{"id":"https://openalex.org/W4295854864","doi":"https://doi.org/10.23919/acc53348.2022.9867627","title":"Hysteresis-Based RL: Robustifying Reinforcement Learning-based Control Policies via Hybrid Control","display_name":"Hysteresis-Based RL: Robustifying Reinforcement Learning-based Control Policies via Hybrid Control","publication_year":2022,"publication_date":"2022-06-08","ids":{"openalex":"https://openalex.org/W4295854864","doi":"https://doi.org/10.23919/acc53348.2022.9867627"},"language":"en","primary_location":{"id":"doi:10.23919/acc53348.2022.9867627","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867627","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.tue.nl/en/publications/b385c917-8ca6-4903-a4d8-e74793f896c5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051727931","display_name":"Jan de Priester","orcid":"https://orcid.org/0000-0002-8904-5904"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan De Priester","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028224738","display_name":"Ricardo G. Sanfelice","orcid":"https://orcid.org/0000-0002-6671-5362"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ricardo G. Sanfelice","raw_affiliation_strings":["University of California,Department of Electrical and Computer Engineering,Santa Cruz,CA,USA,95064"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical and Computer Engineering,Santa Cruz,CA,USA,95064","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004028181","display_name":"Nathan van de Wouw","orcid":"https://orcid.org/0000-0002-6745-9137"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Nathan Van De Wouw","raw_affiliation_strings":["Eindhoven University of Technology,Department of Mechanical Engineering,Eindhoven,AZ,Netherlands,5612"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Department of Mechanical Engineering,Eindhoven,AZ,Netherlands,5612","institution_ids":["https://openalex.org/I83019370"]}]}],"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":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2663","last_page":"2668"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9933000206947327,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.9162441492080688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7615809440612793},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6525883078575134},{"id":"https://openalex.org/keywords/hysteresis","display_name":"Hysteresis","score":0.45959505438804626},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.45825234055519104},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4262402057647705},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.39660120010375977},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3499797582626343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3017348647117615},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1340348720550537}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9162441492080688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7615809440612793},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6525883078575134},{"id":"https://openalex.org/C123299182","wikidata":"https://www.wikidata.org/wiki/Q190837","display_name":"Hysteresis","level":2,"score":0.45959505438804626},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.45825234055519104},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4262402057647705},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.39660120010375977},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3499797582626343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3017348647117615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1340348720550537},{"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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/acc53348.2022.9867627","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867627","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire/b385c917-8ca6-4903-a4d8-e74793f896c5","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/b385c917-8ca6-4903-a4d8-e74793f896c5","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"De Priester, J, Sanfelice, R G & van de Wouw, N 2022, Hysteresis-Based RL : Robustifying Reinforcement Learning-based Control Policies via Hybrid Control. in 2022 American Control Conference, ACC 2022., 9867627, Institute of Electrical and Electronics Engineers, pp. 2663-2668, 2022 American Control Conference, ACC 2022, Atlanta, Georgia, United States, 8/06/22. https://doi.org/10.23919/ACC53348.2022.9867627","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.tue.nl:openaire/b385c917-8ca6-4903-a4d8-e74793f896c5","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/b385c917-8ca6-4903-a4d8-e74793f896c5","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"De Priester, J, Sanfelice, R G & van de Wouw, N 2022, Hysteresis-Based RL : Robustifying Reinforcement Learning-based Control Policies via Hybrid Control. in 2022 American Control Conference, ACC 2022., 9867627, Institute of Electrical and Electronics Engineers, pp. 2663-2668, 2022 American Control Conference, ACC 2022, Atlanta, Georgia, United States, 8/06/22. https://doi.org/10.23919/ACC53348.2022.9867627","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5600000023841858}],"awards":[{"id":"https://openalex.org/G1424887769","display_name":null,"funder_award_id":"ECS-1710621","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1940323886","display_name":null,"funder_award_id":"ECS-1710621","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G2388055263","display_name":null,"funder_award_id":"CNS-2039054","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2774078400","display_name":"Collaborative Research: CPS: Medium: Constraint Aware Planning and Control for Cyber-Physical Systems","funder_award_id":"2039054","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3762554873","display_name":null,"funder_award_id":"CNS-1544396","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3936620348","display_name":null,"funder_award_id":"W911NF-20-1-0253","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G4476256319","display_name":"CPS: Synergy: Collaborative Research: Computationally Aware Cyber-Physical Systems","funder_award_id":"1544396","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7133458872","display_name":"Hybrid Predictive Control for Distributed Multi-agent Systems","funder_award_id":"1710621","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2099308299","https://openalex.org/W2104103836","https://openalex.org/W2145339207","https://openalex.org/W2168457127","https://openalex.org/W2334782222","https://openalex.org/W2736601468","https://openalex.org/W2781726626","https://openalex.org/W2914994663","https://openalex.org/W2950300520","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2982312374","https://openalex.org/W3124446631","https://openalex.org/W3216772467","https://openalex.org/W4210450858","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6759312646","https://openalex.org/W6764339904","https://openalex.org/W6789484704","https://openalex.org/W6804601995"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W2086351220"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"is":[3],"a":[4,46],"promising":[5],"approach":[6],"for":[7,11,76],"deriving":[8],"control":[9,19],"policies":[10,23],"complex":[12],"systems.":[13],"As":[14],"we":[15,44,51],"show":[16],"in":[17,73],"two":[18,65,74],"problems,":[20],"the":[21,26],"derived":[22],"from":[24],"using":[25],"Proximal":[27],"Policy":[28],"Optimization":[29],"(PPO)":[30],"and":[31,64,79],"Deep":[32],"Q-Network":[33],"(DQN)":[34],"algorithms":[35],"may":[36],"lack":[37],"robustness":[38],"guarantees.":[39],"Motivated":[40],"by":[41],"these":[42],"issues,":[43],"propose":[45],"new":[47],"hybrid":[48],"algorithm,":[49],"which":[50,77],"call":[52],"Hysteresis-Based":[53],"RL":[54,59],"(HyRL),":[55],"augmenting":[56],"an":[57],"existing":[58],"algorithm":[60],"with":[61],"hysteresis":[62],"switching":[63],"stages":[66],"of":[67],"learning.":[68],"We":[69],"illustrate":[70],"its":[71],"properties":[72],"examples":[75],"PPO":[78],"DQN":[80],"fail.":[81]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}