{"id":"https://openalex.org/W4229063289","doi":"https://doi.org/10.1145/3477314.3507091","title":"Learning adaptive control in dynamic environments using reproducing kernel priors with bayesian policy gradients","display_name":"Learning adaptive control in dynamic environments using reproducing kernel priors with bayesian policy gradients","publication_year":2022,"publication_date":"2022-04-25","ids":{"openalex":"https://openalex.org/W4229063289","doi":"https://doi.org/10.1145/3477314.3507091"},"language":"en","primary_location":{"id":"doi:10.1145/3477314.3507091","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477314.3507091","pdf_url":null,"source":{"id":"https://openalex.org/S4363608665","display_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","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/A5057842142","display_name":"Apan Dastider","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Apan Dastider","raw_affiliation_strings":["University of Central Florida"],"affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048669336","display_name":"Sayyed Jaffar Ali Raza","orcid":"https://orcid.org/0000-0002-0948-8263"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sayyed Jaffar Ali Raza","raw_affiliation_strings":["University of Central Florida"],"affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060908808","display_name":"Mingjie Lin","orcid":"https://orcid.org/0000-0002-3225-4406"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingjie Lin","raw_affiliation_strings":["University of Central Florida"],"affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057842142"],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":0.1039,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.24267399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"748","last_page":"757"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9937000274658203,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9921000003814697,"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":0.7206384539604187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6578742265701294},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6111097931861877},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5914502143859863},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.576748251914978},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5572100877761841},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.47909215092658997},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4739677608013153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4508884847164154},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.44074639678001404},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.41528576612472534},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40631619095802307},{"id":"https://openalex.org/keywords/hilbert-space","display_name":"Hilbert space","score":0.32767438888549805},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.2947884202003479},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2567131519317627}],"concepts":[{"id":"https://openalex.org/C80884492","wikidata":"https://www.wikidata.org/wiki/Q3345678","display_name":"Reproducing kernel Hilbert space","level":3,"score":0.7206384539604187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6578742265701294},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6111097931861877},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5914502143859863},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.576748251914978},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5572100877761841},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.47909215092658997},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4739677608013153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4508884847164154},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.44074639678001404},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.41528576612472534},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40631619095802307},{"id":"https://openalex.org/C62799726","wikidata":"https://www.wikidata.org/wiki/Q190056","display_name":"Hilbert space","level":2,"score":0.32767438888549805},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2947884202003479},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2567131519317627},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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:10.1145/3477314.3507091","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477314.3507091","pdf_url":null,"source":{"id":"https://openalex.org/S4363608665","display_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2031727428","https://openalex.org/W2100470760","https://openalex.org/W2100785108","https://openalex.org/W2110720940","https://openalex.org/W2149479912","https://openalex.org/W2164569010","https://openalex.org/W2238358308","https://openalex.org/W2747329762","https://openalex.org/W2760355785","https://openalex.org/W2762656673","https://openalex.org/W2967075852","https://openalex.org/W3003373508","https://openalex.org/W3003894547","https://openalex.org/W3126321819","https://openalex.org/W3204843673","https://openalex.org/W4205559380","https://openalex.org/W6684489750"],"related_works":["https://openalex.org/W2580650124","https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W3142333283","https://openalex.org/W3122088529","https://openalex.org/W3041320102","https://openalex.org/W2111669074","https://openalex.org/W2085259108","https://openalex.org/W3123087812","https://openalex.org/W4387349426"],"abstract_inverted_index":{"One":[0],"of":[1,47,107,118,144],"the":[2,33,150],"most":[3],"distinctive":[4],"characteristics":[5],"in":[6,25,61,127],"biological":[7],"evolution":[8],"is":[9],"to":[10,93,104,112,121,153],"not":[11],"only":[12],"learn":[13],"and":[14,90],"reinforce":[15],"knowledge":[16],"from":[17,142],"prior":[18,76],"experience,":[19],"but":[20],"also":[21],"develop":[22,133],"a":[23,44,145],"solution":[24],"(pseudo)":[26],"real-time":[27],"for":[28,53,97],"future":[29],"events":[30],"by":[31,37],"studying":[32],"past":[34],"choices.":[35],"Inspired":[36],"this":[38,102],"observation,":[39],"we":[40,110,132],"aim":[41],"at":[42],"developing":[43],"systematic":[45],"methodology":[46],"dynamically":[48,98],"learning":[49,73],"effective":[50],"control":[51],"policy":[52,83,96,123,134],"robotic":[54],"manipulators":[55],"that":[56],"deftly":[57],"avoid":[58],"dynamic":[59],"obstacles":[60,66],"fast-changing":[62],"environments.":[63,100],"Unfortunately,":[64],"dynamical":[65],"present":[67],"time-varying":[68],"statistical":[69],"sensory":[70],"irregularities,":[71],"making":[72],"based":[74],"on":[75],"experience":[77],"much":[78],"less":[79],"productive.":[80],"Furthermore,":[81,131],"off-the-shelf":[82],"gradient":[84],"methods":[85],"often":[86],"become":[87],"computationally":[88],"expensive,":[89],"sometimes":[91],"intractable,":[92],"adapt":[94],"existing":[95],"changing":[99],"In":[101],"paper,":[103],"mitigate":[105],"both":[106],"these":[108],"challenges,":[109],"propose":[111],"use":[113],"vector-valued":[114],"kernel":[115],"embedding":[116],"(instead":[117],"parameter":[119],"vectors)":[120],"represent":[122],"distribution":[124],"as":[125,156],"features":[126],"non-decreasing":[128],"Euclidean":[129],"space.":[130],"search":[135,151],"algorithm":[136],"over":[137],"Bayesian":[138],"posterior":[139],"estimation":[140],"derived":[141],"inner-product":[143],"priori":[146],"Gaussian":[147],"kernels,":[148],"allowing":[149],"space":[152],"be":[154],"defined":[155],"high":[157],"(possibly":[158],"infinite)":[159],"dimensional":[160],"Reproducing":[161],"Kernel":[162],"Hilbert":[163],"Space":[164],"(RKHS).":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}