{"id":"https://openalex.org/W2126149578","doi":"https://doi.org/10.23919/acc.2004.1384022","title":"Reinforcement learning with supervision by a stable controller","display_name":"Reinforcement learning with supervision by a stable controller","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2126149578","doi":"https://doi.org/10.23919/acc.2004.1384022","mag":"2126149578"},"language":"en","primary_location":{"id":"doi:10.23919/acc.2004.1384022","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2004.1384022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 American Control Conference","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/A5048836790","display_name":"Michael T. Rosenstein","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M.T. Rosenstein","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts, Amherst, MA, USA","Dept. of Comput. Sci., Massachusetts Univ., Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Massachusetts Univ., Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089808068","display_name":"Andrew G. Barto","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A.G. Barto","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts, Amherst, MA, USA","Dept. of Comput. Sci., Massachusetts Univ., Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Massachusetts Univ., Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048836790"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":1.3864,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85601773,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"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":0.9983000159263611,"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":0.9983000159263611,"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":0.9954000115394592,"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/T10142","display_name":"Formal Methods in Verification","score":0.9778000116348267,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9032913446426392},{"id":"https://openalex.org/keywords/supervisor","display_name":"Supervisor","score":0.8115297555923462},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7505398988723755},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.7251708507537842},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5786721110343933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.510676920413971},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.4581148028373718},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.4368078410625458},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4192134737968445},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.39753592014312744},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25734418630599976},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16083693504333496}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9032913446426392},{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.8115297555923462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505398988723755},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.7251708507537842},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5786721110343933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.510676920413971},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4581148028373718},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.4368078410625458},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4192134737968445},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.39753592014312744},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25734418630599976},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16083693504333496},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.23919/acc.2004.1384022","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2004.1384022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 American Control Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarworks.umass.edu:cs_faculty_pubs-1335","is_oa":false,"landing_page_url":"https://scholarworks.umass.edu/cs_faculty_pubs/336","pdf_url":null,"source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Department Faculty Publication Series","raw_type":"text"},{"id":"pmh:oai:scholarworks.umass.edu:20.500.14394/10003","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.14394/10003","pdf_url":null,"source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"published","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5799999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1497976081","https://openalex.org/W1585603966","https://openalex.org/W1589064538","https://openalex.org/W1994923984","https://openalex.org/W2016482167","https://openalex.org/W2062691475","https://openalex.org/W2065356613","https://openalex.org/W2070301851","https://openalex.org/W2091565802","https://openalex.org/W2099767582","https://openalex.org/W2100677568","https://openalex.org/W2103285838","https://openalex.org/W2121863487","https://openalex.org/W2148112459","https://openalex.org/W2164479831","https://openalex.org/W2223493585"],"related_works":["https://openalex.org/W2126149578","https://openalex.org/W2159706408","https://openalex.org/W48176690","https://openalex.org/W2791491203","https://openalex.org/W2182011417","https://openalex.org/W2538183885","https://openalex.org/W2134672787","https://openalex.org/W2351150037","https://openalex.org/W1604647466","https://openalex.org/W1821494716"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,29,89],"(RL)":[2],"methods":[3],"provide":[4],"a":[5,55,72,99,104],"means":[6],"for":[7],"solving":[8],"optimal":[9],"control":[10,60,83],"problems":[11],"when":[12],"accurate":[13],"models":[14],"are":[15],"unavailable.":[16],"For":[17],"many":[18],"such":[19,49],"problems,":[20],"however,":[21],"RL":[22,66,79],"alone":[23],"is":[24],"impractical":[25],"and":[26,103],"the":[27,46,52,78,88,96],"associated":[28],"problem":[30],"must":[31],"be":[32],"structured":[33],"somehow":[34],"to":[35],"take":[36],"advantage":[37],"of":[38,48,54],"prior":[39],"knowledge.":[40],"In":[41],"this":[42],"paper":[43],"we":[44],"examine":[45],"use":[47],"knowledge":[50],"in":[51,62],"form":[53],"stable":[56],"controller":[57,69],"that":[58,74],"generates":[59],"inputs":[61],"parallel":[63],"with":[64,98],"an":[65],"system.":[67],"The":[68],"acts":[70],"as":[71],"supervisor":[73],"not":[75],"only":[76],"teaches":[77],"system":[80,90],"about":[81],"favorable":[82],"actions":[84],"but":[85],"also":[86],"protects":[87],"from":[91],"risky":[92],"behavior.":[93],"We":[94],"demonstrate":[95],"approach":[97],"simulated":[100],"robotic":[101],"arm":[102],"real":[105],"seven-DOF":[106],"manipulator.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
