{"id":"https://openalex.org/W2546571074","doi":"https://doi.org/10.1145/3005745.3005750","title":"Resource Management with Deep Reinforcement Learning","display_name":"Resource Management with Deep Reinforcement Learning","publication_year":2016,"publication_date":"2016-11-02","ids":{"openalex":"https://openalex.org/W2546571074","doi":"https://doi.org/10.1145/3005745.3005750","mag":"2546571074"},"language":"en","primary_location":{"id":"doi:10.1145/3005745.3005750","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3005745.3005750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM Workshop on Hot Topics in Networks","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/A5004578457","display_name":"Hongzi Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hongzi Mao","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101669323","display_name":"Mohammad Alizadeh","orcid":"https://orcid.org/0000-0002-6650-8961"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Alizadeh","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032872922","display_name":"Ishai Menache","orcid":"https://orcid.org/0000-0002-2540-236X"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ishai Menache","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023881736","display_name":"Srikanth Kandula","orcid":"https://orcid.org/0000-0001-9494-6435"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Srikanth Kandula","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004578457"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":74.1249,"has_fulltext":false,"cited_by_count":1178,"citation_normalized_percentile":{"value":0.99960616,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"56"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9994999766349792,"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/T12288","display_name":"Optimization and Search Problems","score":0.9994999766349792,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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":0.835925817489624},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7977235317230225},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7704629302024841},{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.766663670539856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5803053379058838},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5402234792709351},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.5237338542938232},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4542333781719208},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4033159911632538},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.33036381006240845},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.20071735978126526},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09014818072319031}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.835925817489624},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7977235317230225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7704629302024841},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.766663670539856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5803053379058838},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5402234792709351},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.5237338542938232},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4542333781719208},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4033159911632538},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.33036381006240845},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.20071735978126526},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09014818072319031},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3005745.3005750","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3005745.3005750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM Workshop on Hot Topics in Networks","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":41,"referenced_works":["https://openalex.org/W148964820","https://openalex.org/W1442374986","https://openalex.org/W1515851193","https://openalex.org/W1535431348","https://openalex.org/W1539216098","https://openalex.org/W1585546214","https://openalex.org/W1590675038","https://openalex.org/W1694165248","https://openalex.org/W1757796397","https://openalex.org/W1825077972","https://openalex.org/W1890643295","https://openalex.org/W1941445455","https://openalex.org/W1976944900","https://openalex.org/W1977655452","https://openalex.org/W1982063824","https://openalex.org/W1988975763","https://openalex.org/W1998172110","https://openalex.org/W2022678927","https://openalex.org/W2025549137","https://openalex.org/W2096125134","https://openalex.org/W2105947650","https://openalex.org/W2107726111","https://openalex.org/W2110104287","https://openalex.org/W2114296561","https://openalex.org/W2121863487","https://openalex.org/W2123651102","https://openalex.org/W2133569115","https://openalex.org/W2138309709","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2156666755","https://openalex.org/W2160121678","https://openalex.org/W2163112974","https://openalex.org/W2169209873","https://openalex.org/W2257979135","https://openalex.org/W2271840356","https://openalex.org/W2482797934","https://openalex.org/W2495130909","https://openalex.org/W2949608212","https://openalex.org/W2964043796","https://openalex.org/W4241533337"],"related_works":["https://openalex.org/W3197854638","https://openalex.org/W3140454661","https://openalex.org/W4245029315","https://openalex.org/W1492315459","https://openalex.org/W1512434910","https://openalex.org/W2540910169","https://openalex.org/W3148904318","https://openalex.org/W2139970489","https://openalex.org/W2022803902","https://openalex.org/W2105474389"],"abstract_inverted_index":{"Resource":[0],"management":[1],"problems":[2],"in":[3,29,92],"systems":[4,39],"and":[5,23,86],"networking":[6],"often":[7],"manifest":[8],"as":[9],"difficult":[10],"online":[11],"decision":[12],"making":[13],"tasks":[14,60],"where":[15],"appropriate":[16],"solutions":[17],"depend":[18],"on":[19],"understanding":[20],"the":[21,56],"workload":[22],"environment.":[24],"Inspired":[25],"by":[26],"recent":[27],"advances":[28],"deep":[30],"reinforcement":[31],"learning":[32,67],"for":[33],"AI":[34],"problems,":[35],"we":[36],"consider":[37],"building":[38],"that":[40,54,73,89],"learn":[41],"to":[42,77,81],"manage":[43],"resources":[44],"directly":[45],"from":[46],"experience.":[47],"We":[48],"present":[49],"DeepRM,":[50],"an":[51],"example":[52],"solution":[53],"translates":[55],"problem":[57],"of":[58],"packing":[59],"with":[61],"multiple":[62],"resource":[63],"demands":[64],"into":[65],"a":[66],"problem.":[68],"Our":[69],"initial":[70],"results":[71],"show":[72],"DeepRM":[74],"performs":[75],"comparably":[76],"state-of-the-art":[78],"heuristics,":[79],"adapts":[80],"different":[82],"conditions,":[83],"converges":[84],"quickly,":[85],"learns":[87],"strategies":[88],"are":[90],"sensible":[91],"hindsight.":[93]},"counts_by_year":[{"year":2026,"cited_by_count":23},{"year":2025,"cited_by_count":160},{"year":2024,"cited_by_count":95},{"year":2023,"cited_by_count":131},{"year":2022,"cited_by_count":140},{"year":2021,"cited_by_count":193},{"year":2020,"cited_by_count":185},{"year":2019,"cited_by_count":162},{"year":2018,"cited_by_count":65},{"year":2017,"cited_by_count":24}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}