{"id":"https://openalex.org/W2579018619","doi":"https://doi.org/10.1109/ispacs.2016.7824674","title":"Multi-agent Q-learning for autonomous D2D communication","display_name":"Multi-agent Q-learning for autonomous D2D communication","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2579018619","doi":"https://doi.org/10.1109/ispacs.2016.7824674","mag":"2579018619"},"language":"en","primary_location":{"id":"doi:10.1109/ispacs.2016.7824674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispacs.2016.7824674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020666619","display_name":"Alia Asheralieva","orcid":"https://orcid.org/0000-0002-4430-5928"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Alia Asheralieva","raw_affiliation_strings":["Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084006463","display_name":"Yoshikazu Miyanaga","orcid":"https://orcid.org/0000-0002-2795-2234"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshikazu Miyanaga","raw_affiliation_strings":["Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020666619"],"corresponding_institution_ids":["https://openalex.org/I205349734"],"apc_list":null,"apc_paid":null,"fwci":2.3626,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.90447454,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"4","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10579","display_name":"Cognitive Radio Networks and Spectrum Sensing","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7103624939918518},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.46601465344429016},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3553706407546997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3220914602279663},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.19938841462135315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7103624939918518},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.46601465344429016},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3553706407546997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3220914602279663},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.19938841462135315}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ispacs.2016.7824674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispacs.2016.7824674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/25919677","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"mag:2753468861","is_oa":false,"landing_page_url":"http://jglobal.jst.go.jp/en/public/20090422/201702255724139075","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/25919677","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W609261231","https://openalex.org/W1544971848","https://openalex.org/W1893483932","https://openalex.org/W1894378508","https://openalex.org/W1928747060","https://openalex.org/W1982597307","https://openalex.org/W2025356004","https://openalex.org/W2055506820","https://openalex.org/W2061641373","https://openalex.org/W2097498347","https://openalex.org/W2120846115","https://openalex.org/W2147600250","https://openalex.org/W2152835608","https://openalex.org/W2164637474","https://openalex.org/W2275900826","https://openalex.org/W2301521007","https://openalex.org/W2336485934","https://openalex.org/W2345024087","https://openalex.org/W2483325812","https://openalex.org/W4214717370","https://openalex.org/W6674705169","https://openalex.org/W6678168664","https://openalex.org/W6684470913"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"This":[0,31],"paper":[1],"is":[2,18,33],"devoted":[3],"to":[4,19,24],"autonomous":[5],"device-to-device":[6],"(D2D)":[7],"communication":[8],"in":[9,60,107],"cellular":[10],"networks.":[11],"The":[12],"aim":[13],"of":[14,54,69,100,130],"each":[15,58],"D2D":[16],"pair":[17],"maximize":[20],"its":[21,70,105],"throughput":[22,77],"subject":[23],"the":[25,41,50,75,82,94,98,120],"minimum":[26],"signal-to-interference-plus-noise":[27],"ratio":[28],"(SINR)":[29],"constraints.":[30],"problem":[32],"represented":[34],"by":[35,81],"a":[36,64,88,108,123,127],"stochastic":[37],"non-cooperative":[38],"game":[39,62],"where":[40],"players":[42],"(D2D":[43],"pairs)":[44],"have":[45],"no":[46],"prior":[47],"information":[48],"on":[49,74,93],"availability":[51],"and":[52,78,103],"quality":[53],"selected":[55],"channels.":[56],"Therefore,":[57],"player":[59],"this":[61],"becomes":[63],"\u201clearner\u201d":[65],"which":[66],"explores":[67],"all":[68],"possible":[71],"strategies":[72,99],"based":[73,92],"locally-observed":[76],"state":[79],"(defined":[80],"channel":[83],"quality).":[84],"Consequently,":[85],"we":[86],"propose":[87],"multi-agent":[89],"Q-learning":[90],"algorithm":[91,121],"players'":[95],"\u201cbeliefs\u201d":[96],"about":[97],"their":[101],"counterparts":[102],"show":[104],"implementation":[106],"Long":[109],"Term":[110],"Evolution":[111],"-":[112],"Advanced":[113],"(LTE-A)":[114],"network.":[115],"As":[116],"follows":[117],"from":[118],"simulations,":[119],"achieves":[122],"near-optimal":[124],"performance":[125],"after":[126],"small":[128],"number":[129],"iterations.":[131]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}