{"id":"https://openalex.org/W3125413667","doi":"https://doi.org/10.1145/3447928.3456639","title":"Model-based reinforcement learning for approximate optimal control with temporal logic specifications","display_name":"Model-based reinforcement learning for approximate optimal control with temporal logic specifications","publication_year":2021,"publication_date":"2021-05-04","ids":{"openalex":"https://openalex.org/W3125413667","doi":"https://doi.org/10.1145/3447928.3456639","mag":"3125413667"},"language":"en","primary_location":{"id":"doi:10.1145/3447928.3456639","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447928.3456639","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447928.3456639","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on Hybrid Systems: Computation and Control","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3447928.3456639","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054992701","display_name":"M. Cohen","orcid":"https://orcid.org/0000-0001-6957-9645"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Max H. Cohen","raw_affiliation_strings":["Boston University","Boston Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]},{"raw_affiliation_string":"Boston Univ","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086742095","display_name":"C\u0103lin Belta","orcid":"https://orcid.org/0000-0002-7141-2657"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Calin Belta","raw_affiliation_strings":["Boston University","Boston Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]},{"raw_affiliation_string":"Boston Univ","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02656281,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9940999746322632,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9940999746322632,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9919999837875366,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9901000261306763,"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/correctness","display_name":"Correctness","score":0.714415431022644},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.7103216648101807},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6771383881568909},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6733810901641846},{"id":"https://openalex.org/keywords/linear-temporal-logic","display_name":"Linear temporal logic","score":0.6605315208435059},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.607196033000946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5801011919975281},{"id":"https://openalex.org/keywords/certificate","display_name":"Certificate","score":0.5799568891525269},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.5633484125137329},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5388875007629395},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4719630479812622},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4362296164035797},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.35406091809272766},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3525928854942322},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23925769329071045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22065815329551697},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.17712068557739258}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.714415431022644},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.7103216648101807},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6771383881568909},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6733810901641846},{"id":"https://openalex.org/C4777664","wikidata":"https://www.wikidata.org/wiki/Q1536492","display_name":"Linear temporal logic","level":2,"score":0.6605315208435059},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.607196033000946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5801011919975281},{"id":"https://openalex.org/C96865113","wikidata":"https://www.wikidata.org/wiki/Q2946816","display_name":"Certificate","level":2,"score":0.5799568891525269},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.5633484125137329},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5388875007629395},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4719630479812622},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4362296164035797},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.35406091809272766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3525928854942322},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23925769329071045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22065815329551697},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.17712068557739258},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3447928.3456639","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447928.3456639","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447928.3456639","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on Hybrid Systems: Computation and Control","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2101.07156","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.07156","pdf_url":"https://arxiv.org/pdf/2101.07156","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,"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":null,"raw_type":"text"},{"id":"mag:3125413667","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2101.07156.pdf","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,"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},{"id":"doi:10.48550/arxiv.2101.07156","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2101.07156","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,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3447928.3456639","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447928.3456639","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447928.3456639","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on Hybrid Systems: Computation and Control","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G4553413310","display_name":"NRI: FND: A Formal Methods Approach to Safe, Composable, and Distributed Reinforcement Learning for co-Robots","funder_award_id":"2024606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4633791274","display_name":"S&AS: INT: COLLAB: Autonomy as a Service","funder_award_id":"1723995","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8956560402","display_name":"Graduate Research Fellowship (GRFP)","funder_award_id":"1840990","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3125413667.pdf","grobid_xml":"https://content.openalex.org/works/W3125413667.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1483893502","https://openalex.org/W1498432697","https://openalex.org/W1540245649","https://openalex.org/W1540883472","https://openalex.org/W1542432808","https://openalex.org/W1547304883","https://openalex.org/W1935692274","https://openalex.org/W1977671496","https://openalex.org/W1988538197","https://openalex.org/W2016360498","https://openalex.org/W2044323243","https://openalex.org/W2078151802","https://openalex.org/W2086975818","https://openalex.org/W2095274657","https://openalex.org/W2104340364","https://openalex.org/W2116364955","https://openalex.org/W2130290065","https://openalex.org/W2150335178","https://openalex.org/W2152161277","https://openalex.org/W2157577161","https://openalex.org/W2165489953","https://openalex.org/W2167185915","https://openalex.org/W2291649624","https://openalex.org/W2292762495","https://openalex.org/W2296093392","https://openalex.org/W2314983263","https://openalex.org/W2487779201","https://openalex.org/W2524638160","https://openalex.org/W2560504659","https://openalex.org/W2570925621","https://openalex.org/W2594675090","https://openalex.org/W2602683801","https://openalex.org/W2605590175","https://openalex.org/W2772589676","https://openalex.org/W2790688051","https://openalex.org/W2796061040","https://openalex.org/W2800330509","https://openalex.org/W2841721725","https://openalex.org/W2886854944","https://openalex.org/W2887514764","https://openalex.org/W2899349726","https://openalex.org/W2905277694","https://openalex.org/W2911097698","https://openalex.org/W2915060538","https://openalex.org/W2995089744","https://openalex.org/W3014540535","https://openalex.org/W3016201194","https://openalex.org/W3045725247","https://openalex.org/W3048342679","https://openalex.org/W3098925401","https://openalex.org/W3106002372","https://openalex.org/W4255043376"],"related_works":["https://openalex.org/W2739094621","https://openalex.org/W2605590175","https://openalex.org/W2316751503","https://openalex.org/W2735485745","https://openalex.org/W2024376777","https://openalex.org/W3122772106","https://openalex.org/W1979773978","https://openalex.org/W2912832158","https://openalex.org/W2963302365","https://openalex.org/W3120441334","https://openalex.org/W2734633297","https://openalex.org/W3006751794","https://openalex.org/W2951606014","https://openalex.org/W3032939769","https://openalex.org/W2059722814","https://openalex.org/W2902524429","https://openalex.org/W2783274227","https://openalex.org/W2974120149","https://openalex.org/W2942517366","https://openalex.org/W3121117921"],"abstract_inverted_index":{"In":[0],"this":[1,27,77],"paper":[2],"we":[3,69,95,107],"study":[4],"the":[5,40,47,89,109,112],"problem":[6,28,64],"of":[7,32,49,79,88,111],"synthesizing":[8],"optimal":[9,34,43,62,80],"control":[10,35,44,63,81],"policies":[11],"for":[12],"uncertain":[13],"continuous-time":[14],"nonlinear":[15],"systems":[16],"from":[17],"syntactically":[18],"co-safe":[19],"linear":[20],"temporal":[21],"logic":[22],"(scLTL)":[23],"formulas.":[24],"We":[25,37],"formulate":[26],"as":[29],"a":[30,50,56,71,116],"sequence":[31,78],"reach-avoid":[33],"sub-problems.":[36],"show":[38],"that":[39],"resulting":[41],"hybrid":[42],"policy":[45],"guarantees":[46],"satisfaction":[48],"given":[51],"scLTL":[52],"formula":[53],"by":[54],"constructing":[55],"barrier":[57],"certificate.":[58],"Since":[59],"solving":[60],"each":[61],"may":[65],"be":[66],"computationally":[67],"intractable,":[68],"take":[70],"learning-based":[72],"approach":[73],"to":[74],"approximately":[75],"solve":[76],"problems":[82],"online":[83],"without":[84],"requiring":[85],"full":[86],"knowledge":[87],"system":[90],"dynamics.":[91],"Using":[92],"Lyapunov-based":[93],"tools,":[94],"develop":[96],"sufficient":[97],"conditions":[98],"under":[99],"which":[100],"our":[101],"approximate":[102],"solution":[103],"maintains":[104],"correctness.":[105],"Finally,":[106],"demonstrate":[108],"efficacy":[110],"developed":[113],"method":[114],"with":[115],"numerical":[117],"example.":[118]},"counts_by_year":[],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}