{"id":"https://openalex.org/W4309793424","doi":"https://doi.org/10.1109/access.2022.3218216","title":"Deep Reinforcement Learning Under Signal Temporal Logic Constraints Using Lagrangian Relaxation","display_name":"Deep Reinforcement Learning Under Signal Temporal Logic Constraints Using Lagrangian Relaxation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4309793424","doi":"https://doi.org/10.1109/access.2022.3218216"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3218216","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3218216","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09933457.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09933457.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070836427","display_name":"Junya Ikemoto","orcid":"https://orcid.org/0000-0002-0145-3381"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junya Ikemoto","raw_affiliation_strings":["Graduate School of Engineering Science, Osaka University, Toyonaka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0145-3381","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Toyonaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046686505","display_name":"Toshimitsu Ushio","orcid":"https://orcid.org/0000-0002-4009-270X"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshimitsu Ushio","raw_affiliation_strings":["Graduate School of Engineering Science, Osaka University, Toyonaka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4009-270X","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Toyonaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98285908"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.5073,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.84806755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"10","issue":null,"first_page":"114814","last_page":"114828"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9954000115394592,"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":0.9954000115394592,"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":0.9933000206947327,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8223789930343628},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7183507680892944},{"id":"https://openalex.org/keywords/lagrangian-relaxation","display_name":"Lagrangian relaxation","score":0.6722478270530701},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6430178284645081},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5722655057907104},{"id":"https://openalex.org/keywords/relaxation","display_name":"Relaxation (psychology)","score":0.5622835159301758},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5147912502288818},{"id":"https://openalex.org/keywords/lagrangian","display_name":"Lagrangian","score":0.5096907615661621},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4386043846607208},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43536460399627686},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.40958860516548157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3587992191314697},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.347248911857605},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.34224557876586914},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21036630868911743},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.1200716495513916}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8223789930343628},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7183507680892944},{"id":"https://openalex.org/C91765299","wikidata":"https://www.wikidata.org/wiki/Q3424292","display_name":"Lagrangian relaxation","level":2,"score":0.6722478270530701},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6430178284645081},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5722655057907104},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.5622835159301758},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5147912502288818},{"id":"https://openalex.org/C53469067","wikidata":"https://www.wikidata.org/wiki/Q505735","display_name":"Lagrangian","level":2,"score":0.5096907615661621},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4386043846607208},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43536460399627686},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.40958860516548157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3587992191314697},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.347248911857605},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.34224557876586914},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21036630868911743},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.1200716495513916},{"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3218216","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3218216","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09933457.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a7c0ff9ab1144da5be3d8bb14bdf0db5","is_oa":true,"landing_page_url":"https://doaj.org/article/a7c0ff9ab1144da5be3d8bb14bdf0db5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 114814-114828 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3218216","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3218216","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09933457.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1761547297","display_name":"AI\u96c6\u7d04\u7684\u30b5\u30a4\u30d0\u30fc\u30d5\u30a3\u30b8\u30ab\u30eb\u30b7\u30b9\u30c6\u30e0\u306e\u5f62\u5f0f\u7684\u89e3\u6790\u8a2d\u8a08\u624b\u6cd5","funder_award_id":"JPMJCR2012","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G2351232530","display_name":null,"funder_award_id":"JPMJCR2012, Japan","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G4419479967","display_name":"\u5b89\u5168\u6027\u3092\u4fdd\u8a3c\u3057\u305f\u30d8\u30c6\u30ed\u30b8\u30cb\u30a2\u30b9\u306a\u30de\u30eb\u30c1\u30ed\u30dc\u30c3\u30c8\u30b7\u30b9\u30c6\u30e0\u306e\u5b66\u7fd2\u5236\u5fa1","funder_award_id":"21J10780","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8008078829","display_name":null,"funder_award_id":"JPMJCR2012","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G8589389593","display_name":null,"funder_award_id":"JP21J10780","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4309793424.pdf","grobid_xml":"https://content.openalex.org/works/W4309793424.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1498432697","https://openalex.org/W1518931405","https://openalex.org/W1522301498","https://openalex.org/W1547304883","https://openalex.org/W1669104078","https://openalex.org/W1959608418","https://openalex.org/W2049399166","https://openalex.org/W2092884371","https://openalex.org/W2145339207","https://openalex.org/W2524638160","https://openalex.org/W2575705757","https://openalex.org/W2594675090","https://openalex.org/W2787938642","https://openalex.org/W2798588334","https://openalex.org/W2841721725","https://openalex.org/W2898035736","https://openalex.org/W2904246096","https://openalex.org/W2908261578","https://openalex.org/W2963864421","https://openalex.org/W2976866784","https://openalex.org/W2997572754","https://openalex.org/W3001024844","https://openalex.org/W3004091789","https://openalex.org/W3007553593","https://openalex.org/W3130777366","https://openalex.org/W3176233416","https://openalex.org/W3189576409","https://openalex.org/W3201878770","https://openalex.org/W4211171425","https://openalex.org/W4287327731","https://openalex.org/W4312712355","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6684921986","https://openalex.org/W6748839928","https://openalex.org/W6751051826","https://openalex.org/W6757592117","https://openalex.org/W6768323397","https://openalex.org/W6772627330","https://openalex.org/W6774126978","https://openalex.org/W6790543905"],"related_works":["https://openalex.org/W2002102264","https://openalex.org/W4237964977","https://openalex.org/W2155100848","https://openalex.org/W3149469165","https://openalex.org/W4313484281","https://openalex.org/W2616198151","https://openalex.org/W2315999538","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,131],"(DRL)":[3],"has":[4],"been":[5],"attracted":[6],"much":[7],"attention":[8],"to":[9,13,49],"as":[10,110],"an":[11,34,90],"approach":[12],"solve":[14],"optimal":[15,35,44,107],"control":[16,36,45,52,69,108],"problems":[17,46],"without":[18],"mathematical":[19],"models":[20],"of":[21,133],"systems.":[22],"On":[23],"the":[24,43,56,85,104,111,121,130,134],"other":[25],"hand,":[26],"in":[27],"general,":[28],"constraints":[29,48,57],"may":[30],"be":[31],"imposed":[32],"on":[33],"problem.":[37],"In":[38],"this":[39],"study,":[40],"we":[41,88,127],"consider":[42],"with":[47,84],"complete":[50],"temporal":[51,60],"tasks.":[53],"We":[54,102],"describe":[55],"using":[58,120],"signal":[59],"logic":[61],"(STL),":[62],"which":[63,97],"is":[64,98],"useful":[65],"for":[66],"time":[67,80],"sensitive":[68],"tasks":[70],"since":[71],"it":[72],"can":[73],"specify":[74],"continuous":[75],"signals":[76],"within":[77],"a":[78,100,115],"bounded":[79],"interval.":[81],"To":[82],"deal":[83],"STL":[86,105],"constraints,":[87],"introduce":[89],"extended":[91],"constrained":[92,106,117],"Markov":[93],"decision":[94],"process":[95],"(CMDP),":[96],"called":[99],"\u03c4-CMDP.":[101],"formulate":[103],"problem":[109],"\u03c4-CMDP":[112],"and":[113],"propose":[114],"two-phase":[116],"DRL":[118],"algorithm":[119],"Lagrangian":[122],"relaxation":[123],"method.":[124],"Through":[125],"simulations,":[126],"also":[128],"demonstrate":[129],"performance":[132],"proposed":[135],"algorithm.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2022-11-29T00:00:00"}