{"id":"https://openalex.org/W4414405037","doi":"https://doi.org/10.1109/iccworkshops67674.2025.11162180","title":"Rethinking the Reward Design for DRL in Mobile Communication Systems with Generative Diffusion Models","display_name":"Rethinking the Reward Design for DRL in Mobile Communication Systems with Generative Diffusion Models","publication_year":2025,"publication_date":"2025-06-08","ids":{"openalex":"https://openalex.org/W4414405037","doi":"https://doi.org/10.1109/iccworkshops67674.2025.11162180"},"language":"en","primary_location":{"id":"doi:10.1109/iccworkshops67674.2025.11162180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccworkshops67674.2025.11162180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Communications Workshops (ICC Workshops)","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/A5022208421","display_name":"Xinren Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xinren Zhang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Internet of Things Thrust,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Internet of Things Thrust,Guangzhou,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101596215","display_name":"Shang Chen","orcid":"https://orcid.org/0000-0003-1718-8428"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chen Shang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Internet of Things Thrust,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Internet of Things Thrust,Guangzhou,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061063770","display_name":"Jiadong Yu","orcid":"https://orcid.org/0000-0003-4773-5402"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiadong Yu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou),Internet of Things Thrust,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou),Internet of Things Thrust,Guangzhou,China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I200769079"],"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":"250","last_page":"255"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10651","display_name":"IPv6, Mobility, Handover, Networks, Security","score":0.986299991607666,"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/T10651","display_name":"IPv6, Mobility, Handover, Networks, Security","score":0.986299991607666,"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/T13999","display_name":"Digital Rights Management and Security","score":0.9787999987602234,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9682999849319458,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social 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":0.7545999884605408},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.623199999332428},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5752000212669373},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5436000227928162},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5067999958992004},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5029000043869019},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.42100000381469727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7620000243186951},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7545999884605408},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.623199999332428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6104999780654907},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5752000212669373},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5436000227928162},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5067999958992004},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.42100000381469727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.397599995136261},{"id":"https://openalex.org/C95491727","wikidata":"https://www.wikidata.org/wiki/Q992968","display_name":"Mobile telephony","level":3,"score":0.3865000009536743},{"id":"https://openalex.org/C158156997","wikidata":"https://www.wikidata.org/wiki/Q1416645","display_name":"Models of communication","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccworkshops67674.2025.11162180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccworkshops67674.2025.11162180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Communications Workshops (ICC Workshops)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2746553466","https://openalex.org/W2963020121","https://openalex.org/W4297964528","https://openalex.org/W4323644407","https://openalex.org/W4381785965","https://openalex.org/W4396817538","https://openalex.org/W4400188025","https://openalex.org/W4400679915","https://openalex.org/W4409991959"],"related_works":[],"abstract_inverted_index":{"When":[0],"applying":[1],"deep":[2,94],"reinforcement":[3],"learning":[4,20],"(DRL)":[5],"in":[6,34,71,82],"mobile":[7,89],"communication":[8,90],"systems,":[9],"an":[10,68],"appropriate":[11],"reward":[12,32,46,136],"function":[13,33,47],"can":[14],"effectively":[15],"guide":[16],"the":[17,21,35,42,45,57,74,83,100,107,115,131,148],"agent":[18],"towards":[19],"optimal":[22],"action.":[23],"However,":[24],"it":[25],"is":[26,48,80],"challenging":[27],"to":[28,73],"accurately":[29],"design":[30,137],"a":[31,86],"dynamic":[36],"and":[37,111,143],"uncertain":[38],"systems.":[39],"To":[40],"address":[41],"limitations":[43],"when":[44],"unknown,":[49],"suboptimal,":[50],"or":[51],"involves":[52],"multiple":[53],"objectives,":[54],"we":[55],"propose":[56],"Generative":[58],"Diffusion":[59],"Model-based":[60],"Reward":[61],"Exploration":[62],"DRL":[63,102],"(GRE-DRL)":[64],"framework,":[65],"which":[66],"includes":[67],"exploration":[69],"module":[70],"addition":[72],"designed":[75],"rewards.":[76],"The":[77],"proposed":[78,132],"framework":[79],"evaluated":[81],"context":[84],"of":[85,109,150],"full-duplex":[87],"(FD)":[88],"system":[91],"based":[92],"on":[93,105],"deterministic":[95],"policy":[96],"gradient":[97],"(DDPG)":[98],"as":[99],"fundamental":[101],"approach,":[103],"focusing":[104],"improving":[106],"performance":[108],"beam-forming":[110],"power":[112],"allocation":[113],"through":[114],"specific":[116],"generative":[117,123],"artificial":[118],"intelligence":[119],"(GenAI)":[120],"models":[121,125],"(i.e.,":[122],"diffusion":[124],"(GDM)).":[126],"Numerical":[127],"results":[128],"demonstrate":[129],"that":[130],"algorithm":[133],"outperforms":[134],"conventional":[135],"methods":[138],"by":[139],"achieving":[140],"faster":[141],"convergence":[142],"reducing":[144],"computation":[145],"consumption,":[146],"proving":[147],"effectiveness":[149],"our":[151],"approach.":[152]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}