{"id":"https://openalex.org/W4205515766","doi":"https://doi.org/10.1109/mcom.111.2000949","title":"Improving Data-Driven Reinforcement Learning in Wireless IoT Systems Using Domain Knowledge","display_name":"Improving Data-Driven Reinforcement Learning in Wireless IoT Systems Using Domain Knowledge","publication_year":2021,"publication_date":"2021-11-01","ids":{"openalex":"https://openalex.org/W4205515766","doi":"https://doi.org/10.1109/mcom.111.2000949"},"language":"en","primary_location":{"id":"doi:10.1109/mcom.111.2000949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mcom.111.2000949","pdf_url":null,"source":{"id":"https://openalex.org/S158797327","display_name":"IEEE Communications Magazine","issn_l":"0163-6804","issn":["0163-6804","1558-1896"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Communications Magazine","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/A5047238501","display_name":"Nicholas Mastronarde","orcid":"https://orcid.org/0000-0002-8474-7237"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Mastronarde","raw_affiliation_strings":["University of Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020888445","display_name":"Nikhilesh Sharma","orcid":"https://orcid.org/0000-0003-2011-063X"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikhilesh Sharma","raw_affiliation_strings":["University of Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084068339","display_name":"Jacob Chakareski","orcid":"https://orcid.org/0000-0003-2428-9518"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Chakareski","raw_affiliation_strings":["New Jersey Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology","institution_ids":["https://openalex.org/I118118575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.16796748,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"59","issue":"11","first_page":"95","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11392","display_name":"Energy Harvesting in Wireless Networks","score":0.9998000264167786,"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":0.9998000264167786,"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/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.9994999766349792,"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/T13553","display_name":"Age of Information Optimization","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.8923051357269287},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8406288623809814},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.71746426820755},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.5293717384338379},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.48038655519485474},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.4599098563194275},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44905003905296326},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44659796357154846},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4416748881340027},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4112766683101654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3764464855194092},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08567681908607483}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8923051357269287},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8406288623809814},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.71746426820755},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.5293717384338379},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.48038655519485474},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.4599098563194275},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44905003905296326},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44659796357154846},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4416748881340027},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4112766683101654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3764464855194092},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08567681908607483},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mcom.111.2000949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mcom.111.2000949","pdf_url":null,"source":{"id":"https://openalex.org/S158797327","display_name":"IEEE Communications Magazine","issn_l":"0163-6804","issn":["0163-6804","1558-1896"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Communications Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1383633145","display_name":null,"funder_award_id":"ECCS-1711335,CCF-1528030,ECCS-1711592,CNS-1836909,CNS-1821875,CNS-1836909","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1518931405","https://openalex.org/W2107726111","https://openalex.org/W2123117904","https://openalex.org/W2138717292","https://openalex.org/W2216654401","https://openalex.org/W2956490995","https://openalex.org/W2963083073","https://openalex.org/W2986907531","https://openalex.org/W3006109470","https://openalex.org/W3039578309","https://openalex.org/W3048386157","https://openalex.org/W3103738405","https://openalex.org/W3133472358","https://openalex.org/W4297729153","https://openalex.org/W6739506316","https://openalex.org/W6751872652","https://openalex.org/W6785764103"],"related_works":["https://openalex.org/W2264067234","https://openalex.org/W3124243301","https://openalex.org/W1571502335","https://openalex.org/W1589409554","https://openalex.org/W2759038785","https://openalex.org/W2172232600","https://openalex.org/W3123876860","https://openalex.org/W3124172198","https://openalex.org/W2142633247","https://openalex.org/W2768698792"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,78],"(RL)":[2],"algorithms":[3,50,66],"are":[4],"purely":[5],"data-driven":[6,64],"and":[7,26,109],"do":[8],"not":[9],"leverage":[10],"any":[11],"domain":[12],"knowledge":[13,89],"about":[14,90],"the":[15,18,21,45,56,77,91],"nature":[16],"of":[17,39,98],"available":[19],"actions,":[20],"system's":[22],"state":[23],"transition":[24],"dynamics,":[25],"its":[27],"cost/reward":[28],"function.":[29],"This":[30],"severely":[31],"penalizes":[32],"their":[33,53],"ability":[34],"to":[35,44,95,113],"meet":[36],"critical":[37],"requirements":[38],"emerging":[40],"wireless":[41],"applications,":[42],"due":[43],"inefficiency":[46],"with":[47,55,88],"which":[48],"these":[49],"learn":[51],"from":[52],"interactions":[54],"environment.":[57],"In":[58],"this":[59],"article,":[60],"we":[61],"describe":[62],"how":[63],"RL":[65,115],"can":[67],"be":[68],"improved":[69],"by":[70],"systematically":[71],"integrating":[72],"basic":[73],"system":[74,94],"models":[75],"into":[76],"process.":[79],"Our":[80],"proposed":[81],"approach":[82],"uses":[83],"real-time":[84],"data":[85],"in":[86,101],"conjunction":[87],"underlying":[92],"communication":[93],"achieve":[96],"orders":[97],"magnitude":[99],"improvement":[100],"key":[102],"performance":[103],"metrics,":[104],"such":[105],"as":[106],"convergence":[107],"speed":[108],"compute/memory":[110],"complexity,":[111],"relative":[112],"well-established":[114],"benchmarks.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}