{"id":"https://openalex.org/W7224450126","doi":"https://doi.org/10.21203/rs.3.rs-10458922/v1","title":"Certificate-Driven Learning for Safety-Critical Systems: Reward-Free Policy Synthesis via Adversarial Certificate-Margin Optimization","display_name":"Certificate-Driven Learning for Safety-Critical Systems: Reward-Free Policy Synthesis via Adversarial Certificate-Margin Optimization","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224450126","doi":"https://doi.org/10.21203/rs.3.rs-10458922/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-10458922/v1","doi":"https://doi.org/10.21203/rs.3.rs-10458922/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-10458922/v1","pdf_url":"https://www.researchsquare.com/article/rs-10458922/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-10458922/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118906784","display_name":"Mehrshad Eskandarpour","orcid":"https://orcid.org/0009-0006-8597-0293","observed_orcids":["https://orcid.org/0009-0006-8597-0293"]},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mehrshad Eskandarpour","raw_affiliation_strings":["Iran University of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iran University of Science & Technology","institution_ids":["https://openalex.org/I67009956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054876127","display_name":"Mohammad Javad Jannati","orcid":"https://orcid.org/0000-0001-9457-4715","observed_orcids":["https://orcid.org/0000-0001-9457-4715"]},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mohammadjavad Jannati","raw_affiliation_strings":["Iran University of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iran University of Science & Technology","institution_ids":["https://openalex.org/I67009956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078508554","display_name":"Amir Javadi","orcid":"https://orcid.org/0000-0001-7715-4583","observed_orcids":["https://orcid.org/0000-0001-7715-4583"]},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Amir Javadi","raw_affiliation_strings":["Iran University of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iran University of Science & Technology","institution_ids":["https://openalex.org/I67009956"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I67009956"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10142","display_name":"Formal Methods in Verification","score":0.8184000253677368,"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"}},"topics":[{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.8184000253677368,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.09889999777078629,"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/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.019899999722838402,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/safety-critical-systems","display_name":"safety-critical systems","score":0.777999997138977},{"id":"https://openalex.org/keywords/wireless-sensor-networks","display_name":"wireless sensor networks","score":0.9449999928474426},{"id":"https://openalex.org/keywords/cyber-physical-systems","display_name":"cyber-physical systems","score":0.8009999990463257}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7204999923706055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7006000280380249},{"id":"https://openalex.org/C96865113","wikidata":"https://www.wikidata.org/wiki/Q2946816","display_name":"Certificate","level":2,"score":0.5533999800682068},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5504000186920166},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5267999768257141},{"id":"https://openalex.org/C2777632111","wikidata":"https://www.wikidata.org/wiki/Q1937518","display_name":"Reservation","level":2,"score":0.4788999855518341},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.46709999442100525},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4611999988555908},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.444599986076355},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4262999892234802},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.39329999685287476},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3465999960899353},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.3382999897003174},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.329800009727478},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C101403955","wikidata":"https://www.wikidata.org/wiki/Q6707083","display_name":"Lyapunov optimization","level":5,"score":0.30730000138282776},{"id":"https://openalex.org/C527821871","wikidata":"https://www.wikidata.org/wiki/Q228502","display_name":"Access control","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C199622910","wikidata":"https://www.wikidata.org/wiki/Q1128326","display_name":"Constraint satisfaction problem","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.2854999899864197},{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C2776829284","wikidata":"https://www.wikidata.org/wiki/Q1341651","display_name":"Lyapunov stability","level":3,"score":0.2770000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-10458922/v1","doi":"https://doi.org/10.21203/rs.3.rs-10458922/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-10458922/v1","pdf_url":"https://www.researchsquare.com/article/rs-10458922/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-10458922/v1","doi":"https://doi.org/10.21203/rs.3.rs-10458922/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-10458922/v1","pdf_url":"https://www.researchsquare.com/article/rs-10458922/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224450126.pdf","grobid_xml":"https://content.openalex.org/works/W7224450126.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2594675090","https://openalex.org/W4376456312","https://openalex.org/W4376623856"],"related_works":["https://openalex.org/W3217393716","https://openalex.org/W4311418673","https://openalex.org/W4221161266","https://openalex.org/W4315606134","https://openalex.org/W7126361938","https://openalex.org/W7001587376","https://openalex.org/W4388481671","https://openalex.org/W7127591080","https://openalex.org/W3035702124","https://openalex.org/W7223181681"],"abstract_inverted_index":{"Abstract":[0],"Safety-critical":[1],"learning":[2],"systems":[3,137],"require":[4],"controllers":[5],"that":[6,20,35,161,203],"can":[7,207],"be":[8],"audited":[9],"for":[10,83,106,133],"constraint":[11,169],"satisfaction":[12],"under":[13],"adverse":[14],"operating":[15],"conditions,":[16],"not":[17],"only":[18],"policies":[19],"perform":[21],"well":[22],"on":[23],"average.":[24],"This":[25],"paper":[26],"proposes":[27],"Certificate-Driven":[28],"Learning":[29],"(CeDL),":[30],"a":[31,38,55,75,103,117,209],"reward-free":[32],"policy-synthesis":[33],"framework":[34,130],"jointly":[36],"learns":[37],"control":[39,217],"policy":[40,124],"and":[41,71,95,138,154,178,197,211,221],"an":[42],"accompanying":[43],"mathematical":[44],"certificate.":[45],"CeDL":[46,162],"replaces":[47],"expected-return":[48],"maximization":[49,53],"with":[50,184],"worst-case":[51],"certificate-margin":[52],"over":[54],"declared":[56],"admissible":[57],"scenario":[58],"domain.":[59],"The":[60,129],"certificate":[61,165],"unifies":[62],"Lyapunov":[63],"stability":[64],"margins,":[65,68,166],"control-barrier":[66],"safety":[67,111,181],"temporal-logic":[69],"robustness,":[70],"feasibility":[72],"margins":[73],"into":[74],"single":[76],"training":[77],"objective.":[78],"An":[79],"adversarial":[80],"falsifier":[81],"searches":[82],"scenarios":[84],"in":[85,102,140,150,218],"which":[86],"the":[87,96,122,126],"current":[88],"policy-certificate":[89],"pair":[90],"is":[91,113,131],"closest":[92],"to":[93],"violation,":[94],"resulting":[97],"low-margin":[98],"cases":[99],"are":[100],"retained":[101],"hard-scenario":[104],"bank":[105],"counterexample-guided":[107],"optimization.":[108],"A":[109],"runtime":[110],"shield":[112],"further":[114],"introduced":[115],"as":[116],"final":[118],"feasibility-preserving":[119],"mechanism":[120],"when":[121],"nominal":[123],"approaches":[125],"certified":[127],"boundary.":[128],"developed":[132],"general":[134],"stochastic":[135],"discrete-time":[136],"instantiated":[139],"three":[141],"representative":[142],"domains:":[143],"URLLC-aware":[144],"wireless":[145,151],"resource":[146],"allocation,":[147],"energy-safe":[148],"routing":[149],"sensor":[152],"networks,":[153],"robotic":[155,180],"obstacle":[156],"avoidance.":[157],"Simulation":[158],"results":[159,201],"show":[160],"improves":[163],"minimum":[164],"reduces":[167],"observed":[168],"violations,":[170],"lowers":[171],"URLLC":[172],"tail":[173],"delay,":[174],"extends":[175],"sensor-network":[176],"lifetime,":[177],"increases":[179],"distance":[182],"compared":[183],"reward-based":[185],"reinforcement":[186,189,195],"learning,":[187,190,196],"constrained":[188],"model":[191],"predictive":[192],"control,":[193],"shielded":[194],"classical":[198],"controllers.":[199],"These":[200],"indicate":[202],"optimizing":[204],"certifiability":[205],"directly":[206],"provide":[208],"principled":[210],"practical":[212],"path":[213],"toward":[214],"auditable":[215],"learning-based":[216],"safety-critical":[219],"networked":[220],"cyber-physical":[222],"systems.":[223]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-30T00:00:00"}