{"id":"https://openalex.org/W4389476179","doi":"https://doi.org/10.1145/3613424.3623780","title":"Micro-Armed Bandit: Lightweight & Reusable Reinforcement Learning for Microarchitecture Decision-Making","display_name":"Micro-Armed Bandit: Lightweight & Reusable Reinforcement Learning for Microarchitecture Decision-Making","publication_year":2023,"publication_date":"2023-10-28","ids":{"openalex":"https://openalex.org/W4389476179","doi":"https://doi.org/10.1145/3613424.3623780"},"language":"en","primary_location":{"id":"doi:10.1145/3613424.3623780","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3623780","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3623780","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3623780","any_repository_has_fulltext":null},"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":false,"raw_author_name":"Gerasimos Gerogiannis","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-7946-2683","affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, United States of America","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, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-2595-5228","affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, United States of America","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2367,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.93611717,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"698","last_page":"713"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9905999898910522,"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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9904000163078308,"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":0.8548876047134399},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.8218260407447815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7557199001312256},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6811375617980957},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.6239011287689209},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3803165555000305},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.36827725172042847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3402438759803772},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2314237356185913}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8548876047134399},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.8218260407447815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7557199001312256},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6811375617980957},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6239011287689209},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3803165555000305},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.36827725172042847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3402438759803772},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2314237356185913},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3613424.3623780","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3623780","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3623780","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3613424.3623780","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3623780","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3623780","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.75,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1452086972","display_name":null,"funder_award_id":"JUMP 2.0","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"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/G2374893308","display_name":"CNS Core: Medium: Rethinking Architecture and Operating Systems for Modern Virtualization Technologies","funder_award_id":"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"},{"id":"https://openalex.org/G5485016241","display_name":"SHF: Medium: Cross-Cutting Effort to Make Non-Volatile Memories Truly Usable","funder_award_id":"2107470","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7453695159","display_name":"CSR: Medium: Effective Control to Maximize Resource Efficiency in Large Clusters;  Hardware, Runtime, and Compiler Perspectives","funder_award_id":"1763658","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G990447602","display_name":null,"funder_award_id":"CCF 2107470, CNS 1956007, and CNS 1763658","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"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4389476179.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W117083835","https://openalex.org/W1550898840","https://openalex.org/W1998498767","https://openalex.org/W2000041758","https://openalex.org/W2001420671","https://openalex.org/W2039522160","https://openalex.org/W2043340768","https://openalex.org/W2085830671","https://openalex.org/W2101738713","https://openalex.org/W2111444234","https://openalex.org/W2118532220","https://openalex.org/W2118811116","https://openalex.org/W2120230074","https://openalex.org/W2134026160","https://openalex.org/W2147657366","https://openalex.org/W2149265201","https://openalex.org/W2157070686","https://openalex.org/W2157189715","https://openalex.org/W2158125716","https://openalex.org/W2168361773","https://openalex.org/W2725159389","https://openalex.org/W2896795945","https://openalex.org/W2913208203","https://openalex.org/W2915041608","https://openalex.org/W2945496227","https://openalex.org/W2950959891","https://openalex.org/W2977563388","https://openalex.org/W2980229124","https://openalex.org/W2997451313","https://openalex.org/W3005750793","https://openalex.org/W3012303953","https://openalex.org/W3153963463","https://openalex.org/W3157126516","https://openalex.org/W3188005507","https://openalex.org/W4205474951","https://openalex.org/W4210896998","https://openalex.org/W4225988922","https://openalex.org/W4232385523","https://openalex.org/W4232402592","https://openalex.org/W4233722262","https://openalex.org/W4245268430","https://openalex.org/W4252076096","https://openalex.org/W4312917169","https://openalex.org/W4313033857"],"related_works":["https://openalex.org/W122453572","https://openalex.org/W2351011383","https://openalex.org/W2146879484","https://openalex.org/W4221002079","https://openalex.org/W1757458251","https://openalex.org/W1980898636","https://openalex.org/W2141090099","https://openalex.org/W2045325972","https://openalex.org/W3008777550","https://openalex.org/W4302312371"],"abstract_inverted_index":{"Online":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"has":[4],"been":[5],"adopted":[6],"as":[7],"an":[8],"effective":[9],"mechanism":[10],"in":[11,15,30],"various":[12],"decision-making":[13],"problems":[14],"microarchitecture.":[16],"Its":[17],"high":[18,49],"adaptability":[19],"and":[20,51,67,88],"the":[21,59],"ability":[22],"to":[23],"learn":[24],"at":[25],"runtime":[26],"are":[27,38,82,89],"attractive":[28],"characteristics":[29],"microarchitecture":[31],"settings.":[32],"However,":[33],"although":[34],"hardware":[35],"RL":[36,80],"agents":[37,81],"effective,":[39],"they":[40,47],"suffer":[41],"from":[42,57],"two":[43],"main":[44],"problems.":[45],"First,":[46],"have":[48],"complexity":[50,55],"storage":[52],"overhead.":[53],"This":[54],"stems":[56],"decomposing":[58],"environment":[60],"into":[61],"a":[62,85],"large":[63],"number":[64],"of":[65,71],"states":[66],"then,":[68],"for":[69,84],"each":[70],"these":[72],"states,":[73],"bookkeeping":[74],"many":[75,79],"action":[76],"values.":[77],"Second,":[78],"engineered":[83],"specific":[86],"application":[87],"not":[90],"reusable.":[91]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}