{"id":"https://openalex.org/W4387172155","doi":"https://doi.org/10.3233/faia230368","title":"Omega-Regular Reward Machines","display_name":"Omega-Regular Reward Machines","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387172155","doi":"https://doi.org/10.3233/faia230368"},"language":"en","primary_location":{"id":"doi:10.3233/faia230368","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230368","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230368","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230368","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, NL"],"raw_orcid":"https://orcid.org/0000-0002-9348-7684","affiliations":[{"raw_affiliation_string":"University of Twente, NL","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":true,"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":["https://openalex.org/A5020302140"],"corresponding_institution_ids":["https://openalex.org/I188538660"],"apc_list":null,"apc_paid":null,"fwci":0.5054,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68024723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9800999760627747,"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":0.9800999760627747,"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/T11178","display_name":"Receptor Mechanisms and Signaling","score":0.9736999869346619,"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/rotation-formalisms-in-three-dimensions","display_name":"Rotation formalisms in three dimensions","score":0.7403813600540161},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.719813883304596},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7186813354492188},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.6740190386772156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4761536121368408},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40278366208076477},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13043859601020813}],"concepts":[{"id":"https://openalex.org/C171018156","wikidata":"https://www.wikidata.org/wiki/Q7370306","display_name":"Rotation formalisms in three dimensions","level":2,"score":0.7403813600540161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.719813883304596},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7186813354492188},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.6740190386772156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4761536121368408},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40278366208076477},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13043859601020813},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3233/faia230368","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230368","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230368","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:ris.utwente.nl:publications/338c1941-7752-4a3e-a71e-32604eae58a0","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/338c1941-7752-4a3e-a71e-32604eae58a0","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Hahn, E M, Perez, M, Schewe, S, Somenzi, F, Trivedi, A & Wojtczak, D 2023, Omega-Regular Reward Machines. in K Gal, K Gal, A Nowe, G J Nalepa, R Fairstein & R Radulescu (eds), ECAI 2023 - 26th European Conference on Artificial Intelligence, including 12th Conference on Prestigious Applications of Intelligent Systems, PAIS 2023 - Proceedings. Frontiers in Artificial Intelligence and Applications, vol. 372, IOS, pp. 972-979, 26th European Conference on Artificial Intelligence, ECAI 2023, Krak\u00f3w, Poland, 30/09/23. https://doi.org/10.3233/FAIA230368","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:ris.utwente.nl:openaire/338c1941-7752-4a3e-a71e-32604eae58a0","is_oa":true,"landing_page_url":"https://research.utwente.nl/files/359416897/FAIA-372-FAIA230368.pdf","pdf_url":"https://ris.utwente.nl/ws/files/359416897/FAIA-372-FAIA230368.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":null,"license_id":null,"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, Omega-Regular Reward Machines. in K Gal, K Gal, A Nowe, G J Nalepa, R Fairstein & R Radulescu (eds), ECAI 2023 - 26th European Conference on Artificial Intelligence, including 12th Conference on Prestigious Applications of Intelligent Systems, PAIS 2023 - Proceedings. Frontiers in Artificial Intelligence and Applications, vol. 372, IOS, pp. 972-979, 26th European Conference on Artificial Intelligence, ECAI 2023, Krak\u00f3w, Poland, 30/09/23. https://doi.org/10.3233/FAIA230368","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.3233/faia230368","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230368","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230368","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"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/G4683697052","display_name":"TRUSTED: SecuriTy SummaRies for SecUre SofTwarE Development","funder_award_id":"EP/X03688X/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/G7553838803","display_name":null,"funder_award_id":"EP/X03688X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"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"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4387172155.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1491322982","https://openalex.org/W1498432697","https://openalex.org/W1765717155","https://openalex.org/W2020293036","https://openalex.org/W2078151802","https://openalex.org/W2804948070","https://openalex.org/W2895196950","https://openalex.org/W2966537673","https://openalex.org/W2972520119","https://openalex.org/W2972744417","https://openalex.org/W2993025150","https://openalex.org/W2997022832","https://openalex.org/W3011250830","https://openalex.org/W3082540285","https://openalex.org/W3090827750","https://openalex.org/W3091816494","https://openalex.org/W3092156990","https://openalex.org/W3141484263","https://openalex.org/W3213488095","https://openalex.org/W4210504149","https://openalex.org/W4285603402","https://openalex.org/W4288726006","https://openalex.org/W4312983743","https://openalex.org/W4366677748"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W4306674287","https://openalex.org/W3111983280","https://openalex.org/W4319083788"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,32],"(RL)":[2],"is":[3,19],"a":[4,43,92],"powerful":[5],"approach":[6],"for":[7,61,88],"training":[8],"agents":[9],"to":[10,21,57,80,96],"perform":[11],"tasks,":[12],"but":[13],"designing":[14],"an":[15,82],"appropriate":[16],"reward":[17,46,71,75,86,102],"mechanism":[18,87],"critical":[20],"its":[22],"success.":[23],"However,":[24],"in":[25],"many":[26],"cases,":[27],"the":[28,31,36,39,106,109],"complexity":[29],"of":[30,38,108],"objectives":[33],"goes":[34],"beyond":[35],"capabilities":[37],"Markovian":[40],"assumption,":[41],"necessitating":[42],"more":[44],"sophisticated":[45],"mechanism.":[47],"Reward":[48],"machines":[49,76,103],"and":[50,63,84,104],"\u03c9-regular":[51,70,78,101],"languages":[52,79],"are":[53],"two":[54],"formalisms":[55],"used":[56],"express":[58],"non-Markovian":[59],"rewards":[60],"quantitative":[62],"qualitative":[64],"objectives,":[65],"respectively.":[66],"This":[67],"paper":[68],"introduces":[69],"machines,":[72],"which":[73],"integrate":[74],"with":[77],"enable":[81],"expressive":[83],"effective":[85],"RL.":[89],"We":[90],"present":[91],"model-free":[93],"RL":[94],"algorithm":[95,111],"compute":[97],"\u03b5-optimal":[98],"strategies":[99],"against":[100],"evaluate":[105],"effectiveness":[107],"proposed":[110],"through":[112],"experiments.":[113]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}