{"id":"https://openalex.org/W4315471897","doi":"https://doi.org/10.1109/cdc51059.2022.9993026","title":"Performance-Driven Controller Tuning via Derivative-Free Reinforcement Learning","display_name":"Performance-Driven Controller Tuning via Derivative-Free Reinforcement Learning","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315471897","doi":"https://doi.org/10.1109/cdc51059.2022.9993026"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9993026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9993026","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"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 61st Conference on Decision and Control (CDC)","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/A5039910513","display_name":"Yuheng Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuheng Lei","raw_affiliation_strings":["Tsinghua University,School of Vehicle and Mobility,Beijing,China","School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Vehicle and Mobility,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611365","display_name":"Jianyu Chen","orcid":"https://orcid.org/0000-0002-1835-6115"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyu Chen","raw_affiliation_strings":["Tsinghua University,Institute for Interdisciplinary Information Sciences,Beijing,China","Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China","Shanghai Qi Zhi Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute for Interdisciplinary Information Sciences,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I4210122302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747108","display_name":"Shengbo Eben Li","orcid":"https://orcid.org/0000-0003-4923-3633"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Eben Li","raw_affiliation_strings":["Tsinghua University,School of Vehicle and Mobility,Beijing,China","School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Vehicle and Mobility,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036282981","display_name":"Sifa Zheng","orcid":"https://orcid.org/0000-0001-5160-1365"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sifa Zheng","raw_affiliation_strings":["Tsinghua University,School of Vehicle and Mobility,Beijing,China","School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Vehicle and Mobility,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039910513"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.2079,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.45168067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9972000122070312,"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":0.9972000122070312,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9952999949455261,"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"}},{"id":"https://openalex.org/T11749","display_name":"Iterative Learning Control Systems","score":0.995199978351593,"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":0.8197082281112671},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.633827805519104},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5213931202888489},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5210161209106445},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4576711654663086},{"id":"https://openalex.org/keywords/derivative","display_name":"Derivative (finance)","score":0.45206084847450256},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.34697940945625305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27818727493286133},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1594151258468628},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.1145966649055481},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.07964721322059631}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8197082281112671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.633827805519104},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5213931202888489},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5210161209106445},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4576711654663086},{"id":"https://openalex.org/C111771559","wikidata":"https://www.wikidata.org/wiki/Q66295","display_name":"Derivative (finance)","level":2,"score":0.45206084847450256},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.34697940945625305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27818727493286133},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1594151258468628},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.1145966649055481},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.07964721322059631},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc51059.2022.9993026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9993026","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"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 61st Conference on Decision and Control (CDC)","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":43,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W2013610941","https://openalex.org/W2018691083","https://openalex.org/W2082261506","https://openalex.org/W2112862244","https://openalex.org/W2170973929","https://openalex.org/W2192203593","https://openalex.org/W2346505884","https://openalex.org/W2596367596","https://openalex.org/W2599719672","https://openalex.org/W2889731659","https://openalex.org/W2890326782","https://openalex.org/W2904119718","https://openalex.org/W2930426397","https://openalex.org/W2952215314","https://openalex.org/W2954989419","https://openalex.org/W2982388247","https://openalex.org/W3004384589","https://openalex.org/W3011478909","https://openalex.org/W3011550305","https://openalex.org/W3099670724","https://openalex.org/W3103151316","https://openalex.org/W3105904426","https://openalex.org/W3152759608","https://openalex.org/W3180708423","https://openalex.org/W3186106330","https://openalex.org/W3186347355","https://openalex.org/W4214717370","https://openalex.org/W4230674069","https://openalex.org/W4285071855","https://openalex.org/W4287991730","https://openalex.org/W6627932998","https://openalex.org/W6684205842","https://openalex.org/W6735641298","https://openalex.org/W6754302822","https://openalex.org/W6754787993","https://openalex.org/W6767611374","https://openalex.org/W6771685107","https://openalex.org/W6773636707","https://openalex.org/W6779366341","https://openalex.org/W6786442853","https://openalex.org/W6794585241","https://openalex.org/W6797024940"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W2000675896"],"abstract_inverted_index":{"Choosing":[0],"an":[1],"appropriate":[2],"parameter":[3,81],"set":[4],"for":[5,11,29,147],"the":[6,12,60,64,92,105,136],"designed":[7],"controller":[8,56,65,125,148],"is":[9],"critical":[10],"final":[13],"performance":[14],"but":[15],"usually":[16],"requires":[17],"a":[18,26,69],"tedious":[19],"and":[20,86,101,126,142],"careful":[21],"tuning":[22,31,66],"process,":[23],"which":[24,76],"implies":[25],"strong":[27,145],"need":[28],"automatic":[30],"methods.":[32],"However,":[33],"among":[34],"existing":[35],"methods,":[36],"derivative-free":[37,71,88],"ones":[38,48],"suffer":[39],"from":[40,116],"poor":[41],"scalability":[42],"or":[43],"low":[44],"efficiency,":[45],"while":[46],"gradient-based":[47],"are":[49],"often":[50],"unavailable":[51],"due":[52],"to":[53,97],"possibly":[54],"non-differentiable":[55],"structure.":[57],"To":[58,103],"resolve":[59],"issues,":[61],"we":[62,108],"tackle":[63],"problem":[67],"using":[68],"novel":[70],"reinforcement":[72],"learning":[73],"(RL)":[74],"framework,":[75],"performs":[77],"timestep-wise":[78],"perturbation":[79],"in":[80],"space":[82],"during":[83],"experience":[84],"collection":[85],"integrates":[87],"policy":[89],"updates":[90],"into":[91],"advanced":[93],"actor-critic":[94],"RL":[95],"architecture":[96],"achieve":[98],"high":[99],"versatility":[100],"efficiency.":[102],"demonstrate":[104],"framework\u2019s":[106],"efficacy,":[107],"conduct":[109],"numerical":[110],"experiments":[111],"on":[112],"two":[113],"concrete":[114],"examples":[115],"autonomous":[117],"driving,":[118],"namely,":[119],"adaptive":[120],"cruise":[121],"control":[122],"with":[123,129],"PID":[124],"trajectory":[127],"tracking":[128],"MPC":[130],"controller.":[131],"Experimental":[132],"results":[133],"show":[134],"that":[135],"proposed":[137],"method":[138],"outperforms":[139],"popular":[140],"baselines":[141],"highlight":[143],"its":[144],"potential":[146],"tuning.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}