{"id":"https://openalex.org/W2944639720","doi":"https://doi.org/10.1145/3313149.3313369","title":"Limit reachability for model-free reinforcement learning of \u03c9-regular objectives","display_name":"Limit reachability for model-free reinforcement learning of \u03c9-regular objectives","publication_year":2019,"publication_date":"2019-04-15","ids":{"openalex":"https://openalex.org/W2944639720","doi":"https://doi.org/10.1145/3313149.3313369","mag":"2944639720"},"language":"en","primary_location":{"id":"doi:10.1145/3313149.3313369","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3313149.3313369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifth International Workshop on Symbolic-Numeric methods for Reasoning about CPS and IoT","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/A5030417706","display_name":"Ernst Moritz Hahn","orcid":"https://orcid.org/0000-0002-9348-7684"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ernst Moritz Hahn","raw_affiliation_strings":["Queen's University Belfast"],"affiliations":[{"raw_affiliation_string":"Queen's University Belfast","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084221298","display_name":"Mateo Perez","orcid":"https://orcid.org/0000-0003-4220-3212"},"institutions":[{"id":"https://openalex.org/I2802236040","display_name":"University of Colorado System","ror":"https://ror.org/00jc20583","country_code":"US","type":"education","lineage":["https://openalex.org/I2802236040"]},{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mateo Perez","raw_affiliation_strings":["University of Colorado Boulder"],"affiliations":[{"raw_affiliation_string":"University of Colorado Boulder","institution_ids":["https://openalex.org/I2802236040","https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041836791","display_name":"Sven Schewe","orcid":"https://orcid.org/0000-0002-9093-9518"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sven Schewe","raw_affiliation_strings":["University of Liverpool"],"affiliations":[{"raw_affiliation_string":"University of Liverpool","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077549627","display_name":"Fabio Somenzi","orcid":"https://orcid.org/0000-0002-2085-2003"},"institutions":[{"id":"https://openalex.org/I2802236040","display_name":"University of Colorado System","ror":"https://ror.org/00jc20583","country_code":"US","type":"education","lineage":["https://openalex.org/I2802236040"]},{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fabio Somenzi","raw_affiliation_strings":["University of Colorado Boulder"],"affiliations":[{"raw_affiliation_string":"University of Colorado Boulder","institution_ids":["https://openalex.org/I2802236040","https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020302140","display_name":"Ashutosh Trivedi","orcid":"https://orcid.org/0000-0001-9346-0126"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]},{"id":"https://openalex.org/I2802236040","display_name":"University of Colorado System","ror":"https://ror.org/00jc20583","country_code":"US","type":"education","lineage":["https://openalex.org/I2802236040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashutosh Trivedi","raw_affiliation_strings":["University of Colorado Boulder"],"affiliations":[{"raw_affiliation_string":"University of Colorado Boulder","institution_ids":["https://openalex.org/I2802236040","https://openalex.org/I188538660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001234060","display_name":"Dominik Wojtczak","orcid":"https://orcid.org/0000-0001-5560-0546"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dominik Wojtczak","raw_affiliation_strings":["University of Liverpool"],"affiliations":[{"raw_affiliation_string":"University of Liverpool","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5030417706"],"corresponding_institution_ids":["https://openalex.org/I126231945"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07088705,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9990000128746033,"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/T10142","display_name":"Formal Methods in Verification","score":0.9990000128746033,"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":0.9973000288009644,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9754999876022339,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.903942883014679},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.827437162399292},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7944458723068237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6126648187637329},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.6101424694061279},{"id":"https://openalex.org/keywords/constructive","display_name":"Constructive","score":0.6078045964241028},{"id":"https://openalex.org/keywords/learning-automata","display_name":"Learning automata","score":0.5862471461296082},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.52517169713974},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5065709352493286},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4761262536048889},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4215162396430969},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4188942313194275},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3574288487434387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35238391160964966},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2946857213973999}],"concepts":[{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.903942883014679},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.827437162399292},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7944458723068237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6126648187637329},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.6101424694061279},{"id":"https://openalex.org/C2778701210","wikidata":"https://www.wikidata.org/wiki/Q28130034","display_name":"Constructive","level":3,"score":0.6078045964241028},{"id":"https://openalex.org/C2776807809","wikidata":"https://www.wikidata.org/wiki/Q6510160","display_name":"Learning automata","level":3,"score":0.5862471461296082},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.52517169713974},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5065709352493286},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4761262536048889},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4215162396430969},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4188942313194275},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3574288487434387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35238391160964966},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2946857213973999},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3313149.3313369","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3313149.3313369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifth International Workshop on Symbolic-Numeric methods for Reasoning about CPS and IoT","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G3787831247","display_name":null,"funder_award_id":"61761136011 and 61532019","funder_id":"https://openalex.org/F4320335595","funder_display_name":"National Natural Science Foundation of China-Yunnan Joint Fund"},{"id":"https://openalex.org/G6898068357","display_name":null,"funder_award_id":"EP/M027287/1 and EP/P020909/1.","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7815803692","display_name":null,"funder_award_id":"EP/P020909/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8525945721","display_name":null,"funder_award_id":"EP/M027287/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320335595","display_name":"National Natural Science Foundation of China-Yunnan Joint Fund","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W1498432697","https://openalex.org/W1556387789","https://openalex.org/W1972203711","https://openalex.org/W2129670787","https://openalex.org/W2131600418","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2165161585","https://openalex.org/W2173248099","https://openalex.org/W2787259794","https://openalex.org/W2895196950","https://openalex.org/W2962806365","https://openalex.org/W2964161785","https://openalex.org/W6682849425"],"related_works":["https://openalex.org/W2130664212","https://openalex.org/W1554767603","https://openalex.org/W1565729639","https://openalex.org/W4382045631","https://openalex.org/W2032445854","https://openalex.org/W2489338148","https://openalex.org/W2124961391","https://openalex.org/W576785828","https://openalex.org/W1545451257","https://openalex.org/W4388511637"],"abstract_inverted_index":{"We":[0,15],"have":[1],"recently":[2],"solved":[3],"the":[4,21,46,50,61,75,95,98],"model-free":[5],"reinforcement":[6,87],"learning":[7,37,88],"of":[8,24,48,57,63,97],"\u03c9-regular":[9,25,64],"objectives":[10,26],"for":[11],"Markov":[12,99],"decision":[13,100],"processes.":[14],"outline":[16],"our":[17,58],"constructive":[18],"reduction":[19],"from":[20,94],"almost-sure":[22,29],"satisfaction":[23],"to":[27,36,39,83,90],"an":[28,41],"reachability":[30],"problem,":[31],"and":[32],"extend":[33],"this":[34],"technique":[35,59],"how":[38],"control":[40],"unknown":[42],"model":[43],"so":[44],"that":[45],"chance":[47],"satisfying":[49],"objective":[51],"is":[52,60],"maximized.":[53],"A":[54],"key":[55],"feature":[56],"compilation":[62],"properties":[65],"into":[66],"limit-deterministic":[67],"B\u00fcchi":[68],"automata,":[69],"which":[70],"sidesteps":[71],"difficulties":[72],"associated":[73],"with":[74],"traditional":[76],"Rabin":[77],"automata.":[78],"Our":[79],"approach":[80],"allows":[81],"us":[82],"apply":[84],"model-free,":[85],"off-the-shelf":[86],"algorithms":[89],"compute":[91],"optimal":[92],"strategies":[93],"observations":[96],"process.":[101]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
