{"id":"https://openalex.org/W6911903467","doi":"https://doi.org/10.5281/zenodo.15489871","title":"Average Reward Reinforcement Learning for Omega-Regular and Mean-Payoff Objectives","display_name":"Average Reward Reinforcement Learning for Omega-Regular and Mean-Payoff Objectives","publication_year":2025,"publication_date":"2025-05-22","ids":{"openalex":"https://openalex.org/W6911903467","doi":"https://doi.org/10.5281/zenodo.15489871"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.15489871","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15489871","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.15489871","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kazemi, Milad","orcid":"https://orcid.org/0000-0003-2716-2758"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kazemi, Milad","raw_affiliation_strings":["King's College London"],"raw_orcid":"https://orcid.org/0000-0003-2716-2758","affiliations":[{"raw_affiliation_string":"King's College London","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Perez, Mateo","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"]},{"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":"Perez, Mateo","raw_affiliation_strings":["University of Colorado Boulder"],"raw_orcid":"https://orcid.org/0000-0003-4220-3212","affiliations":[{"raw_affiliation_string":"University of Colorado Boulder","institution_ids":["https://openalex.org/I2802236040","https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":null,"display_name":"SOMENZI, FABIO","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"]},{"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":"SOMENZI, FABIO","raw_affiliation_strings":["University of Colorado Boulder"],"raw_orcid":"https://orcid.org/0000-0002-2085-2003","affiliations":[{"raw_affiliation_string":"University of Colorado Boulder","institution_ids":["https://openalex.org/I2802236040","https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Soudjani, Sadegh","orcid":"https://orcid.org/0000-0003-1922-6678"},"institutions":[{"id":"https://openalex.org/I4210121786","display_name":"Max Planck Institute for Software Systems","ror":"https://ror.org/02pe2kf23","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210121786"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Soudjani, Sadegh","raw_affiliation_strings":["Max Planck Institute for Software Systems"],"raw_orcid":"https://orcid.org/0000-0003-1922-6678","affiliations":[{"raw_affiliation_string":"Max Planck Institute for Software Systems","institution_ids":["https://openalex.org/I4210121786"]}]},{"author_position":"middle","author":{"id":null,"display_name":"trivedi, ashutosh","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":"trivedi, ashutosh","raw_affiliation_strings":["University of Colorado Boulder"],"raw_orcid":"https://orcid.org/0000-0001-9346-0126","affiliations":[{"raw_affiliation_string":"University of Colorado Boulder","institution_ids":["https://openalex.org/I2802236040","https://openalex.org/I188538660"]}]},{"author_position":"last","author":{"id":null,"display_name":"Velasquez, Alvaro","orcid":"https://orcid.org/0000-0001-6757-105X"},"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":"Velasquez, Alvaro","raw_affiliation_strings":["University of Colorado Boulder"],"raw_orcid":"https://orcid.org/0000-0001-6757-105X","affiliations":[{"raw_affiliation_string":"University of Colorado Boulder","institution_ids":["https://openalex.org/I2802236040","https://openalex.org/I188538660"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6485000252723694},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5415999889373779},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4016999900341034},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.28360000252723694},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.2745000123977661}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6485000252723694},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5415999889373779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4726000130176544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43779999017715454},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.31189998984336853},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28459998965263367},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.25679999589920044},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25130000710487366},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.15489871","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15489871","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.5281/zenodo.15489871","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15489871","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"implementation":[1],"and":[2,15],"the":[3,7],"case":[4],"studies":[5],"for":[6,13],"paper":[8],"'Average":[9],"Reward":[10],"Reinforcement":[11],"Learning":[12],"Omega-Regular":[14],"Mean-Payoff":[16],"Objectives'":[17]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
