{"id":"https://openalex.org/W4391021830","doi":"https://doi.org/10.1109/cdc49753.2023.10383601","title":"Safe Reinforcement Learning with Probabilistic Guarantees Satisfying Temporal Logic Specifications in Continuous Action Spaces","display_name":"Safe Reinforcement Learning with Probabilistic Guarantees Satisfying Temporal Logic Specifications in Continuous Action Spaces","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391021830","doi":"https://doi.org/10.1109/cdc49753.2023.10383601"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","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/A5065905965","display_name":"Hanna Krasowski","orcid":"https://orcid.org/0000-0002-6730-3802"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Hanna Krasowski","raw_affiliation_strings":["Technical University of Munich,Munich,Germany","California Institute of Technology, Pasadena, USA","Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"California Institute of Technology, Pasadena, USA","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068127497","display_name":"Prithvi Akella","orcid":"https://orcid.org/0000-0003-4375-0015"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prithvi Akella","raw_affiliation_strings":["California Institute of Technology,Pasadena,USA","California Institute of Technology, Pasadena, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology,Pasadena,USA","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"California Institute of Technology, Pasadena, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039171820","display_name":"Aaron D. Ames","orcid":"https://orcid.org/0000-0003-0848-3177"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron D. Ames","raw_affiliation_strings":["California Institute of Technology,Pasadena,USA","California Institute of Technology, Pasadena, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology,Pasadena,USA","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"California Institute of Technology, Pasadena, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005383495","display_name":"Matthias Althoff","orcid":"https://orcid.org/0000-0003-3733-842X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Althoff","raw_affiliation_strings":["Technical University of Munich,Munich,Germany","Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9444,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74350831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4372","last_page":"4378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9937000274658203,"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":0.9937000274658203,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9922999739646912,"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":0.983299970626831,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.8061163425445557},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7601801753044128},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7179216146469116},{"id":"https://openalex.org/keywords/probabilistic-ctl","display_name":"Probabilistic CTL","score":0.6014561653137207},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5958846211433411},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5372386574745178},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.5033261179924011},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4574751853942871},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4111081063747406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35836708545684814},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.26135876774787903},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18471106886863708},{"id":"https://openalex.org/keywords/probabilistic-analysis-of-algorithms","display_name":"Probabilistic analysis of algorithms","score":0.15554112195968628},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13969823718070984}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.8061163425445557},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7601801753044128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7179216146469116},{"id":"https://openalex.org/C52063229","wikidata":"https://www.wikidata.org/wiki/Q7246845","display_name":"Probabilistic CTL","level":4,"score":0.6014561653137207},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5958846211433411},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5372386574745178},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.5033261179924011},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4574751853942871},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4111081063747406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35836708545684814},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26135876774787903},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18471106886863708},{"id":"https://openalex.org/C24404364","wikidata":"https://www.wikidata.org/wiki/Q7246846","display_name":"Probabilistic analysis of algorithms","level":3,"score":0.15554112195968628},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13969823718070984},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1901829485","display_name":null,"funder_award_id":"FA9550-19-1-0302","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G314058022","display_name":"CPS: Medium: Safety-Critical Cyber-Physical Systems: From Validation & Verification to Test & Evaluation","funder_award_id":"1932091","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1533557569","https://openalex.org/W1547304883","https://openalex.org/W2049399166","https://openalex.org/W2053572490","https://openalex.org/W2092884371","https://openalex.org/W2604382266","https://openalex.org/W2736601468","https://openalex.org/W2785700716","https://openalex.org/W2841721725","https://openalex.org/W2905277694","https://openalex.org/W2963575966","https://openalex.org/W2964138223","https://openalex.org/W2966735560","https://openalex.org/W2969218722","https://openalex.org/W3026873144","https://openalex.org/W3048348667","https://openalex.org/W3093055384","https://openalex.org/W3097154153","https://openalex.org/W3121030992","https://openalex.org/W3130777366","https://openalex.org/W3135301907","https://openalex.org/W3135649364","https://openalex.org/W3142005321","https://openalex.org/W3156919398","https://openalex.org/W3206558114","https://openalex.org/W3216772467","https://openalex.org/W4205368732","https://openalex.org/W4312699513","https://openalex.org/W4324116431","https://openalex.org/W6741002519","https://openalex.org/W6774397352","https://openalex.org/W6804601995","https://openalex.org/W6810116908"],"related_works":["https://openalex.org/W1497573972","https://openalex.org/W2289277223","https://openalex.org/W2749065928","https://openalex.org/W1499367685","https://openalex.org/W4238495367","https://openalex.org/W90591307","https://openalex.org/W2225666389","https://openalex.org/W2289944023","https://openalex.org/W2371210594","https://openalex.org/W2138707849"],"abstract_inverted_index":{"Vanilla":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"can":[4],"efficiently":[5,121],"solve":[6],"complex":[7],"tasks":[8],"but":[9],"does":[10],"not":[11],"provide":[12],"any":[13],"guarantees":[14,37,107,146],"on":[15,154,160],"system":[16,66],"behavior.":[17],"To":[18],"bridge":[19],"this":[20,77],"gap,":[21],"we":[22,72,103],"propose":[23],"a":[24,49,55,68,148,165,170,174,178],"three-":[25],"step":[26],"safe":[27,186],"RL":[28,84,150,187],"procedure":[29],"for":[30,91,114,123],"continuous":[31,124],"action":[32,125],"spaces":[33],"that":[34,86,152,184],"provides":[35],"probabilistic":[36,105,144,196],"with":[38,52,108,177],"respect":[39,53,109],"to":[40,54,64,110,168,190],"temporal":[41,56,111],"logic":[42,57,112],"specifications.":[43],"First,":[44],"our":[45,158,185],"approach":[46,119,159,188],"probabilistically":[47,78],"verifies":[48],"candidate":[50],"controller":[51,80,90],"specification":[58],"while":[59,172,193],"randomizing":[60],"the":[61,65,74,88,94,99,115],"control":[62,100],"inputs":[63],"within":[67],"bounded":[69,96],"set.":[70],"Second,":[71],"improve":[73],"performance":[75,92,135],"of":[76,131],"verified":[79,89],"by":[81],"adding":[82],"an":[83,161],"agent":[85],"optimizes":[87],"in":[93],"same":[95],"set":[97],"around":[98],"input.":[101],"Third,":[102],"verify":[104],"safety":[106,132,145,197],"specifications":[113],"learned":[116],"agent.":[117],"Our":[118,181],"is":[120],"implementable":[122],"and":[126,134,147],"state":[127],"spaces.":[128],"The":[129],"separation":[130],"verification":[133],"improvement":[136],"into":[137],"two":[138],"distinct":[139],"steps":[140],"realizes":[141],"both":[142],"explicit":[143],"straightforward":[149],"setup":[151],"focuses":[153],"performance.":[155],"We":[156],"evaluate":[157],"evasion":[162],"task":[163],"where":[164],"robot":[166],"has":[167],"reach":[169],"goal":[171],"evading":[173],"dynamic":[175],"obstacle":[176],"specific":[179],"maneuver.":[180],"results":[182],"show":[183],"leads":[189],"efficient":[191],"learning":[192],"maintaining":[194],"its":[195],"specification.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}