{"id":"https://openalex.org/W4403487837","doi":"https://doi.org/10.3233/faia240676","title":"Multi-Agent Reinforcement Learning for Alternating-Time Logic","display_name":"Multi-Agent Reinforcement Learning for Alternating-Time Logic","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403487837","doi":"https://doi.org/10.3233/faia240676"},"language":"en","primary_location":{"id":"doi:10.3233/faia240676","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240676","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240676","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/FAIA240676","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/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":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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37385715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9280999898910522,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9280999898910522,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.5925731062889099},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4934908151626587},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43493586778640747},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3541710376739502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3423922061920166},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.13892683386802673}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5925731062889099},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4934908151626587},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43493586778640747},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3541710376739502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3423922061920166},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13892683386802673}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia240676","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240676","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240676","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:openaire/5db0a2c8-1b46-421f-9b66-fda5022916bc","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/5db0a2c8-1b46-421f-9b66-fda5022916bc","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 2024, Multi-Agent Reinforcement Learning for Alternating-Time Logic. in U Endriss, F S Melo, K Bach, A Bugarin-Diz, J M Alonso-Moral, S Barro & F Heintz (eds), ECAI 2024 - 27th European Conference on Artificial Intelligence, Including 13th Conference on Prestigious Applications of Intelligent Systems, PAIS 2024, Proceedings. Frontiers in Artificial Intelligence and Applications, vol. 392, IOS, pp. 1680-1687, 27th European Conference on Artificial Intelligence, ECAI 2024, Santiago de Compostela, Spain, 19/10/24. https://doi.org/10.3233/FAIA240676","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.3233/faia240676","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240676","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240676","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7799999713897705}],"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/G4313942165","display_name":"Games for Good","funder_award_id":"EP/X042596/1","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/G4999239871","display_name":"Reinforcement Learning for Finite Horizons (ReLeaF)","funder_award_id":"EP/X021513/1","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/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"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":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403487837.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Alternating-time":[0],"temporal":[1,31],"logic":[2,7],"(ATL)":[3],"extends":[4],"branching":[5],"time":[6],"by":[8,20,64],"enabling":[9],"quantification":[10],"over":[11],"paths":[12],"that":[13],"result":[14],"from":[15,46],"the":[16,27,76,95],"strategic":[17],"choices":[18],"made":[19],"multiple":[21],"agents":[22],"in":[23],"various":[24],"coalitions":[25],"within":[26],"system.":[28],"While":[29],"classical":[30],"logics":[32],"express":[33,40],"properties":[34,41],"of":[35,42,80,97,120,130,145],"\u201cclosed\u201d":[36],"systems,":[37],"ATL":[38,115,135,147],"can":[39],"\u201copen\u201d":[43],"systems":[44,113],"resulting":[45],"interactions":[47,74],"among":[48],"several":[49],"agents.":[50],"Reinforcement":[51],"learning":[52,61],"(RL)":[53],"is":[54,123],"a":[55,65,124,142],"sampling-based":[56],"approach":[57,105],"to":[58,110],"decision-making":[59],"where":[60],"agents,":[62],"guided":[63],"scalar":[66,85],"reward":[67],"function,":[68],"discover":[69],"optimal":[70],"policies":[71],"through":[72],"repeated":[73],"with":[75],"environment.":[77],"The":[78,117],"challenge":[79],"translating":[81],"high-level":[82],"objectives":[83],"into":[84],"rewards":[86],"for":[87,106,127],"RL":[88,99,109,129],"has":[89],"garnered":[90],"increased":[91],"interest,":[92],"particularly":[93],"following":[94],"success":[96],"model-free":[98,108,128],"algorithms.":[100],"This":[101],"paper":[102,122],"presents":[103],"an":[104],"deploying":[107],"verify":[111],"multi-agent":[112],"against":[114],"specifications.":[116],"key":[118],"contribution":[119],"this":[121],"verification":[125],"procedure":[126],"quantitative":[131],"and":[132],"non-nested":[133,146],"classic":[134],"properties,":[136],"based":[137],"on":[138,141],"Q-learning,":[139],"demonstrated":[140],"natural":[143],"subclass":[144],"formulas.":[148]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}