{"id":"https://openalex.org/W4392223972","doi":"https://doi.org/10.48550/arxiv.2402.15893","title":"Concurrent Learning of Policy and Unknown Safety Constraints in Reinforcement Learning","display_name":"Concurrent Learning of Policy and Unknown Safety Constraints in Reinforcement Learning","publication_year":2024,"publication_date":"2024-02-24","ids":{"openalex":"https://openalex.org/W4392223972","doi":"https://doi.org/10.48550/arxiv.2402.15893"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2402.15893","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.15893","pdf_url":"https://arxiv.org/pdf/2402.15893","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.15893","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032884534","display_name":"Lunet Yifru","orcid":"https://orcid.org/0000-0002-8805-8252","observed_orcids":["https://orcid.org/0000-0002-8805-8252"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifru, Lunet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086511671","display_name":"Ali Baheri","orcid":"https://orcid.org/0000-0002-5613-0192","observed_orcids":["https://orcid.org/0000-0002-5613-0192"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baheri, Ali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.00039999998989515007,"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":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/safe-reinforcement-learning","display_name":"safe reinforcement learning","score":0.9559999704360962},{"id":"https://openalex.org/keywords/bi-level-optimization","display_name":"bi-level optimization","score":0.8569999933242798},{"id":"https://openalex.org/keywords/constrained-policy-optimization","display_name":"constrained policy optimization","score":0.7710000276565552},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.9589999914169312}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7605950832366943},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5400832891464233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46387800574302673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3523678183555603},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22695007920265198},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11776083707809448}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2402.15893","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.15893","pdf_url":"https://arxiv.org/pdf/2402.15893","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2402.15893","doi":"https://doi.org/10.48550/arxiv.2402.15893","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.15893","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.15893","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.15893","pdf_url":"https://arxiv.org/pdf/2402.15893","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392223972.pdf","grobid_xml":"https://content.openalex.org/works/W4392223972.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2086122291","https://openalex.org/W1987513656","https://openalex.org/W2072376847"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,46,187,234],"(RL)":[2],"has":[3],"revolutionized":[4],"decision-making":[5],"across":[6,168],"a":[7,78,84,97,102,111,121,131,194],"wide":[8],"range":[9],"of":[10,28,96,133,165,171,188,197,206,212,221],"domains":[11],"over":[12],"the":[13,25,44,91,118,134,150,163],"past":[14],"few":[15],"decades.":[16],"Yet,":[17],"deploying":[18],"RL":[19,33,86,177],"policies":[20,178,236],"in":[21,57,157,227],"real-world":[22,61],"scenarios":[23],"presents":[24],"crucial":[26],"challenge":[27],"ensuring":[29],"safety.":[30],"Traditional":[31],"safe":[32,85,176,235],"approaches":[34],"have":[35],"predominantly":[36],"focused":[37],"on":[38,51],"incorporating":[39],"predefined":[40,52],"safety":[41,53,93,108,153,190,202,222,231],"constraints":[42,54,65,232],"into":[43],"policy":[45,88,128,139],"process.":[47],"However,":[48],"this":[49,74,166],"reliance":[50],"poses":[55],"limitations":[56],"dynamic":[58],"and":[59,89,110,233],"unpredictable":[60],"settings":[62],"where":[63],"such":[64],"may":[66],"not":[67],"be":[68],"available":[69],"or":[70],"sufficiently":[71],"adaptable.":[72],"Bridging":[73],"gap,":[75],"we":[76,116,161],"propose":[77],"novel":[79],"approach":[80,167],"that":[81,211,216,237],"concurrently":[82],"learns":[83],"control":[87],"identifies":[90],"unknown":[92],"constraint":[94,191],"parameters":[95,148],"given":[98,151],"environment.":[99],"Initializing":[100],"with":[101,143,179,199],"parametric":[103],"signal":[104],"temporal":[105],"logic":[106],"(pSTL)":[107],"specification":[109],"small":[112],"initial":[113],"labeled":[114],"dataset,":[115],"frame":[117],"problem":[119],"as":[120],"bilevel":[122],"optimization":[123,145],"task,":[124],"intricately":[125],"integrating":[126],"constrained":[127],"optimization,":[129],"using":[130],"Lagrangian-variant":[132],"twin":[135],"delayed":[136],"deep":[137],"deterministic":[138],"gradient":[140],"(TD3)":[141],"algorithm,":[142],"Bayesian":[144],"for":[146,149],"optimizing":[147],"pSTL":[152],"specification.":[154],"Through":[155],"experimentation":[156],"comprehensive":[158],"case":[159],"studies,":[160],"validate":[162],"efficacy":[164],"varying":[169],"forms":[170],"environmental":[172,201,230],"constraints,":[173,223],"consistently":[174],"yielding":[175],"high":[180,195],"returns.":[181],"Furthermore,":[182],"our":[183,207],"findings":[184],"indicate":[185],"successful":[186],"STL":[189],"parameters,":[192],"exhibiting":[193],"degree":[196],"conformity":[198],"true":[200],"constraints.":[203,241],"The":[204],"performance":[205],"model":[208],"closely":[209],"mirrors":[210],"an":[213],"ideal":[214],"scenario":[215],"possesses":[217],"complete":[218],"prior":[219],"knowledge":[220],"demonstrating":[224],"its":[225],"proficiency":[226],"accurately":[228],"identifying":[229],"adhere":[238],"to":[239],"those":[240]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2024-02-28T00:00:00"}