{"id":"https://openalex.org/W3185807839","doi":"https://doi.org/10.1109/tie.2021.3099234","title":"Reinforcement Learning With Constrained Uncertain Reward Function Through Particle Filtering","display_name":"Reinforcement Learning With Constrained Uncertain Reward Function Through Particle Filtering","publication_year":2021,"publication_date":"2021-07-28","ids":{"openalex":"https://openalex.org/W3185807839","doi":"https://doi.org/10.1109/tie.2021.3099234","mag":"3185807839"},"language":"en","primary_location":{"id":"doi:10.1109/tie.2021.3099234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tie.2021.3099234","pdf_url":null,"source":{"id":"https://openalex.org/S58031724","display_name":"IEEE Transactions on Industrial Electronics","issn_l":"0278-0046","issn":["0278-0046","1557-9948"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Industrial Electronics","raw_type":"journal-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/A5084963030","display_name":"Oguzhan Dogru","orcid":"https://orcid.org/0000-0002-6745-4117"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Oguzhan Dogru","raw_affiliation_strings":["Department of Chemical and Materials Engineering, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":"https://orcid.org/0000-0002-6745-4117","affiliations":[{"raw_affiliation_string":"Department of Chemical and Materials Engineering, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017597087","display_name":"Ranjith Chiplunkar","orcid":"https://orcid.org/0000-0001-5546-0918"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ranjith Chiplunkar","raw_affiliation_strings":["Department of Chemical and Materials Engineering, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":"https://orcid.org/0000-0001-5546-0918","affiliations":[{"raw_affiliation_string":"Department of Chemical and Materials Engineering, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100432851","display_name":"Biao Huang","orcid":"https://orcid.org/0000-0001-9082-2216"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Biao Huang","raw_affiliation_strings":["Department of Chemical and Materials Engineering, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":"https://orcid.org/0000-0001-9082-2216","affiliations":[{"raw_affiliation_string":"Department of Chemical and Materials Engineering, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":1.3534,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.80468986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"69","issue":"7","first_page":"7491","last_page":"7499"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.9891999959945679,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8080195784568787},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6917082667350769},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6723917722702026},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6400552988052368},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6394416689872742},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5358542203903198},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.5093642473220825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49826550483703613},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45407283306121826},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41506093740463257},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41336822509765625},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3308750092983246},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1820577085018158},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08943766355514526}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8080195784568787},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6917082667350769},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6723917722702026},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6400552988052368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6394416689872742},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5358542203903198},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.5093642473220825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49826550483703613},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45407283306121826},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41506093740463257},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41336822509765625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3308750092983246},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1820577085018158},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08943766355514526},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tie.2021.3099234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tie.2021.3099234","pdf_url":null,"source":{"id":"https://openalex.org/S58031724","display_name":"IEEE Transactions on Industrial Electronics","issn_l":"0278-0046","issn":["0278-0046","1557-9948"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Industrial Electronics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1557517019","https://openalex.org/W1959608418","https://openalex.org/W1967995127","https://openalex.org/W1972967324","https://openalex.org/W1980516134","https://openalex.org/W2037514740","https://openalex.org/W2045173716","https://openalex.org/W2050521487","https://openalex.org/W2051146554","https://openalex.org/W2098630962","https://openalex.org/W2105078254","https://openalex.org/W2105934661","https://openalex.org/W2130363011","https://openalex.org/W2133902258","https://openalex.org/W2134831125","https://openalex.org/W2145339207","https://openalex.org/W2415594836","https://openalex.org/W2504240155","https://openalex.org/W2522548478","https://openalex.org/W2747014259","https://openalex.org/W2775595038","https://openalex.org/W2790374560","https://openalex.org/W2894961023","https://openalex.org/W2912841061","https://openalex.org/W2920582597","https://openalex.org/W2953495059","https://openalex.org/W2963943581","https://openalex.org/W2964361030","https://openalex.org/W2973229164","https://openalex.org/W2978320887","https://openalex.org/W2996785115","https://openalex.org/W2998116579","https://openalex.org/W3004881034","https://openalex.org/W3006312629","https://openalex.org/W3019978224","https://openalex.org/W3021332410","https://openalex.org/W3023262556","https://openalex.org/W3023586494","https://openalex.org/W3030166701","https://openalex.org/W3047632670","https://openalex.org/W3048582611","https://openalex.org/W3089506933","https://openalex.org/W3096211637","https://openalex.org/W3099242408","https://openalex.org/W3113558818","https://openalex.org/W3127561923","https://openalex.org/W3128350768","https://openalex.org/W3194918255","https://openalex.org/W4214717370","https://openalex.org/W4231367092","https://openalex.org/W6640963894","https://openalex.org/W6692846177","https://openalex.org/W6748839928","https://openalex.org/W6768785780","https://openalex.org/W6773787650"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2089013912","https://openalex.org/W2076061571","https://openalex.org/W1987513656","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Advancements":[0],"in":[1,14,56,91],"computational":[2],"sciences":[3],"have":[4,20],"stimulated":[5],"the":[6,23,26,32,63,80,92,98,113,140,145],"use":[7],"of":[8,12,25,52,65,82,112],"an":[9,131],"abundant":[10],"amount":[11],"data":[13,33],"control":[15,28],"and":[16,44,58,116],"monitoring.":[17],"Recent":[18],"studies":[19],"reemphasized":[21],"that":[22,97,129,139],"performance":[24,64],"data-driven":[27],"significantly":[29],"depends":[30],"on":[31],"quality.":[34],"This":[35,47],"quality":[36],"is":[37,76,122],"affected":[38],"by":[39,104],"uncertainties":[40],"such":[41],"as":[42],"process":[43,128,146],"measurement":[45],"noises.":[46],"study":[48],"addresses":[49],"a":[50,66,73,106,110,125],"type":[51],"noise":[53,84],"commonly":[54],"seen":[55],"industry":[57],"shows":[59],"how":[60],"it":[61,86],"degrades":[62],"deep":[67],"reinforcement":[68],"learning":[69],"(RL)":[70],"agent.":[71],"Then,":[72],"novel":[74],"filter":[75,108],"proposed":[77,120,141],"to":[78,124],"reduce":[79],"effect":[81],"this":[83],"when":[85],"causes":[87],"skewed":[88],"probabilistic":[89],"distributions":[90],"reward":[93],"functions.":[94],"We":[95],"demonstrate":[96,138],"RL":[99,117],"policy":[100],"can":[101,143],"be":[102],"improved":[103],"using":[105],"constrained":[107],"with":[109],"combination":[111],"optimal":[114],"filtering":[115],"concepts.":[118],"The":[119,135],"algorithm":[121,142],"applied":[123],"pilot-scale":[126],"separation":[127,133],"resembles":[130],"industrial":[132],"vessel.":[134],"experimental":[136],"results":[137],"improve":[144],"operation":[147],"efficiency.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}