{"id":"https://openalex.org/W3044168612","doi":"https://doi.org/10.23919/wiopt47501.2019.9144097","title":"Beyond Max-weight Scheduling: A Reinforcement Learning-based Approach","display_name":"Beyond Max-weight Scheduling: A Reinforcement Learning-based Approach","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W3044168612","doi":"https://doi.org/10.23919/wiopt47501.2019.9144097","mag":"3044168612"},"language":"en","primary_location":{"id":"doi:10.23919/wiopt47501.2019.9144097","is_oa":false,"landing_page_url":"https://doi.org/10.23919/wiopt47501.2019.9144097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOPT)","raw_type":"proceedings-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/A5106761258","display_name":"Jeongmin Bae","orcid":"https://orcid.org/0000-0002-7430-0183"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongmin Bae","raw_affiliation_strings":["Department of Electrical Engineering, KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, KAIST","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318495","display_name":"Joohyun Lee","orcid":"https://orcid.org/0000-0002-7698-1568"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joohyun Lee","raw_affiliation_strings":["Division of Electrical Engineering, Hanyang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Electrical Engineering, Hanyang University","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102076010","display_name":"Song Chong","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Song Chong","raw_affiliation_strings":["Department of Electrical Engineering, KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, KAIST","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4876,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8505676,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","score":0.9987999796867371,"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/T11409","display_name":"Advanced Wireless Network Optimization","score":0.9977999925613403,"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":0.9944000244140625,"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":0.9152763485908508},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7956114411354065},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5776293873786926},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5112206935882568},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4908609986305237},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3718137741088867},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35977351665496826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3344707787036896},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07817342877388}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9152763485908508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7956114411354065},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5776293873786926},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5112206935882568},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4908609986305237},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3718137741088867},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35977351665496826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3344707787036896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07817342877388}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/wiopt47501.2019.9144097","is_oa":false,"landing_page_url":"https://doi.org/10.23919/wiopt47501.2019.9144097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOPT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1518931405","https://openalex.org/W1966208686","https://openalex.org/W1984181498","https://openalex.org/W1986389067","https://openalex.org/W2029631728","https://openalex.org/W2030544250","https://openalex.org/W2101242010","https://openalex.org/W2105177639","https://openalex.org/W2109341366","https://openalex.org/W2135663206","https://openalex.org/W2137152139","https://openalex.org/W2145339207","https://openalex.org/W2165131254","https://openalex.org/W2173655337","https://openalex.org/W2327545172","https://openalex.org/W2553188523","https://openalex.org/W2562947506","https://openalex.org/W2596760110","https://openalex.org/W2741401130","https://openalex.org/W2756144809","https://openalex.org/W2784320632","https://openalex.org/W2963549123","https://openalex.org/W3044168612","https://openalex.org/W4253201987","https://openalex.org/W4297972233","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6675043515","https://openalex.org/W6729964979","https://openalex.org/W6747875335"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W2742483371","https://openalex.org/W3038962357","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3099153698","https://openalex.org/W3087814763","https://openalex.org/W2025663273"],"abstract_inverted_index":{"As":[0],"network":[1,15,23,44,62],"architecture":[2],"becomes":[3,18],"complex":[4],"and":[5,52,79],"the":[6,11,28,61,113],"user":[7],"requirement":[8],"gets":[9],"diverse,":[10],"role":[12],"of":[13,107],"efficient":[14],"resource":[16],"management":[17],"more":[19],"important.":[20],"However,":[21],"existing":[22],"scheduling":[24,45],"algorithms":[25],"such":[26],"as":[27,65],"max-weight":[29,114],"algorithm":[30,46,84,103,115],"suffer":[31],"from":[32],"poor":[33],"delay":[34,105],"performance.":[35],"In":[36],"this":[37,56],"paper,":[38],"we":[39,58,70,99],"present":[40],"a":[41,72,81,93],"reinforcement":[42,82],"learning-based":[43],"that":[47,87,101],"achieves":[48],"both":[49],"optimal":[50],"throughput":[51],"low":[53],"delay.":[54],"To":[55],"end,":[57],"first":[59],"formulate":[60],"optimization":[63],"problem":[64],"an":[66],"MDP":[67],"problem.":[68],"Then":[69],"introduce":[71],"new":[73],"state-action":[74],"value":[75],"function":[76],"called":[77,85],"W-function":[78],"develop":[80],"learning":[83,94],"W-Learning":[86],"guarantees":[88],"little":[89],"performance":[90],"loss":[91],"during":[92],"process.":[95],"Finally,":[96],"via":[97],"simulation,":[98],"verify":[100],"our":[102],"shows":[104],"reduction":[106],"up":[108],"to":[109,112],"40.8%":[110],"compared":[111],"over":[116],"various":[117],"scenarios.":[118]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}