing kernel Hilbert space","score":0.8635157346725464},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6426569819450378},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6054498553276062},{"id":"https://openalex.org/keywords/descent-direction","display_name":"Descent direction","score":0.5474165678024292},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5400546193122864},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4837181866168976},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.46895450353622437},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.43327903747558594},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4176880419254303},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4143199622631073},{"id":"https://openalex.org/keywords/hilbert-space","display_name":"Hilbert space","score":0.3737354278564453},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.3662087321281433},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3651966452598572},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.32888782024383545},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2990974187850952},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17457789182662964},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.13839980959892273},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09124526381492615}],"concepts":[{"id":"https://openalex.org/C80884492","wikidata":"https://www.wikidata.org/wiki/Q3345678","display_name":"Reproducing kernel Hilbert space","level":3,"score":0.8635157346725464},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6426569819450378},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6054498553276062},{"id":"https://openalex.org/C116149140","wikidata":"https://www.wikidata.org/wiki/Q2070951","display_name":"Descent direction","level":4,"score":0.5474165678024292},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5400546193122864},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4837181866168976},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.46895450353622437},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43327903747558594},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4176880419254303},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4143199622631073},{"id":"https://openalex.org/C62799726","wikidata":"https://www.wikidata.org/wiki/Q190056","display_name":"Hilbert space","level":2,"score":0.3737354278564453},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.3662087321281433},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3651966452598572},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.32888782024383545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2990974187850952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17457789182662964},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.13839980959892273},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09124526381492615},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc.2018.8430925","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2018.8430925","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Annual American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1494085563","https://openalex.org/W1529558080","https://openalex.org/W1540155273","https://openalex.org/W1541527977","https://openalex.org/W1550698229","https://openalex.org/W1600437712","https://openalex.org/W1646707810","https://openalex.org/W1757796397","https://openalex.org/W1977655452","https://openalex.org/W1980516134","https://openalex.org/W1995033525","https://openalex.org/W2015418199","https://openalex.org/W2015904350","https://openalex.org/W2071983464","https://openalex.org/W2098613147","https://openalex.org/W2100677568","https://openalex.org/W2113484479","https://openalex.org/W2121863487","https://openalex.org/W2131831090","https://openalex.org/W2132849848","https://openalex.org/W2134042548","https://openalex.org/W2136687243","https://openalex.org/W2139418546","https://openalex.org/W2147750403","https://openalex.org/W2151693816","https://openalex.org/W2155027007","https://openalex.org/W2165905123","https://openalex.org/W2173248099","https://openalex.org/W2294586855","https://openalex.org/W2756361477","https://openalex.org/W2912289066","https://openalex.org/W2913243980","https://openalex.org/W2962755279","https://openalex.org/W2963672698","https://openalex.org/W2963864421","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W4233696721","https://openalex.org/W4245296547","https://openalex.org/W4298857966","https://openalex.org/W4302236756","https://openalex.org/W6635902665","https://openalex.org/W6676812857","https://openalex.org/W6679599195","https://openalex.org/W6680187362","https://openalex.org/W6680307681","https://openalex.org/W6683204974","https://openalex.org/W6750925820","https://openalex.org/W6758804334"],"related_works":["https://openalex.org/W2123107849","https://openalex.org/W2152670157","https://openalex.org/W4308702637","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2156021013","https://openalex.org/W2903299703","https://openalex.org/W2016648086","https://openalex.org/W3105579180","https://openalex.org/W2808418668"],"abstract_inverted_index":{"We":[0,36,67,140],"consider":[1],"Markov":[2],"Decision":[3],"Problems":[4],"defined":[5,45,59],"over":[6,46,60],"continuous":[7,182],"state":[8,199],"and":[9,95,124,192],"action":[10],"spaces,":[11],"where":[12],"an":[13],"autonomous":[14],"agent":[15],"seeks":[16],"to":[17,24,28,76,81,118,153,175],"learn":[18],"a":[19,53,61,69,88,128,154,161],"map":[20],"from":[21],"its":[22,30],"states":[23],"actions":[25],"so":[26],"as":[27],"maximize":[29],"long-term":[31],"discounted":[32],"accumulation":[33],"of":[34,72,84,92,121,135,157,164,200],"rewards.":[35],"address":[37],"this":[38,109,158],"problem":[39,58],"by":[40],"considering":[41],"Bellman's":[42],"optimality":[43,167],"equation":[44],"action-value":[47,190],"functions,":[48],"which":[49,99,126],"we":[50,112],"reformulate":[51],"into":[52],"nested":[54],"non-convex":[55],"stochastic":[56,73],"optimization":[57,138],"Reproducing":[62],"Kernel":[63,114],"Hilbert":[64],"Space":[65],"(RKHS).":[66],"develop":[68],"functional":[70],"generalization":[71],"quasi-gradient":[74],"method":[75],"solve":[77],"it,":[78],"which,":[79],"owing":[80],"the":[82,85,103,119,132,136,143,165,170,176,181,198,201],"structure":[83],"RKHS,":[86],"admits":[87],"parameterization":[89],"in":[90,131],"terms":[91],"scalar":[93],"weights":[94,123],"past":[96],"state-action":[97],"pairs":[98],"grows":[100],"proportionately":[101],"with":[102,150,197],"algorithm":[104],"iteration":[105],"index.":[106],"To":[107],"ameliorate":[108],"complexity":[110],"explosion,":[111],"apply":[113],"Orthogonal":[115],"Matching":[116],"Pursuit":[117],"sequence":[120],"kernel":[122],"dictionaries,":[125],"yields":[127,186],"controllable":[129],"error":[130],"descent":[133],"direction":[134],"underlying":[137],"method.":[139],"prove":[141],"that":[142,172,194],"resulting":[144],"algorithm,":[145],"called":[146],"KQ":[147],"Learning,":[148],"converges":[149],"probability":[151],"1":[152],"stationary":[155],"point":[156,163],"problem,":[159],"yielding":[160],"fixed":[162],"Bellman":[166],"operator":[168],"under":[169],"hypothesis":[171],"it":[173],"belongs":[174],"RKHS.":[177],"Numerical":[178],"evaluation":[179],"on":[180],"Mountain":[183],"Car":[184],"task":[185],"convergent":[187],"parsimonious":[188],"learned":[189],"functions":[191],"policies":[193],"are":[195],"competitive":[196],"art.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}