{"id":"https://openalex.org/W4382024748","doi":"https://doi.org/10.1145/3605950","title":"Multi-objective \u03c9-Regular Reinforcement Learning","display_name":"Multi-objective \u03c9-Regular Reinforcement Learning","publication_year":2023,"publication_date":"2023-06-26","ids":{"openalex":"https://openalex.org/W4382024748","doi":"https://doi.org/10.1145/3605950"},"language":"en","primary_location":{"id":"doi:10.1145/3605950","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3605950","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605950","source":{"id":"https://openalex.org/S128250343","display_name":"Formal Aspects of Computing","issn_l":"0934-5043","issn":["0934-5043","1433-299X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Formal Aspects of Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3605950","any_repository_has_fulltext":true},"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/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ernst Moritz Hahn","raw_affiliation_strings":["University of Twente, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-9348-7684","affiliations":[{"raw_affiliation_string":"University of Twente, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"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/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, USA"],"raw_orcid":"https://orcid.org/0000-0003-4220-3212","affiliations":[{"raw_affiliation_string":"University of Colorado Boulder, USA","institution_ids":["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, UK"],"raw_orcid":"https://orcid.org/0000-0002-9093-9518","affiliations":[{"raw_affiliation_string":"University of Liverpool, UK","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/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, USA"],"raw_orcid":"https://orcid.org/0000-0002-2085-2003","affiliations":[{"raw_affiliation_string":"University of Colorado Boulder, USA","institution_ids":["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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashutosh Trivedi","raw_affiliation_strings":["University of Colorado Boulder, USA"],"raw_orcid":"https://orcid.org/0000-0001-9346-0126","affiliations":[{"raw_affiliation_string":"University of Colorado Boulder, USA","institution_ids":["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, UK"],"raw_orcid":"https://orcid.org/0000-0001-5560-0546","affiliations":[{"raw_affiliation_string":"University of Liverpool, UK","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4856,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69854335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"35","issue":"2","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9950000047683716,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7968159317970276},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6980651617050171},{"id":"https://openalex.org/keywords/theory-of-computation","display_name":"Theory of computation","score":0.6536946892738342},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.613662600517273},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5235773324966431},{"id":"https://openalex.org/keywords/lexicographical-order","display_name":"Lexicographical order","score":0.519925057888031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4446921646595001},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41344618797302246},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40988612174987793},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.31651240587234497},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2871091663837433},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15642112493515015},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07921236753463745}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7968159317970276},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6980651617050171},{"id":"https://openalex.org/C24858836","wikidata":"https://www.wikidata.org/wiki/Q844718","display_name":"Theory of computation","level":2,"score":0.6536946892738342},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.613662600517273},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5235773324966431},{"id":"https://openalex.org/C159254197","wikidata":"https://www.wikidata.org/wiki/Q1144915","display_name":"Lexicographical order","level":2,"score":0.519925057888031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4446921646595001},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41344618797302246},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40988612174987793},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.31651240587234497},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2871091663837433},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15642112493515015},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07921236753463745},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3605950","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3605950","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605950","source":{"id":"https://openalex.org/S128250343","display_name":"Formal Aspects of Computing","issn_l":"0934-5043","issn":["0934-5043","1433-299X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Formal Aspects of Computing","raw_type":"journal-article"},{"id":"pmh:oai:ris.utwente.nl:publications/80812bae-76c3-4689-a395-b45dd45cfaf4","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/80812bae-76c3-4689-a395-b45dd45cfaf4","pdf_url":"https://ris.utwente.nl/ws/files/370193024/3605950.pdf","source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hahn, E M, Perez, M, Schewe, S, Somenzi, F, Trivedi, A & Wojtczak, D 2023, 'Multi-objective \u03c9-Regular Reinforcement Learning', Formal aspects of computing, vol. 35, no. 2, 12. https://doi.org/10.1145/3605950","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/80812bae-76c3-4689-a395-b45dd45cfaf4","is_oa":true,"landing_page_url":"https://research.utwente.nl/files/370193024/3605950.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hahn, E M, Perez, M, Schewe, S, Somenzi, F, Trivedi, A & Wojtczak, D 2023, 'Multi-objective \u03c9-Regular Reinforcement Learning', Formal aspects of computing, vol. 35, no. 2, 12. https://doi.org/10.1145/3605950","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1145/3605950","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3605950","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605950","source":{"id":"https://openalex.org/S128250343","display_name":"Formal Aspects of Computing","issn_l":"0934-5043","issn":["0934-5043","1433-299X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Formal Aspects of Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1170451441","display_name":"Below the Branches of Universal Trees","funder_award_id":"EP/X017796/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1364539167","display_name":null,"funder_award_id":"956123","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3795356847","display_name":"Synthesising Game Solving Techniques","funder_award_id":"101032464","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4684090925","display_name":null,"funder_award_id":"EP/P020909/1 and EP/X017796/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4968910455","display_name":"Solving Parity Games in Theory and Practice","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/G6332253830","display_name":"SHF: Small: Omega-Regular Objectives for Model-Free Reinforcement Learning","funder_award_id":"2009022","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G655446035","display_name":null,"funder_award_id":"EP/X017796/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"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/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G842143413","display_name":"CAREER: Reinforcement Learning for Recursive Markov Decision Processes and Beyond","funder_award_id":"2146563","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8491077145","display_name":null,"funder_award_id":"864075","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382024748.pdf","grobid_xml":"https://content.openalex.org/works/W4382024748.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W163688550","https://openalex.org/W986424706","https://openalex.org/W1458771408","https://openalex.org/W1498432697","https://openalex.org/W1502195915","https://openalex.org/W1584965098","https://openalex.org/W1786377004","https://openalex.org/W1845972764","https://openalex.org/W1862398452","https://openalex.org/W1965692465","https://openalex.org/W1987725948","https://openalex.org/W1999766763","https://openalex.org/W2020293036","https://openalex.org/W2050233777","https://openalex.org/W2058192020","https://openalex.org/W2063511957","https://openalex.org/W2078268196","https://openalex.org/W2093916942","https://openalex.org/W2102660061","https://openalex.org/W2116001481","https://openalex.org/W2116085129","https://openalex.org/W2128480458","https://openalex.org/W2145339207","https://openalex.org/W2148252761","https://openalex.org/W2165686945","https://openalex.org/W2186820913","https://openalex.org/W2257979135","https://openalex.org/W2288565641","https://openalex.org/W2334782222","https://openalex.org/W2521432080","https://openalex.org/W2531563875","https://openalex.org/W2555847713","https://openalex.org/W2582998992","https://openalex.org/W2611254621","https://openalex.org/W2615497679","https://openalex.org/W2924278904","https://openalex.org/W2949594712","https://openalex.org/W2963204502","https://openalex.org/W2982316857","https://openalex.org/W3011120880","https://openalex.org/W3012026310","https://openalex.org/W3046820103","https://openalex.org/W3090827750","https://openalex.org/W3091816494","https://openalex.org/W3101221300","https://openalex.org/W3122403361","https://openalex.org/W3141484263","https://openalex.org/W4211246281","https://openalex.org/W4237456806","https://openalex.org/W4298163977"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2315999538"],"abstract_inverted_index":{"The":[0],"expanding":[1],"role":[2],"of":[3,24,88,90,99,151,186],"reinforcement":[4,175],"learning":[5,19,176,191],"(RL)":[6],"in":[7,116,172],"safety-critical":[8],"system":[9],"design":[10],"has":[11],"promoted":[12],"\u03c9-automata":[13],"as":[14],"a":[15,91,100,131,138,173],"way":[16],"to":[17,47,96,112,137,164],"express":[18,48],"requirements\u2014often":[20],"non-Markovian\u2014with":[21],"greater":[22],"ease":[23],"expression":[25],"and":[26,69,108,126,159,180],"interpretation":[27],"than":[28],"scalar":[29,64,139],"reward":[30,140,147],"signals.":[31],"However,":[32],"real-world":[33],"sequential":[34],"decision":[35,61,76,118],"making":[36],"situations":[37],"often":[38],"involve":[39],"multiple,":[40],"potentially":[41],"conflicting,":[42],"objectives.":[43],"Two":[44],"dominant":[45],"approaches":[46],"relative":[49],"preferences":[50],"over":[51,81],"multiple":[52,121,134],"objectives":[53,83,123,136,154],"are:":[54],"(1)":[55],"weighted":[56,125],"preference":[57,72],",":[58,73,179],"where":[59,74],"the":[60,75,82,153,156,170],"maker":[62,77],"provides":[63,78],"weights":[65],"for":[66],"various":[67],"objectives,":[68],"(2)":[70],"lexicographic":[71,127],"an":[79,183],"order":[80],"such":[84],"that":[85,142],"any":[86,97],"amount":[87,98],"satisfaction":[89],"higher-ordered":[92],"objective":[93],"is":[94,143],"preferable":[95],"lower-ordered":[101],"one.":[102],"In":[103],"this":[104],"article,":[105],"we":[106,181],"study":[107],"develop":[109],"RL":[110],"algorithms":[111],"compute":[113],"optimal":[114,165],"strategies":[115],"Markov":[117],"processes":[119],"against":[120],"\u03c9-regular":[122,135],"under":[124,155],"preferences.":[128],"We":[129,167],"provide":[130],"translation":[132],"from":[133],"signal":[141],"both":[144],"faithful":[145],"(maximising":[146],"means":[148],"maximising":[149],"probability":[150],"achieving":[152],"corresponding":[157],"preference)":[158],"effective":[160],"(RL":[161],"quickly":[162],"converges":[163],"strategies).":[166],"have":[168],"implemented":[169],"translations":[171],"formal":[174],"tool,":[177],"Mungojerrie":[178],"present":[182],"experimental":[184],"evaluation":[185],"our":[187],"technique":[188],"on":[189],"benchmark":[190],"problems.":[192]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}