{"id":"https://openalex.org/W4200633913","doi":"https://doi.org/10.1109/lra.2022.3169309","title":"Improving the Robustness of Reinforcement Learning Policies With ${\\mathcal {L}_{1}}$ Adaptive Control","display_name":"Improving the Robustness of Reinforcement Learning Policies With ${\\mathcal {L}_{1}}$ Adaptive Control","publication_year":2022,"publication_date":"2022-04-21","ids":{"openalex":"https://openalex.org/W4200633913","doi":"https://doi.org/10.1109/lra.2022.3169309"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3169309","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2022.3169309","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/9750005/09761728.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"preprint","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/7083369/9750005/09761728.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yikun Cheng","orcid":"https://orcid.org/0000-0002-7911-1496"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yikun Cheng","raw_affiliation_strings":["Mechanical Science and Engineering Department, University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"Mechanical Science and Engineering Department, University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pan Zhao","orcid":"https://orcid.org/0000-0001-9349-1125"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pan Zhao","raw_affiliation_strings":["Mechanical Science and Engineering Department, University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"Mechanical Science and Engineering Department, University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fanxin Wang","orcid":"https://orcid.org/0000-0002-3935-7205"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fanxin Wang","raw_affiliation_strings":["Mechanical Science and Engineering Department, University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"Mechanical Science and Engineering Department, University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065829362","display_name":"Daniel J. Block","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel J. Block","raw_affiliation_strings":["Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029998748","display_name":"Naira Hovakimyan","orcid":"https://orcid.org/0000-0003-3850-1073"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naira Hovakimyan","raw_affiliation_strings":["Mechanical Science and Engineering Department, University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"Mechanical Science and Engineering Department, University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00657068,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"3","first_page":"6574","last_page":"6581"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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"}},{"id":"https://openalex.org/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9391000270843506,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9283999800682068,"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":0.8899040818214417},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8703960180282593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6526853442192078},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5623417496681213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31391870975494385},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.288385272026062}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8899040818214417},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8703960180282593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6526853442192078},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5623417496681213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31391870975494385},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.288385272026062},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2022.3169309","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2022.3169309","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/9750005/09761728.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"doi:10.48550/arxiv.2112.01953","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2112.01953","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1109/lra.2022.3169309","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2022.3169309","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/9750005/09761728.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3499615532","display_name":null,"funder_award_id":"1830639","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6456014046","display_name":null,"funder_award_id":"2133656","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7944664620","display_name":"AI Institute: Planning: TRustworthy Autonomous Systems Engineering (TRASE)","funder_award_id":"2020289","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4200633913.pdf","grobid_xml":"https://content.openalex.org/works/W4200633913.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2087617385","https://openalex.org/W2230652337","https://openalex.org/W2605102758","https://openalex.org/W2767050701","https://openalex.org/W2790355818","https://openalex.org/W2911087563","https://openalex.org/W2982095652","https://openalex.org/W3010680978","https://openalex.org/W3041470844","https://openalex.org/W3118935517","https://openalex.org/W3119915811","https://openalex.org/W3197315420","https://openalex.org/W4231017914","https://openalex.org/W6679524480","https://openalex.org/W6680657880","https://openalex.org/W6681631837","https://openalex.org/W6735677848","https://openalex.org/W6736057607","https://openalex.org/W6747473740","https://openalex.org/W6752941136","https://openalex.org/W6756463683","https://openalex.org/W6757223306","https://openalex.org/W6766505436","https://openalex.org/W6771484861","https://openalex.org/W6774681163","https://openalex.org/W6776735271","https://openalex.org/W6779618582","https://openalex.org/W6786292401","https://openalex.org/W6804686668","https://openalex.org/W6805268425","https://openalex.org/W6840472118"],"related_works":["https://openalex.org/W3168137637","https://openalex.org/W4200633913","https://openalex.org/W2121017125","https://openalex.org/W3118752938","https://openalex.org/W1978316810","https://openalex.org/W1968750113","https://openalex.org/W3027695597","https://openalex.org/W3111184071","https://openalex.org/W2350129475","https://openalex.org/W2494072558"],"abstract_inverted_index":{"A":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"control":[4],"policy":[5,45,95],"could":[6],"fail":[7],"in":[8,100,104,129],"a":[9,42,101,111],"new/perturbed":[10],"environment":[11],"that":[12],"is":[13,97],"different":[14],"from":[15],"the":[16,21,66,85,90,105,123,126],"training":[17],"environment,":[18],"due":[19],"to":[20,40],"presence":[22],"of":[23,68,82,92,110,114,125],"dynamic":[24,83,115],"variations.":[25,116],"For":[26],"controlling":[27],"systems":[28],"with":[29,49],"continuous":[30],"state":[31],"and":[32,79,118,137],"action":[33],"spaces,":[34],"we":[35],"propose":[36],"an":[37,50,69,93],"add-on":[38],"approach":[39,87,128],"robustifying":[41,130],"pre-trained":[43],"RL":[44,94,131],"by":[46],"augmenting":[47],"it":[48],"<inline-formula":[51,59,70],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[52,60,71],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[53,61,72],"notation=\"LaTeX\">${\\mathcal":[54,62,73],"{L}_{1}}$</tex-math></inline-formula>":[55,63,74],"adaptive":[56],"controller":[57],"(":[58],"AC).":[64],"Leveraging":[65],"capability":[67],"AC":[75],"for":[76],"fast":[77],"estimation":[78],"active":[80],"compensation":[81],"variations,":[84],"proposed":[86,127],"can":[88],"improve":[89],"robustness":[91],"which":[96],"trained":[98,133],"either":[99],"simulator":[102],"or":[103],"real":[106],"world":[107],"without":[108],"consideration":[109],"broad":[112],"class":[113],"Numerical":[117],"real-world":[119],"experiments":[120],"empirically":[121],"demonstrate":[122],"efficacy":[124],"policies":[132],"using":[134],"both":[135],"model-free":[136],"model-based":[138],"methods.":[139]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2021-12-31T00:00:00"}