{"id":"https://openalex.org/W2587718442","doi":"https://doi.org/10.1109/smc.2016.7844563","title":"Temporal and agent abstractions in multiagent reinforcement learning","display_name":"Temporal and agent abstractions in multiagent reinforcement learning","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2587718442","doi":"https://doi.org/10.1109/smc.2016.7844563","mag":"2587718442"},"language":"en","primary_location":{"id":"doi:10.1109/smc.2016.7844563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc.2016.7844563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5012398433","display_name":"Danielle M. Clement","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danielle M. Clement","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047174917","display_name":"Manfred Huber","orcid":"https://orcid.org/0009-0007-0294-9147"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manfred Huber","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"002190","last_page":"002195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T11182","display_name":"Auction Theory and Applications","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9825999736785889,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8547085523605347},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7747176885604858},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.7346089482307434},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.6379621624946594},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43117856979370117},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.4124816060066223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.396401047706604},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.35358208417892456},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.15339669585227966},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0874650776386261}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8547085523605347},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7747176885604858},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.7346089482307434},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.6379621624946594},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43117856979370117},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.4124816060066223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.396401047706604},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35358208417892456},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.15339669585227966},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0874650776386261},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc.2016.7844563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc.2016.7844563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1515436326","https://openalex.org/W1540755814","https://openalex.org/W1851682374","https://openalex.org/W1965332792","https://openalex.org/W1985742288","https://openalex.org/W2005043268","https://openalex.org/W2104641222","https://openalex.org/W2109910161","https://openalex.org/W2112632840","https://openalex.org/W2114199765","https://openalex.org/W2156277419","https://openalex.org/W2162022118","https://openalex.org/W2290743114","https://openalex.org/W2294192315","https://openalex.org/W2399410261","https://openalex.org/W2572491855","https://openalex.org/W3015571647","https://openalex.org/W4237171445","https://openalex.org/W6632237392","https://openalex.org/W6646846885","https://openalex.org/W6676824205","https://openalex.org/W6677068649","https://openalex.org/W6696285106","https://openalex.org/W6697106730","https://openalex.org/W6712484124","https://openalex.org/W6731611783"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2045155990","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4313163053","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474"],"abstract_inverted_index":{"A":[0],"major":[1],"challenge":[2],"in":[3,27,52,108,118],"the":[4,13,19,23,33,37,40,53,64,119],"area":[5],"of":[6,15,25,35,42,55,63,85],"multiagent":[7,73,88],"reinforcement":[8],"learning":[9],"has":[10],"been":[11,58],"addressing":[12],"problem":[14,38],"scale,":[16],"more":[17],"specifically":[18],"fact":[20],"that":[21,97],"increasing":[22],"number":[24],"agents":[26,104],"a":[28,44,83,92,109],"system":[29],"dramatically":[30],"increases":[31],"both":[32],"cost":[34,41],"representing":[36],"and":[39,90],"calculating":[43],"solution.":[45],"In":[46],"single":[47],"agent":[48,95],"systems,":[49,74],"temporal":[50],"abstractions":[51],"form":[54],"options":[56,86,101],"have":[57],"used":[59],"to":[60,77,103,116],"address":[61],"part":[62],"scaling":[65],"problem,":[66],"but":[67],"only":[68],"limited":[69,76],"work":[70],"exists":[71],"for":[72,87,94],"largely":[75],"cooperative":[78],"games.":[79],"This":[80],"paper":[81],"presents":[82],"formalization":[84],"systems":[89],"introduces":[91],"framework":[93],"abstraction":[96],"treats":[98],"coalitions":[99],"executing":[100],"analogously":[102],"with":[105],"policies,":[106],"resulting":[107],"lower-dimensional":[110],"game":[111],"whose":[112],"equilibria":[113,117],"approximately":[114],"correspond":[115],"higher":[120],"dimensional":[121],"game.":[122]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}