{"id":"https://openalex.org/W4378800968","doi":"https://doi.org/10.1145/3583781.3590298","title":"Efficient Off-Policy Reinforcement Learning via Brain-Inspired Computing","display_name":"Efficient Off-Policy Reinforcement Learning via Brain-Inspired Computing","publication_year":2023,"publication_date":"2023-05-31","ids":{"openalex":"https://openalex.org/W4378800968","doi":"https://doi.org/10.1145/3583781.3590298"},"language":"en","primary_location":{"id":"doi:10.1145/3583781.3590298","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583781.3590298","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583781.3590298","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2023","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/10.1145/3583781.3590298","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007658850","display_name":"Yang Ni","orcid":"https://orcid.org/0000-0002-8509-7803"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Ni","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8509-7803","affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087277377","display_name":"Danny Abraham","orcid":"https://orcid.org/0009-0000-3857-8826"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danny Abraham","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0009-0000-3857-8826","affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073737480","display_name":"Mariam Issa","orcid":"https://orcid.org/0000-0001-7405-2768"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mariam Issa","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7405-2768","affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067380102","display_name":"Yeseong Kim","orcid":"https://orcid.org/0000-0001-5947-9632"},"institutions":[{"id":"https://openalex.org/I193352282","display_name":"Daegu Gyeongbuk Institute of Science and Technology","ror":"https://ror.org/03frjya69","country_code":"KR","type":"education","lineage":["https://openalex.org/I193352282"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeseong Kim","raw_affiliation_strings":["Daegu Gyeongbuk Institute of Science and Technology, Daegu, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-5947-9632","affiliations":[{"raw_affiliation_string":"Daegu Gyeongbuk Institute of Science and Technology, Daegu, Republic of Korea","institution_ids":["https://openalex.org/I193352282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020615383","display_name":"Pietro Mercati","orcid":"https://orcid.org/0000-0003-2842-7201"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pietro Mercati","raw_affiliation_strings":["Intel Labs, Hilsboro, OR, USA"],"raw_orcid":"https://orcid.org/0000-0003-2842-7201","affiliations":[{"raw_affiliation_string":"Intel Labs, Hilsboro, OR, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033221192","display_name":"Mohsen Imani","orcid":"https://orcid.org/0000-0002-5761-0622"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohsen Imani","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5761-0622","affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3499,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.80478292,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"449","last_page":"453"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":1.0,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9991000294685364,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9959999918937683,"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":0.9463964700698853},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8608525991439819},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8384795188903809},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5776759386062622},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49915575981140137},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49136462807655334},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45265644788742065},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3925207853317261},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.1014481782913208}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9463964700698853},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8608525991439819},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8384795188903809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5776759386062622},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49915575981140137},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49136462807655334},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45265644788742065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3925207853317261},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.1014481782913208},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583781.3590298","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583781.3590298","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583781.3590298","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3583781.3590298","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583781.3590298","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583781.3590298","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G4267587286","display_name":null,"funder_award_id":"22RT0060","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4720003262","display_name":null,"funder_award_id":"N00014-22","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6098521345","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6604890474","display_name":null,"funder_award_id":"FA9550-22-1-0253","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8017170229","display_name":null,"funder_award_id":"N00014-21-1-2225","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G8134046633","display_name":null,"funder_award_id":"N00014-22-1-2067","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G826239146","display_name":null,"funder_award_id":"N00014-21-1-2225, N00014-22-1-2067","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8824570850","display_name":null,"funder_award_id":"2022-0-00991","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8862787963","display_name":null,"funder_award_id":"2127780","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8915565379","display_name":null,"funder_award_id":"N00014-21-1-2225","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"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/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320332923","display_name":"U.S. Navy","ror":"https://ror.org/03ar0mv07"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4378800968.pdf","grobid_xml":"https://content.openalex.org/works/W4378800968.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2056653303","https://openalex.org/W2070862086","https://openalex.org/W2766329790","https://openalex.org/W2771590529","https://openalex.org/W2772526503","https://openalex.org/W2897044384","https://openalex.org/W2911261584","https://openalex.org/W2938321354","https://openalex.org/W2973885157","https://openalex.org/W3117080414","https://openalex.org/W3184049905","https://openalex.org/W3184307506","https://openalex.org/W4210566186","https://openalex.org/W4288068445","https://openalex.org/W4293023456","https://openalex.org/W6637967152","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W4391547476","https://openalex.org/W2597809628"],"abstract_inverted_index":{"Reinforcement":[0,49],"Learning":[1],"(RL)":[2],"has":[3],"opened":[4],"up":[5],"new":[6],"opportunities":[7],"to":[8,67,128],"enhance":[9],"existing":[10],"smart":[11],"systems":[12],"that":[13,51,122],"generally":[14],"include":[15],"a":[16,63,116],"complex":[17],"decision-making":[18],"process.":[19],"However,":[20],"modern":[21],"RL":[22],"algorithms,":[23],"e.g.,":[24],"Deep":[25],"Q-Networks":[26],"(DQN),":[27],"are":[28],"based":[29],"on":[30,62],"deep":[31],"neural":[32],"networks,":[33],"resulting":[34],"in":[35,72],"high":[36],"computational":[37],"costs.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"propose":[43],"QHD,":[44],"an":[45,69,73],"off-policy":[46],"value-based":[47],"Hyperdimensional":[48],"Learning,":[50],"mimics":[52],"brain":[53],"properties":[54],"toward":[55],"robust":[56],"and":[57,79,110,147],"real-time":[58,111,141],"learning.":[59,112],"QHD":[60,83,97,138],"relies":[61],"lightweight":[64],"brain-inspired":[65],"model":[66],"learn":[68],"optimal":[70],"policy":[71],"unknown":[74],"environment.":[75],"On":[76],"both":[77],"desktop":[78],"power-limited":[80],"embedded":[81],"platforms,":[82],"achieves":[84],"significantly":[85,148],"better":[86,149],"overall":[87],"efficiency":[88],"than":[89,153],"DQN":[90,129],"while":[91,130],"providing":[92,143],"higher":[93],"or":[94],"comparable":[95],"rewards.":[96],"is":[98],"also":[99],"suitable":[100],"for":[101,108,140],"highly-efficient":[102],"reinforcement":[103],"learning":[104,152],"with":[105],"great":[106],"potential":[107],"online":[109],"Our":[113,135],"solution":[114],"supports":[115],"small":[117],"experience":[118],"replay":[119],"batch":[120],"size":[121],"provides":[123],"12.3":[124],"times":[125,145],"speedup":[126,146],"compared":[127],"ensuring":[131],"minimal":[132],"quality":[133,150],"loss.":[134],"evaluation":[136],"shows":[137],"capability":[139],"learning,":[142],"34.6":[144],"of":[151],"DQN.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}