{"id":"https://openalex.org/W2790972108","doi":"https://doi.org/10.1109/lra.2018.2800106","title":"Model-Plant Mismatch Compensation Using Reinforcement Learning","display_name":"Model-Plant Mismatch Compensation Using Reinforcement Learning","publication_year":2018,"publication_date":"2018-01-31","ids":{"openalex":"https://openalex.org/W2790972108","doi":"https://doi.org/10.1109/lra.2018.2800106","mag":"2790972108"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2018.2800106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2018.2800106","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://resolver.tudelft.nl/uuid:4ea9a42f-9d8a-4080-936e-d603feaac5ab","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022898577","display_name":"Ivan Koryakovskiy","orcid":"https://orcid.org/0000-0002-9193-1016"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ivan Koryakovskiy","raw_affiliation_strings":["Robotics Institute, TU Delft, Delft, CD, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-9193-1016","affiliations":[{"raw_affiliation_string":"Robotics Institute, TU Delft, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085087999","display_name":"Manuel Kudruss","orcid":"https://orcid.org/0000-0003-4598-7833"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Manuel Kudruss","raw_affiliation_strings":["Interdisciplinary Center for Scientific Computing, Heidelberg University, Heidelberg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4598-7833","affiliations":[{"raw_affiliation_string":"Interdisciplinary Center for Scientific Computing, Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007760731","display_name":"Heike Vallery","orcid":"https://orcid.org/0000-0002-0305-398X"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Heike Vallery","raw_affiliation_strings":["Robotics Institute, TU Delft, Delft, CD, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-0305-398X","affiliations":[{"raw_affiliation_string":"Robotics Institute, TU Delft, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084264842","display_name":"Robert Babu\u0161ka","orcid":"https://orcid.org/0000-0001-9578-8598"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Robert Babuska","raw_affiliation_strings":["Robotics Institute, TU Delft, Delft, CD, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-9578-8598","affiliations":[{"raw_affiliation_string":"Robotics Institute, TU Delft, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009958441","display_name":"Wouter Caarls","orcid":"https://orcid.org/0000-0001-9069-2378"},"institutions":[{"id":"https://openalex.org/I2699952","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Rio de Janeiro","ror":"https://ror.org/01dg47b60","country_code":"BR","type":"education","lineage":["https://openalex.org/I2699952"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Wouter Caarls","raw_affiliation_strings":["Department of Electrical Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-9069-2378","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I2699952"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.81,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.90842351,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"3","issue":"3","first_page":"2471","last_page":"2477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","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/T10791","display_name":"Advanced Control Systems Optimization","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/T10876","display_name":"Fault Detection and Control Systems","score":0.9943000078201294,"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/T11236","display_name":"Control Systems and Identification","score":0.9879000186920166,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/setpoint","display_name":"Setpoint","score":0.9478650689125061},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6919030547142029},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6853669285774231},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6745805740356445},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.596526563167572},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5883801579475403},{"id":"https://openalex.org/keywords/iterative-learning-control","display_name":"Iterative learning control","score":0.5252009034156799},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.5217581391334534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4748166799545288},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4741586744785309},{"id":"https://openalex.org/keywords/internal-model","display_name":"Internal model","score":0.45874035358428955},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4330252408981323},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.43147140741348267},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18257707357406616},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.09711924195289612}],"concepts":[{"id":"https://openalex.org/C12302492","wikidata":"https://www.wikidata.org/wiki/Q1752097","display_name":"Setpoint","level":2,"score":0.9478650689125061},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6919030547142029},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6853669285774231},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6745805740356445},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.596526563167572},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5883801579475403},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.5252009034156799},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.5217581391334534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4748166799545288},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4741586744785309},{"id":"https://openalex.org/C28427503","wikidata":"https://www.wikidata.org/wiki/Q13580300","display_name":"Internal model","level":3,"score":0.45874035358428955},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4330252408981323},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.43147140741348267},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18257707357406616},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.09711924195289612},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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":2,"locations":[{"id":"doi:10.1109/lra.2018.2800106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2018.2800106","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:tudelft.nl:uuid:4ea9a42f-9d8a-4080-936e-d603feaac5ab","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:4ea9a42f-9d8a-4080-936e-d603feaac5ab","pdf_url":"http://resolver.tudelft.nl/uuid:4ea9a42f-9d8a-4080-936e-d603feaac5ab","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:4ea9a42f-9d8a-4080-936e-d603feaac5ab","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:4ea9a42f-9d8a-4080-936e-d603feaac5ab","pdf_url":"http://resolver.tudelft.nl/uuid:4ea9a42f-9d8a-4080-936e-d603feaac5ab","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2790972108.pdf"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W15411808","https://openalex.org/W1191599655","https://openalex.org/W1499669280","https://openalex.org/W1517081929","https://openalex.org/W1571179961","https://openalex.org/W1771410628","https://openalex.org/W1923344279","https://openalex.org/W1975517766","https://openalex.org/W2072752020","https://openalex.org/W2091638547","https://openalex.org/W2104733512","https://openalex.org/W2115008305","https://openalex.org/W2121863487","https://openalex.org/W2130801532","https://openalex.org/W2134491302","https://openalex.org/W2165150801","https://openalex.org/W2167417157","https://openalex.org/W2169744859","https://openalex.org/W2290354866","https://openalex.org/W2477791619","https://openalex.org/W2529477964","https://openalex.org/W2530944449","https://openalex.org/W2592001929","https://openalex.org/W2700407638","https://openalex.org/W2736601468","https://openalex.org/W2771827793","https://openalex.org/W2950471160","https://openalex.org/W2952720101","https://openalex.org/W2963525569","https://openalex.org/W3011594214","https://openalex.org/W4214717370","https://openalex.org/W4297780563","https://openalex.org/W4297824641","https://openalex.org/W4302570325","https://openalex.org/W6600644339","https://openalex.org/W6627932998","https://openalex.org/W6629881138","https://openalex.org/W6630711612","https://openalex.org/W6634153895","https://openalex.org/W6638018090","https://openalex.org/W6675999342","https://openalex.org/W6677179944","https://openalex.org/W6679257226","https://openalex.org/W6682367392","https://openalex.org/W6684205842","https://openalex.org/W6684602696","https://openalex.org/W6696324988","https://openalex.org/W6728252718","https://openalex.org/W6728367041","https://openalex.org/W6737214707","https://openalex.org/W6740033195","https://openalex.org/W6741002519","https://openalex.org/W6774575170"],"related_works":["https://openalex.org/W2152551869","https://openalex.org/W3125270601","https://openalex.org/W4235132187","https://openalex.org/W2245608695","https://openalex.org/W2064796971","https://openalex.org/W2360223712","https://openalex.org/W2112578702","https://openalex.org/W1973102996","https://openalex.org/W2080929820","https://openalex.org/W3208176960"],"abstract_inverted_index":{"Learning-based":[0],"approaches":[1,80,135],"are":[2],"suitable":[3],"for":[4,74],"the":[5,34,65,75,86,99,107,125,134,141,153,157],"control":[6,25,95],"of":[7,67,81,120],"systems":[8],"with":[9,19,48,85],"unknown":[10,69],"dynamics.":[11],"However,":[12],"learning":[13,47,84,163],"from":[14,117],"scratch":[15],"involves":[16],"many":[17],"trials":[18],"exploratory":[20,35],"actions":[21,36],"until":[22],"a":[23,49,57,93,114,118,121,137,145],"good":[24],"policy":[26],"is":[27,62,104],"discovered.":[28],"Real":[29],"robots":[30],"usually":[31],"cannot":[32],"withstand":[33],"and":[37,128,143,160],"suffer":[38],"damage.":[39],"This":[40],"problem":[41],"can":[42],"be":[43],"circumvented":[44],"by":[45,64,106,124],"combining":[46,82],"model-based":[50],"control.":[51],"In":[52],"this":[53],"letter,":[54],"we":[55,77],"employ":[56],"nominal":[58,87,108],"model-predictive":[59],"controller":[60],"that":[61,97],"impeded":[63],"presence":[66],"an":[68,129],"model-plant":[70],"mismatch.":[71],"To":[72],"compensate":[73],"mismatch,":[76],"propose":[78],"two":[79],"reinforcement":[83],"controller.":[88,109],"The":[89,110],"first":[90],"approach":[91,112,155],"learns":[92,113],"compensatory":[94,115],"action":[96],"minimizes":[98],"same":[100],"performance":[101],"measure":[102],"as":[103],"minimized":[105],"second":[111],"signal":[116],"difference":[119],"transition":[122],"predicted":[123],"internal":[126],"model":[127],"actual":[130],"transition.":[131],"We":[132,151],"compare":[133],"on":[136,156],"robot":[138,159],"attached":[139],"to":[140],"ground":[142],"performing":[144],"setpoint":[146],"reaching":[147],"task":[148],"in":[149],"simulations.":[150],"implement":[152],"better":[154],"real":[158],"demonstrate":[161],"successful":[162],"results.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}