{"id":"https://openalex.org/W7161804555","doi":"https://doi.org/10.48550/arxiv.2605.18841","title":"From Cumulative Constraints to Adaptive Runtime Safety Control for Nonstationary Reinforcement Learning","display_name":"From Cumulative Constraints to Adaptive Runtime Safety Control for Nonstationary Reinforcement Learning","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7161804555","doi":"https://doi.org/10.48550/arxiv.2605.18841"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.18841","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18841","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.18841","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050619633","display_name":"Timofey Tomashevskiy","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tomashevskiy, Timofey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5050619633"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6482999920845032,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6482999920845032,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.15649999678134918,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.04969999939203262,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.6546000242233276},{"id":"https://openalex.org/keywords/enforcement","display_name":"Enforcement","score":0.5291000008583069},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5149000287055969},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5051000118255615},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.47119998931884766},{"id":"https://openalex.org/keywords/budget-constraint","display_name":"Budget constraint","score":0.4648999869823456},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.3801000118255615}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6546000242233276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5781999826431274},{"id":"https://openalex.org/C2779777834","wikidata":"https://www.wikidata.org/wiki/Q4202277","display_name":"Enforcement","level":2,"score":0.5291000008583069},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5051000118255615},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C8505890","wikidata":"https://www.wikidata.org/wiki/Q605095","display_name":"Budget constraint","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4205999970436096},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.3801000118255615},{"id":"https://openalex.org/C132835097","wikidata":"https://www.wikidata.org/wiki/Q7663745","display_name":"System safety","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.36730000376701355},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34139999747276306},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3206000030040741},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.28349998593330383},{"id":"https://openalex.org/C153517567","wikidata":"https://www.wikidata.org/wiki/Q26090","display_name":"Mechanism design","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C49261128","wikidata":"https://www.wikidata.org/wiki/Q1132455","display_name":"Hazard","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.18841","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18841","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.18841","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18841","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6089747548103333}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Safety":[0,63],"in":[1,121,167,179],"reinforcement":[2,230],"learning":[3,231],"is":[4,32,110,136],"often":[5],"specified":[6],"through":[7],"cumulative":[8,72,158,220],"cost":[9,103,159],"constraints,":[10],"but":[11],"these":[12],"trajectory-level":[13],"guarantees":[14,149],"do":[15],"not":[16],"directly":[17],"prevent":[18],"unsafe":[19],"individual":[20],"decisions,":[21],"especially":[22],"under":[23],"nonstationarity.":[24],"In":[25],"continual":[26,229],"and":[27,96,128,144,161,172,195],"nonstationary":[28,180],"settings,":[29],"the":[30,35,39,84,105,132,140,147,205],"difficulty":[31],"amplified":[33],"because":[34],"risk":[36,94],"associated":[37],"with":[38],"same":[40],"action":[41],"can":[42],"vary":[43],"across":[44],"contexts,":[45],"while":[46,199],"a":[47,66,71,91,163,215],"fixed":[48],"state-level":[49,77],"threshold":[50,109,151],"may":[51],"be":[52],"either":[53],"too":[54,57],"conservative":[55],"or":[56,124],"weak.":[58],"We":[59,138,176],"propose":[60],"Constraint":[61],"Projection":[62],"Shield":[64],"(CPSS),":[65],"runtime":[67],"mechanism":[68,148],"that":[69,117,146],"converts":[70],"safety":[73,86,102,134,193,221,226],"budget":[74,135],"into":[75,90,223],"adaptive":[76,211],"control":[78,227],"constraints":[79],"during":[80],"execution.":[81],"CPSS":[82,178,189],"tracks":[83],"remaining":[85],"budget,":[87],"projects":[88],"it":[89],"time-varying":[92],"admissible":[93],"threshold,":[95],"filters":[97],"policy":[98,143],"actions":[99],"whose":[100],"predicted":[101],"exceeds":[104],"active":[106],"threshold.":[107],"The":[108],"adjusted":[111],"online":[112],"using":[113,184],"contextual":[114],"signals":[115],"so":[116],"enforcement":[118],"becomes":[119],"stricter":[120],"more":[122],"demanding":[123],"rapidly":[125],"changing":[126],"regimes":[127],"less":[129],"restrictive":[130],"when":[131],"available":[133],"sufficient.":[137],"analyze":[139],"resulting":[141],"shielded":[142],"show":[145],"per-state":[150],"satisfaction":[152],"for":[153,228],"executed":[154],"actions,":[155],"induces":[156],"finite-horizon":[157],"bounds,":[160],"yields":[162],"performance":[164],"degradation":[165],"bound":[166],"terms":[168],"of":[169],"intervention":[170],"frequency":[171],"per-step":[173],"reward":[174],"distortion.":[175],"evaluate":[177],"highway":[181],"merging":[182],"scenarios":[183],"highway-env.":[185],"Across":[186],"multiple":[187],"seeds,":[188],"substantially":[190],"reduces":[191],"proximity-based":[192],"violations":[194],"increases":[196],"separation":[197],"margins":[198],"intervening":[200],"selectively":[201],"rather":[202],"than":[203],"dominating":[204],"learned":[206],"policy.":[207],"These":[208],"results":[209],"support":[210],"budget-to-threshold":[212],"projection":[213],"as":[214],"practical":[216],"way":[217],"to":[218],"transform":[219],"specifications":[222],"effective":[224],"local":[225],"systems.":[232]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-21T00:00:00"}