{"id":"https://openalex.org/W2569414656","doi":"https://doi.org/10.1109/cdc.2016.7799164","title":"Actor-critic reinforcement learning for tracking control in robotics","display_name":"Actor-critic reinforcement learning for tracking control in robotics","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2569414656","doi":"https://doi.org/10.1109/cdc.2016.7799164","mag":"2569414656"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2016.7799164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7799164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","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/A5031856556","display_name":"Yudha Pane","orcid":"https://orcid.org/0000-0003-0246-5605"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Yudha P. Pane","raw_affiliation_strings":["Department of Mechanical Engineering, KU Leuven, Heverlee, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, KU Leuven, Heverlee, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061604841","display_name":"Subramanya Nageshrao","orcid":null},"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":"Subramanya P. Nageshrao","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","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":["Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5819","last_page":"5826"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11749","display_name":"Iterative Learning Control Systems","score":0.9994999766349792,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9994999766349792,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9914000034332275,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9905999898910522,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8549413084983826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7025129199028015},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6743732690811157},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.589664876461029},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5225155353546143},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.45387357473373413},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4435107409954071},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4098653793334961},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3872070908546448},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2852949798107147},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.25178423523902893},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11889463663101196}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8549413084983826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7025129199028015},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6743732690811157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.589664876461029},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5225155353546143},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.45387357473373413},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4435107409954071},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4098653793334961},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3872070908546448},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2852949798107147},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.25178423523902893},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11889463663101196},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2016.7799164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7799164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1484499605","https://openalex.org/W1564897360","https://openalex.org/W1594783240","https://openalex.org/W1596805757","https://openalex.org/W1966086707","https://openalex.org/W1975517766","https://openalex.org/W1977655452","https://openalex.org/W2041242313","https://openalex.org/W2046376809","https://openalex.org/W2097520388","https://openalex.org/W2104144149","https://openalex.org/W2121863487","https://openalex.org/W2611980291","https://openalex.org/W4214717370","https://openalex.org/W6628904170","https://openalex.org/W6635508374"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W3119422923"],"abstract_inverted_index":{"In":[0],"this":[1],"article":[2],"we":[3],"provide":[4],"experimental":[5,84],"results":[6],"and":[7,37],"evaluation":[8],"of":[9,18,25,79,98],"a":[10,19,40,65],"compensation":[11,92],"method":[12,93],"which":[13],"improves":[14,95],"the":[15,34,44,49,53,72,89,96,99],"tracking":[16,54],"performance":[17,55,97],"nominal":[20,45,100],"feedback":[21,101],"controller":[22],"by":[23],"means":[24],"reinforcement":[26],"learning":[27],"(RL).":[28],"The":[29,59],"compensator":[30],"is":[31],"based":[32],"on":[33,64],"actor-critic":[35],"scheme":[36],"it":[38],"adds":[39],"correction":[41],"signal":[42],"to":[43,51,74],"control":[46],"input":[47],"with":[48,71],"goal":[50],"improve":[52],"using":[56],"on-line":[57],"learning.":[58],"algorithm":[60],"has":[61,86],"been":[62],"evaluated":[63],"6":[66],"DOF":[67],"industrial":[68],"robot":[69],"manipulator":[70],"objective":[73],"accurately":[75],"track":[76],"different":[77],"types":[78],"reference":[80],"trajectories.":[81],"An":[82],"extensive":[83],"study":[85],"shown":[87],"that":[88],"proposed":[90],"RL-based":[91],"significantly":[94],"controller.":[102]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}