{"id":"https://openalex.org/W4399376391","doi":"https://doi.org/10.1109/mm.2024.3408719","title":"Practical Online Reinforcement Learning for Microprocessors With Micro-Armed Bandit","display_name":"Practical Online Reinforcement Learning for Microprocessors With Micro-Armed Bandit","publication_year":2024,"publication_date":"2024-06-05","ids":{"openalex":"https://openalex.org/W4399376391","doi":"https://doi.org/10.1109/mm.2024.3408719"},"language":"en","primary_location":{"id":"doi:10.1109/mm.2024.3408719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2024.3408719","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"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 Micro","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/A5034202662","display_name":"Gerasimos Gerogiannis","orcid":"https://orcid.org/0000-0002-7946-2683"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gerasimos Gerogiannis","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055909708","display_name":"Josep Torrellas","orcid":"https://orcid.org/0000-0003-2595-5228"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Josep Torrellas","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034202662"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.516,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66072901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"44","issue":"4","first_page":"80","last_page":"87"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9914000034332275,"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/T10558","display_name":"Advancements in Semiconductor Devices and Circuit Design","score":0.9908999800682068,"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/computer-science","display_name":"Computer science","score":0.8466556072235107},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7532129287719727},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.441133588552475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3500071167945862},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3456214666366577},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3206854462623596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8466556072235107},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7532129287719727},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.441133588552475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3500071167945862},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3456214666366577},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3206854462623596}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mm.2024.3408719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2024.3408719","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"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 Micro","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1570238416","display_name":null,"funder_award_id":"CNS 1763658","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2004457323","display_name":null,"funder_award_id":"CNS 1956007","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4845837577","display_name":null,"funder_award_id":"CCF 2107470","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":13,"referenced_works":["https://openalex.org/W1944301273","https://openalex.org/W2001420671","https://openalex.org/W2039522160","https://openalex.org/W2118532220","https://openalex.org/W2121863487","https://openalex.org/W2930718998","https://openalex.org/W3147501999","https://openalex.org/W3203303453","https://openalex.org/W3205610680","https://openalex.org/W4252076096","https://openalex.org/W4380875466","https://openalex.org/W4389476179","https://openalex.org/W6640648879"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Although":[0],"online":[1,148],"reinforcement":[2],"learning":[3],"(RL)":[4],"has":[5],"shown":[6],"promise":[7],"for":[8,44,91,152],"microarchitecture":[9,68],"decision":[10],"making,":[11],"processor":[12],"vendors":[13],"are":[14,21,42,49,74],"still":[15],"reluctant":[16],"to":[17,59],"adopt":[18],"it.":[19],"There":[20],"two":[22,123],"main":[23],"reasons":[24],"that":[25,96,107,139],"make":[26,147],"RL-based":[27],"solutions":[28],"unattractive.":[29],"First,":[30],"they":[31],"have":[32],"high":[33],"complexity":[34],"and":[35,48,119,128,143],"storage":[36,145],"overhead.":[37],"Second,":[38],"many":[39],"RL":[40,94,118,149],"agents":[41],"engineered":[43],"a":[45,57,71,77],"specific":[46],"problem":[47],"not":[50],"reusable.":[51],"In":[52],"this":[53,83],"work,":[54],"we":[55,85],"propose":[56],"way":[58],"tackle":[60],"these":[61],"shortcomings.":[62],"We":[63,105,137],"find":[64],"that,":[65],"in":[66,76,122,133],"diverse":[67],"problems,":[69],"only":[70],"few":[72],"actions":[73],"useful":[75],"given":[78],"time":[79],"window.":[80],"Motivated":[81],"by":[82],"property,":[84],"design":[86],"Micro-Armed":[87],"Bandit":[88,90,103,108],"(or":[89],"short),":[92],"an":[93],"agent":[95],"is":[97],"based":[98],"on":[99],"the":[100,113],"low-complexity":[101],"Multi-Armed":[102],"algorithms.":[104],"show":[106],"can":[109],"match":[110],"or":[111],"exceed":[112],"performance":[114],"of":[115],"more":[116,150],"complex":[117],"non-RL":[120],"alternatives":[121],"different":[124],"problems:":[125],"data":[126],"prefetching":[127],"instruction":[129],"fetch":[130],"thread":[131],"selection":[132],"simultaneous":[134],"multithreaded":[135],"processors.":[136],"believe":[138],"Bandit\u2019s":[140],"simplicity,":[141],"reusability,":[142],"small":[144],"overhead":[146],"practical":[151],"microarchitecture.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}