{"id":"https://openalex.org/W4414360393","doi":"https://doi.org/10.24963/ijcai.2025/554","title":"SPoRt - Safe Policy Ratio: Certified Training and Deployment of Task Policies in Model-Free RL","display_name":"SPoRt - Safe Policy Ratio: Certified Training and Deployment of Task Policies in Model-Free RL","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360393","doi":"https://doi.org/10.24963/ijcai.2025/554"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/554","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073819879","display_name":"Jacques Cloete","orcid":"https://orcid.org/0000-0003-4864-2662"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jacques Cloete","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089227448","display_name":"Nikolaus Vertovec","orcid":"https://orcid.org/0000-0003-4244-8623"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nikolaus Vertovec","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091718585","display_name":"Alessandro Abate","orcid":"https://orcid.org/0000-0002-5627-9093"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alessandro Abate","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I40120149"],"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":"4976","last_page":"4984"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9463000297546387,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9463000297546387,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9383000135421753,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.9379000067710876,"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/task","display_name":"Task (project management)","score":0.6473000049591064},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6122000217437744},{"id":"https://openalex.org/keywords/certification","display_name":"Certification","score":0.5931000113487244},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5566999912261963},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.5289999842643738},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4961000084877014},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4823000133037567},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4519999921321869}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6473000049591064},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6122000217437744},{"id":"https://openalex.org/C46304622","wikidata":"https://www.wikidata.org/wiki/Q374814","display_name":"Certification","level":2,"score":0.5931000113487244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5602999925613403},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5566999912261963},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5289999842643738},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4961000084877014},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4823000133037567},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.41819998621940613},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.313400000333786},{"id":"https://openalex.org/C109986646","wikidata":"https://www.wikidata.org/wiki/Q546113","display_name":"Public policy","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.27950000762939453},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.26269999146461487},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/554","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"To":[0],"apply":[1],"reinforcement":[2],"learning":[3],"to":[4,9,62,73,79,133,160],"safety-critical":[5],"applications,":[6],"we":[7,22,144],"ought":[8],"provide":[10,28],"safety":[11,37,136],"guarantees":[12,137],"during":[13],"both":[14],"policy":[15,43,55,119],"training":[16,116],"and":[17,78,106],"deployment.":[18],"In":[19],"this":[20,149],"work":[21],"present":[23,85,145],"novel":[24],"theoretical":[25,158],"results":[26,147],"that":[27,57],"a":[29,36,40,45,53,63,90,96,111,122,154],"bound":[30,97,124,159],"on":[31,52,103,125,164],"the":[32,49,99,117,131,157],"probability":[33],"of":[34,156],"violating":[35],"property":[38,126],"for":[39,93,98,115,140],"new":[41,112],"task-specific":[42,118,141],"in":[44,138],"model-free,":[46],"episodic":[47],"setup:":[48],"bound,":[50],"based":[51,102,163],"'maximum":[54],"ratio'":[56],"is":[58],"computed":[59],"with":[60],"respect":[61],"'safe'":[64],"base":[65,100],"policy,":[66,101],"can":[67],"also":[68,88],"be":[69],"more":[70],"generally":[71],"applied":[72],"temporally-extended":[74],"properties":[75],"(beyond":[76],"safety)":[77],"robust":[80],"control":[81],"problems.":[82],"We":[83],"thus":[84],"SPoRt,":[86],"which":[87,107],"provides":[89],"data-driven":[91],"approach":[92,114],"obtaining":[94],"such":[95],"scenario":[104],"theory,":[105],"includes":[108],"Projected":[109],"PPO,":[110],"projection-based":[113],"while":[120],"maintaining":[121],"user-specified":[123],"violation.":[127],"Hence,":[128],"SPoRt":[129],"enables":[130],"user":[132],"trade":[134],"off":[135],"exchange":[139],"performance.":[142],"Accordingly,":[143],"experimental":[146],"demonstrating":[148],"trade-off,":[150],"as":[151,153],"well":[152],"comparison":[155],"posterior":[161],"bounds":[162],"empirical":[165],"violation":[166],"rates.":[167]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
