{"id":"https://openalex.org/W4387872840","doi":"https://doi.org/10.1109/iccworkshops57953.2023.10283540","title":"On Reward Shaping Methods in Deep Reinforcement Learning for Radio Resource Management in Wireless Networks","display_name":"On Reward Shaping Methods in Deep Reinforcement Learning for Radio Resource Management in Wireless Networks","publication_year":2023,"publication_date":"2023-05-28","ids":{"openalex":"https://openalex.org/W4387872840","doi":"https://doi.org/10.1109/iccworkshops57953.2023.10283540"},"language":"en","primary_location":{"id":"doi:10.1109/iccworkshops57953.2023.10283540","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iccworkshops57953.2023.10283540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5093111872","display_name":"Amna Kopic","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Amna Kopic","raw_affiliation_strings":["Institute for Communication Technologies and Embedded Systems, RWTH Aachen University,Aachen,Germany","Institute for Communication Technologies and Embedded Systems, RWTH Aachen University, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Communication Technologies and Embedded Systems, RWTH Aachen University,Aachen,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Institute for Communication Technologies and Embedded Systems, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005607654","display_name":"Kenan Turbi\u0107","orcid":"https://orcid.org/0000-0002-1951-9916"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kenan Turbic","raw_affiliation_strings":["Institute for Communication Technologies and Embedded Systems, RWTH Aachen University,Aachen,Germany","Institute for Communication Technologies and Embedded Systems, RWTH Aachen University, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Communication Technologies and Embedded Systems, RWTH Aachen University,Aachen,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Institute for Communication Technologies and Embedded Systems, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026448728","display_name":"Haris Gacanin","orcid":"https://orcid.org/0000-0003-3168-8883"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Haris Gacanin","raw_affiliation_strings":["Institute for Communication Technologies and Embedded Systems, RWTH Aachen University,Aachen,Germany","Institute for Communication Technologies and Embedded Systems, RWTH Aachen University, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Communication Technologies and Embedded Systems, RWTH Aachen University,Aachen,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Institute for Communication Technologies and Embedded Systems, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":1.6246,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82481511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1020","last_page":"1025"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11392","display_name":"Energy Harvesting in Wireless Networks","score":0.9933000206947327,"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/T11392","display_name":"Energy Harvesting in Wireless Networks","score":0.9933000206947327,"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/T12131","display_name":"Wireless Signal Modulation Classification","score":0.9850999712944031,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.974399983882904,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7783185243606567},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.673711359500885},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.6584095358848572},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6395456790924072},{"id":"https://openalex.org/keywords/orthogonal-frequency-division-multiplexing","display_name":"Orthogonal frequency-division multiplexing","score":0.6054182052612305},{"id":"https://openalex.org/keywords/base-station","display_name":"Base station","score":0.5365239381790161},{"id":"https://openalex.org/keywords/wireless-network","display_name":"Wireless network","score":0.5074333548545837},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.5064531564712524},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.48428624868392944},{"id":"https://openalex.org/keywords/symbol","display_name":"Symbol (formal)","score":0.461760014295578},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.42709124088287354},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.41423943638801575},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4108509421348572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3640996813774109},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33384013175964355},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32937151193618774},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.24774101376533508},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.19929808378219604},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17400938272476196},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14504602551460266}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7783185243606567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.673711359500885},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.6584095358848572},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6395456790924072},{"id":"https://openalex.org/C40409654","wikidata":"https://www.wikidata.org/wiki/Q375889","display_name":"Orthogonal frequency-division multiplexing","level":3,"score":0.6054182052612305},{"id":"https://openalex.org/C68649174","wikidata":"https://www.wikidata.org/wiki/Q1379116","display_name":"Base station","level":2,"score":0.5365239381790161},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.5074333548545837},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.5064531564712524},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.48428624868392944},{"id":"https://openalex.org/C134400042","wikidata":"https://www.wikidata.org/wiki/Q2372244","display_name":"Symbol (formal)","level":2,"score":0.461760014295578},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.42709124088287354},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.41423943638801575},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4108509421348572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3640996813774109},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33384013175964355},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32937151193618774},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.24774101376533508},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.19929808378219604},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17400938272476196},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14504602551460266},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccworkshops57953.2023.10283540","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iccworkshops57953.2023.10283540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Communications Workshops (ICC Workshops)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2170475648","https://openalex.org/W2784277076","https://openalex.org/W2886374543","https://openalex.org/W2887286578","https://openalex.org/W2937571395","https://openalex.org/W2956537170","https://openalex.org/W2963000651","https://openalex.org/W2963864421","https://openalex.org/W2969195240","https://openalex.org/W2991856612","https://openalex.org/W2998578058","https://openalex.org/W3036160090","https://openalex.org/W3059813204","https://openalex.org/W3089324491","https://openalex.org/W3109884127","https://openalex.org/W3182816986","https://openalex.org/W6677916085","https://openalex.org/W6684921986","https://openalex.org/W6783236513"],"related_works":["https://openalex.org/W2124130287","https://openalex.org/W2923452570","https://openalex.org/W206598027","https://openalex.org/W2978610750","https://openalex.org/W2022931285","https://openalex.org/W1589966275","https://openalex.org/W2086872282","https://openalex.org/W2137789903","https://openalex.org/W1592324786","https://openalex.org/W2534160330"],"abstract_inverted_index":{"This":[0],"paper":[1],"provides":[2],"a":[3,31,37,116],"comprehensive":[4],"study":[5],"on":[6],"the":[7,46,56,61,76,81,96,101,106],"learning":[8,43,85],"models'":[9],"power":[10,18,57,78,102],"violation,":[11],"sum-rate":[12,62],"performance":[13],"while":[14,59,74],"taking":[15],"into":[16],"consideration":[17],"constraint,":[19],"and":[20,27,41],"computational":[21],"efficiency":[22],"in":[23],"terms":[24],"of":[25,80],"training":[26],"execution":[28],"times":[29],"over":[30],"dynamic":[32],"wireless":[33],"channel.":[34],"We":[35],"propose":[36],"reward":[38],"shaping":[39],"method":[40],"modify":[42],"models":[44,86],"with":[45],"output":[47],"scaling":[48],"strategy":[49],"to":[50,53,72,89,95],"enforce":[51],"them":[52],"fully":[54],"respect":[55],"constraints":[58],"optimizing":[60],"performance.":[63],"The":[64],"proposed":[65],"approach":[66],"reaches":[67],"close-to-optimal":[68],"accuracy,":[69],"i.e.,":[70],"up":[71],"99.15%,":[73],"satisfying":[75],"predefined":[77],"constraint":[79],"base":[82],"station.":[83],"Moreover,":[84],"are":[87],"shown":[88],"be":[90],"more":[91],"computationally":[92],"efficient":[93],"compared":[94],"traditional":[97],"algorithm.":[98],"However,":[99],"solving":[100],"allocation":[103],"problem":[104],"within":[105],"Orthogonal":[107],"Frequency":[108],"Division":[109],"Multiplexing":[110],"(OFDM)":[111],"symbol":[112],"duration":[113],"of$16.7\\mu":[114],"\\mathrm{s}$is":[115],"remaining":[117],"challenge.":[118]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
