{"id":"https://openalex.org/W2969147069","doi":"https://doi.org/10.1109/access.2019.2935255","title":"An Improved Sarsa($\\lambda$ ) Reinforcement Learning Algorithm for Wireless Communication Systems","display_name":"An Improved Sarsa($\\lambda$ ) Reinforcement Learning Algorithm for Wireless Communication Systems","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2969147069","doi":"https://doi.org/10.1109/access.2019.2935255","mag":"2969147069"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2935255","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2935255","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08798608.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08798608.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041881347","display_name":"Hao Jiang","orcid":"https://orcid.org/0000-0002-6757-4231"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Jiang","raw_affiliation_strings":["School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-6757-4231","affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020880105","display_name":"Renjie Gui","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renjie Gui","raw_affiliation_strings":["National Mobile Communications Research Laboratory, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Mobile Communications Research Laboratory, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457678","display_name":"Zhe Chen","orcid":"https://orcid.org/0000-0002-2919-4481"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Chen","raw_affiliation_strings":["School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044817346","display_name":"Liang Wu","orcid":"https://orcid.org/0000-0001-9054-0155"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Wu","raw_affiliation_strings":["National Mobile Communications Research Laboratory, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9054-0155","affiliations":[{"raw_affiliation_string":"National Mobile Communications Research Laboratory, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056446385","display_name":"Jian Dang","orcid":"https://orcid.org/0000-0002-4199-9645"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Dang","raw_affiliation_strings":["National Mobile Communications Research Laboratory, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-4199-9645","affiliations":[{"raw_affiliation_string":"National Mobile Communications Research Laboratory, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101978223","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0002-1885-2274"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":["School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1750,"currency":"USD","value_usd":1750},"apc_paid":{"value":1750,"currency":"USD","value_usd":1750},"fwci":1.8619,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.88973759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"7","issue":null,"first_page":"115418","last_page":"115427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.994700014591217,"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"}},"topics":[{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.994700014591217,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9937999844551086,"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/T12131","display_name":"Wireless Signal Modulation Classification","score":0.9901999831199646,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7805752754211426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7510327100753784},{"id":"https://openalex.org/keywords/lambda","display_name":"Lambda","score":0.5351686477661133},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.477155864238739},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3516649603843689},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3276040256023407},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13549759984016418}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7805752754211426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7510327100753784},{"id":"https://openalex.org/C2778113609","wikidata":"https://www.wikidata.org/wiki/Q10897","display_name":"Lambda","level":2,"score":0.5351686477661133},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.477155864238739},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3516649603843689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3276040256023407},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13549759984016418},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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":2,"locations":[{"id":"doi:10.1109/access.2019.2935255","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2935255","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08798608.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6f908aeec50a4173b82996c2e6f43998","is_oa":true,"landing_page_url":"https://doaj.org/article/6f908aeec50a4173b82996c2e6f43998","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 115418-115427 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2935255","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2935255","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08798608.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G5186004268","display_name":null,"funder_award_id":"2018YF-B1801101","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6854474914","display_name":"\u7279\u6b8a\u573a\u666fMIMO\u4fe1\u9053\u5efa\u6a21\u53ca\u5176\u7a00\u758f\u4f30\u8ba1\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61771248","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320324849","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19"},{"id":"https://openalex.org/F4320327518","display_name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335990","display_name":"Startup Foundation for Introducing Talent of Nanjing University of Information Science and Technology","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2969147069.pdf","grobid_xml":"https://content.openalex.org/works/W2969147069.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2068768759","https://openalex.org/W2068923975","https://openalex.org/W2084779837","https://openalex.org/W2090861152","https://openalex.org/W2099706679","https://openalex.org/W2137680104","https://openalex.org/W2145339207","https://openalex.org/W2514879101","https://openalex.org/W2767359317","https://openalex.org/W2896666719","https://openalex.org/W2896890603","https://openalex.org/W2909191390","https://openalex.org/W2914738388","https://openalex.org/W2916238263","https://openalex.org/W2921429506","https://openalex.org/W2941435312","https://openalex.org/W2960246799","https://openalex.org/W2962834214","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2951695430","https://openalex.org/W4403749602","https://openalex.org/W2073681303","https://openalex.org/W4300891849","https://openalex.org/W2318687609","https://openalex.org/W91590591","https://openalex.org/W1525257472","https://openalex.org/W4306904969","https://openalex.org/W159772521"],"abstract_inverted_index":{"In":[0,32],"this":[1],"article,":[2],"we":[3,34],"provide":[4],"a":[5,88,105],"novel":[6],"improved":[7],"model-free":[8],"temporal-difference":[9],"control":[10],"algorithm,":[11],"namely,":[12],"Expected":[13,95],"Sarsa($\\lambda":[14,98],"$),":[15],"using":[16,39],"the":[17,36,40,55,66,77,81,101,116],"average":[18,41],"value":[19,43],"as":[20],"an":[21,112,125],"update":[22,37],"target":[23,38],"and":[24,49,70,87,97,118,127],"introducing":[25],"eligibility":[26,51],"traces":[27,52],"in":[28,100],"wireless":[29,120],"communication":[30,121,135],"networks.":[31,122,136],"particular,":[33],"construct":[35],"action":[42,61],"of":[44,58,83,104],"all":[45],"possible":[46],"successive":[47],"actions,":[48],"apply":[50],"to":[53,130],"record":[54],"historical":[56],"access":[57],"every":[59],"state":[60],"pair,":[62],"which":[63],"greatly":[64],"improve":[65],"model\u2019s":[67],"convergence":[68],"property":[69],"learning":[71,85],"efficiency.":[72],"Numerical":[73],"results":[74],"demonstrate":[75],"that":[76],"proposed":[78],"algorithm":[79],"has":[80],"advantage":[82],"high":[84],"efficiency":[86],"higher":[89],"learning-rate":[90],"tolerance":[91],"range":[92],"than$Q$Learning,":[93],"Sarsa,":[94,96],"$)":[99],"tabular":[102],"case":[103],"finite":[106],"Markov":[107],"decision":[108],"process,":[109],"thereby":[110],"providing":[111],"efficient":[113,126],"solution":[114,129],"for":[115],"study":[117],"design":[119,131],"This":[123],"provides":[124],"effective":[128],"further":[132],"artificial":[133],"intelligent":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2019-08-22T00:00:00"}
