{"id":"https://openalex.org/W3166026547","doi":"https://doi.org/10.1109/tmc.2021.3085206","title":"Make Smart Decisions Faster: Deciding D2D Resource Allocation via Stackelberg Game Guided Multi-Agent Deep Reinforcement Learning","display_name":"Make Smart Decisions Faster: Deciding D2D Resource Allocation via Stackelberg Game Guided Multi-Agent Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-06-01","ids":{"openalex":"https://openalex.org/W3166026547","doi":"https://doi.org/10.1109/tmc.2021.3085206","mag":"3166026547"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2021.3085206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2021.3085206","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-article"},"type":"article","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/A5020681881","display_name":"Dian Shi","orcid":"https://orcid.org/0000-0002-9219-5516"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dian Shi","raw_affiliation_strings":["Electrical and Computer Engineering Department, University of Houston, Houston, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-9219-5516","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420723","display_name":"Liang Li","orcid":"https://orcid.org/0000-0003-3369-3571"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["School of Cyber Engineering, Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-3369-3571","affiliations":[{"raw_affiliation_string":"School of Cyber Engineering, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016337773","display_name":"Tomoaki Ohtsuki","orcid":"https://orcid.org/0000-0003-3961-1426"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoaki Ohtsuki","raw_affiliation_strings":["Department of Information and Computer Science, Keio University, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3961-1426","affiliations":[{"raw_affiliation_string":"Department of Information and Computer Science, Keio University, Tokyo, Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047722991","display_name":"Miao Pan","orcid":"https://orcid.org/0000-0003-2138-4413"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miao Pan","raw_affiliation_strings":["Electrical and Computer Engineering Department, University of Houston, Houston, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-2138-4413","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063667378","display_name":"Zhu Han","orcid":"https://orcid.org/0000-0002-6606-5822"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]},{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Zhu Han","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Houston, Houston, TX, USA","Department of Computer Science and Engineering, Kyung Hee University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-6606-5822","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Kyung Hee University, Seoul, South Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042307561","display_name":"H. Vincent Poor","orcid":"https://orcid.org/0000-0002-2062-131X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Vincent Poor","raw_affiliation_strings":["Department of Electrical Engineering, Princeton University, Princeton, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-2062-131X","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7372,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.93846298,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"21","issue":"12","first_page":"4426","last_page":"4438"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11392","display_name":"Energy Harvesting in Wireless Networks","score":0.995199978351593,"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"}},{"id":"https://openalex.org/T10579","display_name":"Cognitive Radio Networks and Spectrum Sensing","score":0.9929999709129333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stackelberg-competition","display_name":"Stackelberg competition","score":0.9679526090621948},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8388429284095764},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7862255573272705},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.7461055517196655},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.511167585849762},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.5070693492889404},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.49698570370674133},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46988725662231445},{"id":"https://openalex.org/keywords/power-control","display_name":"Power control","score":0.4328700006008148},{"id":"https://openalex.org/keywords/channel-allocation-schemes","display_name":"Channel allocation schemes","score":0.4162786304950714},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3603171706199646},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3425212800502777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2724725604057312},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.2565419673919678},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.22054997086524963},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14404547214508057}],"concepts":[{"id":"https://openalex.org/C199510392","wikidata":"https://www.wikidata.org/wiki/Q1184602","display_name":"Stackelberg competition","level":2,"score":0.9679526090621948},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8388429284095764},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7862255573272705},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.7461055517196655},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.511167585849762},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.5070693492889404},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.49698570370674133},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46988725662231445},{"id":"https://openalex.org/C56685638","wikidata":"https://www.wikidata.org/wiki/Q2300474","display_name":"Power control","level":3,"score":0.4328700006008148},{"id":"https://openalex.org/C114237682","wikidata":"https://www.wikidata.org/wiki/Q5072483","display_name":"Channel allocation schemes","level":3,"score":0.4162786304950714},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3603171706199646},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3425212800502777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2724725604057312},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.2565419673919678},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.22054997086524963},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14404547214508057},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","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},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmc.2021.3085206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2021.3085206","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1086481652","display_name":"Wireless Communications using Signal Processing Design based on Conditional Mutual Information Norm Adaptive Quantization and Deep Learning","funder_award_id":"19H02142","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G2453749321","display_name":null,"funder_award_id":"CCF-1908308","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G3094966838","display_name":null,"funder_award_id":"CNS-1801925","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G3325918464","display_name":null,"funder_award_id":"CNS-1731424","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G3554202431","display_name":null,"funder_award_id":"EARS-1839818","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G3904951113","display_name":null,"funder_award_id":"CNS-1717454","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G7758496514","display_name":null,"funder_award_id":"CNS-1702850","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G8133724804","display_name":null,"funder_award_id":"CNS-2029569","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W361876","https://openalex.org/W1502765764","https://openalex.org/W1513468570","https://openalex.org/W1519783625","https://openalex.org/W1990557017","https://openalex.org/W2009171710","https://openalex.org/W2054767147","https://openalex.org/W2076807755","https://openalex.org/W2089415692","https://openalex.org/W2113271807","https://openalex.org/W2120846115","https://openalex.org/W2145339207","https://openalex.org/W2164854244","https://openalex.org/W2331789166","https://openalex.org/W2604698298","https://openalex.org/W2761465998","https://openalex.org/W2767359317","https://openalex.org/W2785315072","https://openalex.org/W2807817153","https://openalex.org/W2891517080","https://openalex.org/W2892023691","https://openalex.org/W2895341959","https://openalex.org/W2896161835","https://openalex.org/W2904455790","https://openalex.org/W2914154006","https://openalex.org/W2922490142","https://openalex.org/W2946053445","https://openalex.org/W2963000651","https://openalex.org/W2963396074","https://openalex.org/W2963605646","https://openalex.org/W2963836746","https://openalex.org/W2963864421","https://openalex.org/W2966510405","https://openalex.org/W2968764495","https://openalex.org/W2969195240","https://openalex.org/W2969658074","https://openalex.org/W2983557232","https://openalex.org/W2987209137","https://openalex.org/W2997072274","https://openalex.org/W2997499903","https://openalex.org/W2998709521","https://openalex.org/W2999146029","https://openalex.org/W3013198216","https://openalex.org/W3091004758","https://openalex.org/W3093651199","https://openalex.org/W3098133185","https://openalex.org/W4211166364","https://openalex.org/W4299802797","https://openalex.org/W6600018571","https://openalex.org/W6630520071","https://openalex.org/W6631168379","https://openalex.org/W6663743460","https://openalex.org/W6678168664","https://openalex.org/W6684921986","https://openalex.org/W6738796088","https://openalex.org/W6747941106"],"related_works":["https://openalex.org/W2117352219","https://openalex.org/W2923452570","https://openalex.org/W2408103561","https://openalex.org/W206598027","https://openalex.org/W2978610750","https://openalex.org/W86175780","https://openalex.org/W1589966275","https://openalex.org/W2181493188","https://openalex.org/W2164591489","https://openalex.org/W2153007255"],"abstract_inverted_index":{"Device-to-Device":[0],"(D2D)":[1],"communication":[2,53],"enabling":[3],"direct":[4],"data":[5],"transmission":[6],"between":[7],"two":[8],"mobile":[9],"users":[10,74],"has":[11],"emerged":[12],"as":[13],"a":[14,51,60,85,92],"vital":[15],"component":[16],"for":[17,32],"5G":[18],"cellular":[19],"networks":[20,38],"to":[21,40,75,97,164],"improve":[22],"spectrum":[23],"utilization":[24],"and":[25,80,134,199],"enhance":[26],"system":[27],"capacity.":[28],"A":[29],"critical":[30],"issue":[31],"realizing":[33],"these":[34],"benefits":[35],"in":[36,50,84,111,139,172,191],"D2D-enabled":[37],"is":[39],"properly":[41],"allocate":[42],"radio":[43],"resources":[44],"while":[45],"coordinating":[46],"the":[47,99,108,112,116,119,130,141,145,166,186,194],"co-channel":[48],"interference":[49],"time-varying":[52],"environment.":[54],"In":[55,88],"this":[56],"paper,":[57],"we":[58,90],"propose":[59],"Stackelberg":[61,94,113,120],"game":[62],"(SG)":[63],"guided":[64],"multi-agent":[65],"deep":[66],"reinforcement":[67],"learning":[68,100],"(MADRL)":[69],"approach,":[70],"which":[71,102],"allows":[72],"D2D":[73,153],"make":[76],"smart":[77],"power":[78],"control":[79],"channel":[81,197],"allocation":[82,155,176],"decisions":[83],"distributed":[86,158],"manner.":[87],"particular,":[89],"define":[91],"crucial":[93],"Q-value":[95],"(ST-Q)":[96],"guide":[98],"direction,":[101],"can":[103,150],"be":[104],"calculated":[105],"based":[106,189],"on":[107],"equilibrium":[109],"achieved":[110],"game.":[114],"With":[115],"guidance":[117],"of":[118,168,193],"equilibrium,":[121],"our":[122,169,183],"approach":[123,190],"converges":[124],"faster":[125],"with":[126,157],"fewer":[127],"iterations":[128],"than":[129],"general":[131,187],"MADRL":[132,188],"method":[133,184],"thereby":[135],"exhibits":[136],"better":[137],"performance":[138],"handling":[140],"network":[142],"dynamics.":[143],"After":[144],"initial":[146],"training,":[147],"each":[148],"agent":[149],"infer":[151],"timely":[152,174],"resource":[154,175],"strategies":[156],"execution.":[159],"Extensive":[160],"simulations":[161],"are":[162],"conducted":[163],"validate":[165],"efficacy":[167],"proposed":[170],"scheme":[171],"developing":[173],"strategies.":[177],"The":[178],"results":[179],"also":[180],"show":[181],"that":[182],"outperforms":[185],"terms":[192],"average":[195],"utility,":[196],"capacity,":[198],"training":[200],"time.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}