{"id":"https://openalex.org/W4397026472","doi":"https://doi.org/10.1109/tcst.2024.3393210","title":"Guaranteeing Control Requirements via Reward Shaping in Reinforcement Learning","display_name":"Guaranteeing Control Requirements via Reward Shaping in Reinforcement Learning","publication_year":2024,"publication_date":"2024-05-17","ids":{"openalex":"https://openalex.org/W4397026472","doi":"https://doi.org/10.1109/tcst.2024.3393210"},"language":"en","primary_location":{"id":"doi:10.1109/tcst.2024.3393210","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcst.2024.3393210","pdf_url":"https://ieeexplore.ieee.org/ielx7/87/4389040/10534075.pdf","source":{"id":"https://openalex.org/S133363738","display_name":"IEEE Transactions on Control Systems Technology","issn_l":"1063-6536","issn":["1063-6536","1558-0865","2374-0159"],"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 Transactions on Control Systems Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/87/4389040/10534075.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045546410","display_name":"Francesco De Lellis","orcid":null},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco De Lellis","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2997-543X","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071902133","display_name":"Marco Coraggio","orcid":"https://orcid.org/0000-0003-2784-1486"},"institutions":[{"id":"https://openalex.org/I2800920820","display_name":"Istituto Universitario di Studi Superiori di Pavia","ror":"https://ror.org/0290wsh42","country_code":"IT","type":"education","lineage":["https://openalex.org/I2800920820"]},{"id":"https://openalex.org/I4210149489","display_name":"Scuola Superiore Meridionale","ror":"https://ror.org/04swxte59","country_code":"IT","type":"education","lineage":["https://openalex.org/I4210149489"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Coraggio","raw_affiliation_strings":["School for Advanced Studies, Scuola Superiore Meridionale, Naples, Italy"],"raw_orcid":"https://orcid.org/0000-0003-2784-1486","affiliations":[{"raw_affiliation_string":"School for Advanced Studies, Scuola Superiore Meridionale, Naples, Italy","institution_ids":["https://openalex.org/I4210149489","https://openalex.org/I2800920820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000619566","display_name":"Giovanni Russo","orcid":"https://orcid.org/0000-0001-5001-3027"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Russo","raw_affiliation_strings":["Department of Computer and Electrical Engineering and Applied Mathematics, DIEM, University of Salerno, Salerno, Italy"],"raw_orcid":"https://orcid.org/0000-0001-5001-3027","affiliations":[{"raw_affiliation_string":"Department of Computer and Electrical Engineering and Applied Mathematics, DIEM, University of Salerno, Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078886343","display_name":"Mirco Musolesi","orcid":"https://orcid.org/0000-0001-9712-4090"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mirco Musolesi","raw_affiliation_strings":["Department of Computer Science, University College London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0001-9712-4090","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University College London, London, U.K","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034953482","display_name":"Mario di Bernardo","orcid":"https://orcid.org/0000-0002-2171-4745"},"institutions":[{"id":"https://openalex.org/I2800920820","display_name":"Istituto Universitario di Studi Superiori di Pavia","ror":"https://ror.org/0290wsh42","country_code":"IT","type":"education","lineage":["https://openalex.org/I2800920820"]},{"id":"https://openalex.org/I4210149489","display_name":"Scuola Superiore Meridionale","ror":"https://ror.org/04swxte59","country_code":"IT","type":"education","lineage":["https://openalex.org/I4210149489"]},{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mario di Bernardo","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy","School for Advanced Studies, Scuola Superiore Meridionale, Naples, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2171-4745","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy","institution_ids":["https://openalex.org/I71267560"]},{"raw_affiliation_string":"School for Advanced Studies, Scuola Superiore Meridionale, Naples, Italy","institution_ids":["https://openalex.org/I4210149489","https://openalex.org/I2800920820"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3601,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93004362,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"32","issue":"6","first_page":"2102","last_page":"2113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.48080000281333923,"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":0.48080000281333923,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7652246952056885},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6467454433441162},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5555640459060669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.465945839881897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3698025941848755},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3082215189933777},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.14499765634536743}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7652246952056885},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6467454433441162},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5555640459060669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.465945839881897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3698025941848755},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3082215189933777},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.14499765634536743}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tcst.2024.3393210","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcst.2024.3393210","pdf_url":"https://ieeexplore.ieee.org/ielx7/87/4389040/10534075.pdf","source":{"id":"https://openalex.org/S133363738","display_name":"IEEE Transactions on Control Systems Technology","issn_l":"1063-6536","issn":["1063-6536","1558-0865","2374-0159"],"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 Transactions on Control Systems Technology","raw_type":"journal-article"},{"id":"pmh:oai:cris.unibo.it:11585/1034268","is_oa":false,"landing_page_url":"https://hdl.handle.net/11585/1034268","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:zenodo.org:13206260","is_oa":true,"landing_page_url":"https://doi.org/10.1109/TCST.2024.3393210","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Control Systems Technology, (2024-05-17)","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1109/tcst.2024.3393210","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcst.2024.3393210","pdf_url":"https://ieeexplore.ieee.org/ielx7/87/4389040/10534075.pdf","source":{"id":"https://openalex.org/S133363738","display_name":"IEEE Transactions on Control Systems Technology","issn_l":"1063-6536","issn":["1063-6536","1558-0865","2374-0159"],"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 Transactions on Control Systems Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4397026472.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1499408472","https://openalex.org/W1522301498","https://openalex.org/W1970916399","https://openalex.org/W2114682338","https://openalex.org/W2145339207","https://openalex.org/W2164479831","https://openalex.org/W2165726932","https://openalex.org/W2746553466","https://openalex.org/W2963575966","https://openalex.org/W3005355833","https://openalex.org/W3010920281","https://openalex.org/W3042731680","https://openalex.org/W3048735518","https://openalex.org/W3127561923","https://openalex.org/W3133533407","https://openalex.org/W3163638858","https://openalex.org/W4200629417","https://openalex.org/W4213377513","https://openalex.org/W4238538572","https://openalex.org/W4297792208","https://openalex.org/W4310746929","https://openalex.org/W4312713104","https://openalex.org/W4314946886","https://openalex.org/W4391021838","https://openalex.org/W6631190155","https://openalex.org/W6638088447","https://openalex.org/W6684037837","https://openalex.org/W6738483526","https://openalex.org/W6748523217","https://openalex.org/W6751535212","https://openalex.org/W6780559895","https://openalex.org/W6810137820","https://openalex.org/W6846310611"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"In":[0],"addressing":[1],"control":[2,66,130],"problems":[3],"such":[4,29],"as":[5,30],"regulation":[6],"and":[7,26,35,49,68,99,106],"tracking":[8],"through":[9,83],"reinforcement":[10],"learning":[11],"(RL),":[12],"it":[13],"is":[14],"often":[15],"required":[16],"to":[17,71,127],"guarantee":[18],"that":[19,62],"the":[20,57,95,100,114,128],"acquired":[21],"policy":[22,59,76,125],"meets":[23],"essential":[24],"performance":[25],"stability":[27],"criteria":[28],"a":[31,45,50],"desired":[32],"settling":[33],"time":[34],"steady-state":[36],"error":[37],"before":[38],"deployment.":[39],"Motivated":[40],"by":[41],"this,":[42],"we":[43],"present":[44],"set":[46],"of":[47,116],"results":[48],"systematic":[51],"reward-shaping":[52],"procedure":[53],"that:":[54],"1)":[55],"ensures":[56],"optimal":[58],"generates":[60],"trajectories":[61],"align":[63],"with":[64],"specified":[65],"requirements":[67],"2)":[69],"allows":[70],"assess":[72],"whether":[73],"any":[74],"given":[75],"satisfies":[77],"them.":[78],"We":[79],"validate":[80],"our":[81,110,117],"approach":[82],"comprehensive":[84],"numerical":[85],"experiments":[86,111],"conducted":[87],"in":[88,123],"two":[89],"representative":[90],"environments":[91],"from":[92],"OpenAI":[93],"Gym:":[94],"Pendulum":[96],"swing-up":[97],"problem":[98],"Lunar":[101],"Lander.":[102],"Utilizing":[103],"both":[104],"tabular":[105],"deep":[107],"RL":[108],"methods,":[109],"consistently":[112],"affirm":[113],"efficacy":[115],"proposed":[118],"framework,":[119],"highlighting":[120],"its":[121],"effectiveness":[122],"ensuring":[124],"adherence":[126],"prescribed":[129],"requirements.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}