{"id":"https://openalex.org/W4312954585","doi":"https://doi.org/10.1109/case49997.2022.9926573","title":"Non-Parametric Stochastic Policy Gradient with Strategic Retreat for Non-Stationary Environment","display_name":"Non-Parametric Stochastic Policy Gradient with Strategic Retreat for Non-Stationary Environment","publication_year":2022,"publication_date":"2022-08-20","ids":{"openalex":"https://openalex.org/W4312954585","doi":"https://doi.org/10.1109/case49997.2022.9926573"},"language":"en","primary_location":{"id":"doi:10.1109/case49997.2022.9926573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case49997.2022.9926573","pdf_url":null,"source":{"id":"https://openalex.org/S4363607892","display_name":"2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)","issn_l":"2161-8070","issn":["2161-8070"],"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":"2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},"type":"conference-paper","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":false,"raw_author_name":"Apan Dastider","raw_affiliation_strings":["Univ. of Central Florida,Dept. of ECE,Orlando,FL,USA","Dept. of ECE, Univ. of Central Florida, Orlando, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Central Florida,Dept. of ECE,Orlando,FL,USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"Dept. of ECE, Univ. of Central Florida, Orlando, FL, USA","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":["Univ. of Central Florida,Dept. of ECE,Orlando,FL,USA","Dept. of ECE, Univ. of Central Florida, Orlando, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Central Florida,Dept. of ECE,Orlando,FL,USA","institution_ids":["https://openalex.org/I106165777"]},{"raw_affiliation_string":"Dept. of ECE, Univ. of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":0.1687,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45633901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996399998664856,"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":0.996399998664856,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9736999869346619,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9484000205993652,"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":0.7119306921958923},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6367630362510681},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6224310994148254},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5699996948242188},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5470876693725586},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5421918034553528},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5087187886238098},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49069035053253174},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4850710928440094},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.4567107558250427},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44971808791160583},{"id":"https://openalex.org/keywords/hilbert-space","display_name":"Hilbert space","score":0.28717124462127686},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20656904578208923},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14426898956298828},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10173317790031433}],"concepts":[{"id":"https://openalex.org/C80884492","wikidata":"https://www.wikidata.org/wiki/Q3345678","display_name":"Reproducing kernel Hilbert space","level":3,"score":0.7119306921958923},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6367630362510681},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6224310994148254},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5699996948242188},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5470876693725586},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5421918034553528},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5087187886238098},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49069035053253174},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4850710928440094},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.4567107558250427},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44971808791160583},{"id":"https://openalex.org/C62799726","wikidata":"https://www.wikidata.org/wiki/Q190056","display_name":"Hilbert space","level":2,"score":0.28717124462127686},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20656904578208923},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14426898956298828},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10173317790031433},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case49997.2022.9926573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case49997.2022.9926573","pdf_url":null,"source":{"id":"https://openalex.org/S4363607892","display_name":"2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)","issn_l":"2161-8070","issn":["2161-8070"],"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":"2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2065805792","https://openalex.org/W2123107849","https://openalex.org/W4285290579","https://openalex.org/W149320920","https://openalex.org/W3125885229","https://openalex.org/W1527525543","https://openalex.org/W2370512383","https://openalex.org/W2896570485","https://openalex.org/W1835315728","https://openalex.org/W2962818398"],"abstract_inverted_index":{"In":[0,38],"modern":[1],"robotics,":[2],"effectively":[3],"computing":[4],"optimal":[5,52,129],"control":[6,53],"policies":[7,54],"under":[8],"dynamically":[9,47,159],"varying":[10],"environments":[11],"poses":[12],"substantial":[13],"challenges":[14],"to":[15,46,87],"the":[16,24,60,75,105,117,128,167],"off-the-shelf":[17],"parametric":[18],"policy":[19,35,72],"gradient":[20,36],"methods,":[21],"such":[22],"as":[23,74,90],"Deep":[25,33],"Deterministic":[26,34],"Policy":[27],"Gradient":[28],"(DDPG)":[29],"and":[30,153,170],"Twin":[31],"Delayed":[32],"(TD3).":[37],"this":[39],"paper,":[40],"we":[41,111,145],"propose":[42],"a":[43,49,71,78,91,123,174],"systematic":[44],"methodology":[45,69,164,172],"learn":[48],"sequence":[50],"of":[51,119,126,131,179],"non-parametrically,":[55],"while":[56],"autonomously":[57],"adapting":[58],"with":[59,116,149,158],"constantly":[61],"changing":[62,160],"environment":[63],"dynamics.":[64],"Specifically,":[65],"our":[66,113,142,163],"non-parametric":[67,114],"kernel-based":[68],"embeds":[70],"distribution":[73],"features":[76],"in":[77,109,177],"non-decreasing":[79],"Euclidean":[80],"space,":[81],"therefore":[82],"allowing":[83],"its":[84],"search":[85],"space":[86],"be":[88],"defined":[89],"very":[92],"high":[93],"(possible":[94],"infinite)":[95],"dimensional":[96],"RKHS":[97],"(Reproducing":[98],"Kernel":[99],"Hilbert":[100],"Space).":[101],"Moreover,":[102],"by":[103,173],"leveraging":[104],"similarity":[106],"metric":[107],"computed":[108],"RKHS,":[110],"augmented":[112],"learning":[115,180],"technique":[118],"AdaptiveH\u2014":[120],"adaptively":[121],"selecting":[122],"time-frame":[124],"window":[125],"finishing":[127],"part":[130],"whole":[132],"action-sequence":[133],"sampled":[134],"on":[135],"some":[136],"preceding":[137],"observed":[138],"state.":[139],"To":[140],"validate":[141],"proposed":[143],"approach,":[144],"conducted":[146],"extensive":[147],"experiments":[148],"multiple":[150],"classic":[151],"benchmarks":[152],"one":[154],"robotics":[155],"benchmark":[156],"equipped":[157],"environments.":[161],"Overall,":[162],"has":[165],"outperformed":[166],"well-established":[168],"DDPG":[169],"TD3":[171],"sizeable":[175],"margin":[176],"terms":[178],"performance.":[181]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}