{"id":"https://openalex.org/W3198607174","doi":null,"title":"Safety-Critical Modular Deep Reinforcement Learning with Temporal Logic through Gaussian Processes and Control Barrier Functions","display_name":"Safety-Critical Modular Deep Reinforcement Learning with Temporal Logic through Gaussian Processes and Control Barrier Functions","publication_year":2021,"publication_date":"2021-09-07","ids":{"openalex":"https://openalex.org/W3198607174","mag":"3198607174"},"language":"en","primary_location":{"id":"mag:3198607174","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2109.02791","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2109.02791","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001420415","display_name":"Mingyu Cai","orcid":"https://orcid.org/0000-0002-2967-2703","observed_orcids":["https://orcid.org/0000-0002-2967-2703"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingyu Cai","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2967-2703","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086654963","display_name":"Cristian-Ioan Vasile","orcid":"https://orcid.org/0000-0002-1132-1462","observed_orcids":["https://orcid.org/0000-0002-1132-1462"]},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cristian-Ioan Vasile","raw_affiliation_strings":["Lehigh University,"],"raw_orcid":"https://orcid.org/0000-0002-1132-1462","affiliations":[{"raw_affiliation_string":"Lehigh University,","institution_ids":["https://openalex.org/I186143895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9785000085830688,"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":0.9785000085830688,"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/T10142","display_name":"Formal Methods in Verification","score":0.015799999237060547,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0017000000225380063,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.8500000238418579},{"id":"https://openalex.org/keywords/linear-temporal-logic","display_name":"linear temporal logic","score":0.949999988079071},{"id":"https://openalex.org/keywords/gaussian-processes","display_name":"Gaussian processes","score":0.7860000133514404},{"id":"https://openalex.org/keywords/control-barrier-functions","display_name":"control barrier functions","score":0.8510000109672546},{"id":"https://openalex.org/keywords/reward-shaping","display_name":"reward shaping","score":0.8330000042915344},{"id":"https://openalex.org/keywords/safe-exploration","display_name":"safe exploration","score":0.6110000014305115},{"id":"https://openalex.org/keywords/robot-control","display_name":"robot control","score":0.5189999938011169},{"id":"https://openalex.org/keywords/unknown-dynamics","display_name":"unknown dynamics","score":0.3499999940395355}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8079164624214172},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.719807505607605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056176662445068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5343156456947327},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4911658465862274},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.48235243558883667},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.465268611907959},{"id":"https://openalex.org/C2776807809","wikidata":"https://www.wikidata.org/wiki/Q6510160","display_name":"Learning automata","level":3,"score":0.4163038730621338},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37378811836242676},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3458136320114136},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3435249328613281},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11837264895439148},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3198607174","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2109.02791","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3198607174","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2109.02791","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W125598877","https://openalex.org/W1494502909","https://openalex.org/W1771410628","https://openalex.org/W1777239053","https://openalex.org/W1845972764","https://openalex.org/W2053572490","https://openalex.org/W2078151802","https://openalex.org/W2099089255","https://openalex.org/W2121863487","https://openalex.org/W2133255100","https://openalex.org/W2145339207","https://openalex.org/W2150335178","https://openalex.org/W2164419340","https://openalex.org/W2165726630","https://openalex.org/W2173248099","https://openalex.org/W2336416123","https://openalex.org/W2397581010","https://openalex.org/W2487186542","https://openalex.org/W2489231587","https://openalex.org/W2489939061","https://openalex.org/W2524638160","https://openalex.org/W2560504659","https://openalex.org/W2611136914","https://openalex.org/W2735010720","https://openalex.org/W2736601468","https://openalex.org/W2804948070","https://openalex.org/W2892521964","https://openalex.org/W2895196950","https://openalex.org/W2914941842","https://openalex.org/W2931553127","https://openalex.org/W2952905979","https://openalex.org/W2963148914","https://openalex.org/W2963575966","https://openalex.org/W2966537673","https://openalex.org/W2966735560","https://openalex.org/W2972520119","https://openalex.org/W2976866784","https://openalex.org/W2995074243","https://openalex.org/W3011888914","https://openalex.org/W3012136760","https://openalex.org/W3014472602","https://openalex.org/W3015304327","https://openalex.org/W3037396281","https://openalex.org/W3039276491","https://openalex.org/W3080598349","https://openalex.org/W3093240915","https://openalex.org/W3110550608","https://openalex.org/W3119278263","https://openalex.org/W3130777366","https://openalex.org/W3131897549","https://openalex.org/W3133533407","https://openalex.org/W3136316167","https://openalex.org/W3175871729","https://openalex.org/W3175925814","https://openalex.org/W3195647294"],"related_works":["https://openalex.org/W4286985629","https://openalex.org/W2923132828","https://openalex.org/W7116288948","https://openalex.org/W4386821348","https://openalex.org/W4312433875","https://openalex.org/W2914702425","https://openalex.org/W4391021830","https://openalex.org/W4210504149","https://openalex.org/W2922874720","https://openalex.org/W2966735560"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,37],"(RL)":[2],"is":[3,22,70],"a":[4,23,36,57,85,118,124,159,188,228],"promising":[5],"approach":[6],"and":[7,32,50,138,184,224],"has":[8],"limited":[9],"success":[10,222],"towards":[11],"real-world":[12],"applications,":[13],"because":[14],"ensuring":[15],"safe":[16],"exploration":[17],"or":[18],"facilitating":[19],"adequate":[20],"exploitation":[21],"challenges":[24],"for":[25,43,96],"controlling":[26],"robotic":[27,208],"systems":[28],"with":[29,98,171,227],"unknown":[30],"models":[31],"measurement":[33],"uncertainties.":[34],"Such":[35],"problem":[38],"becomes":[39],"even":[40],"more":[41],"intractable":[42],"complex":[44,74],"tasks":[45,75,137],"over":[46,76],"continuous":[47],"space":[48],"(state-space":[49],"action-space).":[51],"In":[52,175],"this":[53],"paper,":[54],"we":[55,90,122,157,177,199,211],"propose":[56,91],"learning-based":[58],"control":[59],"framework":[60,205],"consisting":[61],"of":[62,110,131,142,181,196,203],"several":[63,207],"aspects:":[64],"(1)":[65],"linear":[66],"temporal":[67],"logic":[68],"(LTL)":[69],"leveraged":[71],"to":[72,84,134,151,168,186,191],"facilitate":[73,139],"an":[77,92,214],"infinite":[78],"horizons":[79],"which":[80],"can":[81],"be":[82],"translated":[83],"novel":[86],"automaton":[87,132],"structure;":[88],"(2)":[89],"innovative":[93],"reward":[94,119],"scheme":[95],"RL-agent":[97],"the":[99,108,112,129,140,153,179,194,201,204],"formal":[100],"guarantee":[101],"such":[102,213],"that":[103],"global":[104],"optimal":[105],"policies":[106],"maximize":[107],"probability":[109,230],"satisfying":[111],"LTL":[113,182],"specifications;":[114],"(3)":[115],"based":[116],"on":[117],"shaping":[120],"technique,":[121],"develop":[123],"modular":[125,216],"policy-gradient":[126],"architecture":[127],"utilizing":[128],"benefits":[130],"structures":[133],"decompose":[135],"overall":[136],"performance":[141],"learned":[143],"controllers;":[144],"(4)":[145],"by":[146],"incorporating":[147],"Gaussian":[148],"Processes":[149],"(GPs)":[150],"estimate":[152],"uncertain":[154],"dynamic":[155],"systems,":[156],"synthesize":[158],"model-based":[160],"safeguard":[161],"using":[162],"Exponential":[163],"Control":[164],"Barrier":[165],"Functions":[166],"(ECBFs)":[167],"address":[169],"problems":[170],"high-order":[172],"relative":[173],"degrees.":[174],"addition,":[176],"utilize":[178],"properties":[180],"automatons":[183],"ECBFs":[185],"construct":[187],"guiding":[189],"process":[190],"further":[192],"improve":[193],"efficiency":[195],"exploration.":[197],"Finally,":[198],"demonstrate":[200],"effectiveness":[202],"via":[206],"environments.":[209],"And":[210],"show":[212],"ECBF-based":[215],"deep":[217],"RL":[218],"algorithm":[219],"achieves":[220],"near-perfect":[221],"rates":[223],"guard":[225],"safety":[226],"high":[229],"confidence":[231],"during":[232],"training.":[233]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-09-13T00:00:00"}