{"id":"https://openalex.org/W3129402851","doi":"https://doi.org/10.1109/iros51168.2021.9636598","title":"Probabilistically Guaranteed Satisfaction of Temporal Logic Constraints During Reinforcement Learning","display_name":"Probabilistically Guaranteed Satisfaction of Temporal Logic Constraints During Reinforcement Learning","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3129402851","doi":"https://doi.org/10.1109/iros51168.2021.9636598","mag":"3129402851"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9636598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636598","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","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/A5053550436","display_name":"Derya Aksaray","orcid":"https://orcid.org/0000-0003-4236-9116"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Derya Aksaray","raw_affiliation_strings":["University of Minnesota, Minneapolis, MN"],"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, MN","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041762786","display_name":"Yasin Yaz\u0131c\u0131o\u011flu","orcid":"https://orcid.org/0000-0001-6957-6831"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yasin Yazicioglu","raw_affiliation_strings":["University of Minnesota, Minneapolis, MN"],"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, MN","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071095014","display_name":"Ahmet Semi Asarkaya","orcid":null},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmet Semi Asarkaya","raw_affiliation_strings":["University of Minnesota, Minneapolis, MN"],"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, MN","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053550436"],"corresponding_institution_ids":["https://openalex.org/I130238516"],"apc_list":null,"apc_paid":null,"fwci":1.3958,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.84308289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"16","issue":null,"first_page":"6531","last_page":"6537"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T12288","display_name":"Optimization and Search Problems","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9926000237464905,"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/constraint-satisfaction","display_name":"Constraint satisfaction","score":0.7567629218101501},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7543364763259888},{"id":"https://openalex.org/keywords/constraint-satisfaction-problem","display_name":"Constraint satisfaction problem","score":0.7372089624404907},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7329955697059631},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6983766555786133},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6497390270233154},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6247177720069885},{"id":"https://openalex.org/keywords/constraint-logic-programming","display_name":"Constraint logic programming","score":0.5909500122070312},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5292415022850037},{"id":"https://openalex.org/keywords/local-consistency","display_name":"Local consistency","score":0.49091750383377075},{"id":"https://openalex.org/keywords/hybrid-algorithm","display_name":"Hybrid algorithm (constraint satisfaction)","score":0.47301581501960754},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.46433815360069275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41994529962539673},{"id":"https://openalex.org/keywords/constraint-programming","display_name":"Constraint programming","score":0.4152772128582001},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.195794939994812},{"id":"https://openalex.org/keywords/stochastic-programming","display_name":"Stochastic programming","score":0.15729603171348572}],"concepts":[{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"score":0.7567629218101501},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7543364763259888},{"id":"https://openalex.org/C199622910","wikidata":"https://www.wikidata.org/wiki/Q1128326","display_name":"Constraint satisfaction problem","level":3,"score":0.7372089624404907},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7329955697059631},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6983766555786133},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6497390270233154},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6247177720069885},{"id":"https://openalex.org/C176783269","wikidata":"https://www.wikidata.org/wiki/Q5164378","display_name":"Constraint logic programming","level":4,"score":0.5909500122070312},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5292415022850037},{"id":"https://openalex.org/C137105694","wikidata":"https://www.wikidata.org/wiki/Q3407510","display_name":"Local consistency","level":4,"score":0.49091750383377075},{"id":"https://openalex.org/C62469222","wikidata":"https://www.wikidata.org/wiki/Q17092103","display_name":"Hybrid algorithm (constraint satisfaction)","level":5,"score":0.47301581501960754},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.46433815360069275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41994529962539673},{"id":"https://openalex.org/C173404611","wikidata":"https://www.wikidata.org/wiki/Q528588","display_name":"Constraint programming","level":3,"score":0.4152772128582001},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.195794939994812},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.15729603171348572},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros51168.2021.9636598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636598","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.75,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W1498432697","https://openalex.org/W1526540304","https://openalex.org/W1607782211","https://openalex.org/W1845972764","https://openalex.org/W1975255760","https://openalex.org/W1996625075","https://openalex.org/W2078151802","https://openalex.org/W2097838240","https://openalex.org/W2121863487","https://openalex.org/W2129226651","https://openalex.org/W2133632477","https://openalex.org/W2151958719","https://openalex.org/W2267331800","https://openalex.org/W2416117881","https://openalex.org/W2524638160","https://openalex.org/W2887514764","https://openalex.org/W2963525569","https://openalex.org/W2963575966","https://openalex.org/W2964219844","https://openalex.org/W2964352321","https://openalex.org/W2966735560","https://openalex.org/W2997105835","https://openalex.org/W3006844914","https://openalex.org/W3009922106","https://openalex.org/W3021964239","https://openalex.org/W3037396281","https://openalex.org/W3085843156","https://openalex.org/W3090827750","https://openalex.org/W3101868692","https://openalex.org/W3129402851","https://openalex.org/W3131957051","https://openalex.org/W4287829052","https://openalex.org/W6636258220","https://openalex.org/W6774521036","https://openalex.org/W6790433712"],"related_works":["https://openalex.org/W4303044088","https://openalex.org/W1486916474","https://openalex.org/W2049055139","https://openalex.org/W2140769824","https://openalex.org/W2569549435","https://openalex.org/W96881443","https://openalex.org/W115413730","https://openalex.org/W2148600103","https://openalex.org/W2091348864","https://openalex.org/W2032348095"],"abstract_inverted_index":{"We":[0,85,99],"propose":[1],"a":[2,22,56,69,107],"novel":[3],"constrained":[4],"reinforcement":[5],"learning":[6,27],"method":[7],"for":[8],"finding":[9],"optimal":[10],"policies":[11],"in":[12,42,106],"Markov":[13],"Decision":[14],"Processes":[15],"while":[16],"satisfying":[17],"temporal":[18],"logic":[19],"constraints":[20],"with":[21],"desired":[23],"probability":[24,74],"throughout":[25],"the":[26,36,40,73,80,90,96,103,111,123],"process.":[28],"An":[29],"automata-theoretic":[30],"approach":[31,64],"is":[32,46,65,113,125],"proposed":[33,63,97,104],"to":[34,51,114,126,131],"ensure":[35],"probabilistic":[37,91],"satisfaction":[38,54,77,93],"of":[39,60,75],"constraint":[41,53,76,92,112],"each":[43],"episode,":[44],"which":[45],"different":[47],"from":[48],"penalizing":[49],"violations":[50],"achieve":[52],"after":[55],"sufficiently":[57],"large":[58],"number":[59],"episodes.":[61],"The":[62],"based":[66],"on":[67,72,89],"computing":[68],"lower":[70],"bound":[71],"and":[78,119,122],"adjusting":[79],"exploration":[81],"behavior":[82],"as":[83],"needed.":[84],"present":[86],"theoretical":[87],"results":[88],"achieved":[94],"by":[95],"approach.":[98],"also":[100],"numerically":[101],"demonstrate":[102],"idea":[105],"drone":[108],"scenario,":[109],"where":[110],"perform":[115,133],"periodically":[116],"arriving":[117],"pick-up":[118],"delivery":[120],"tasks":[121],"objective":[124],"fly":[127],"over":[128],"high-reward":[129],"zones":[130],"simultaneously":[132],"aerial":[134],"monitoring.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}