{"id":"https://openalex.org/W7125925222","doi":"https://doi.org/10.1109/smc58881.2025.11343361","title":"ArchERL: Evolutionary Reinforcement Learning Framework for Efficient Hardware Architecture Design without Domain Knowledge","display_name":"ArchERL: Evolutionary Reinforcement Learning Framework for Efficient Hardware Architecture Design without Domain Knowledge","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125925222","doi":"https://doi.org/10.1109/smc58881.2025.11343361"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5124134736","display_name":"Yuwei Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuwei Huang","raw_affiliation_strings":["Southern University of Science and Technology,Department of Computer Science and Engineering,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Department of Computer Science and Engineering,Shenzhen,China,518055","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123390142","display_name":"Yuhui Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhui Shi","raw_affiliation_strings":["Southern University of Science and Technology,Department of Computer Science and Engineering,Shenzhen,China,518055"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,Department of Computer Science and Engineering,Shenzhen,China,518055","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5124134736"],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87021819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5933","last_page":"5939"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.22519999742507935,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.22519999742507935,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.21160000562667847,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.08229999989271164,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.7807999849319458},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5364000201225281},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4950000047683716},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.46560001373291016},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.4124999940395355},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.38850000500679016},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.3824000060558319},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3377000093460083}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7807999849319458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7249000072479248},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5364000201225281},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4950000047683716},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.46560001373291016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44760000705718994},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.40959998965263367},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32839998602867126},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C199505168","wikidata":"https://www.wikidata.org/wiki/Q3267529","display_name":"Evolutionary robotics","level":3,"score":0.2863999903202057},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C65232700","wikidata":"https://www.wikidata.org/wiki/Q5656403","display_name":"Hardware architecture","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.40007588267326355,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1191365092","https://openalex.org/W2194775991","https://openalex.org/W2951278471","https://openalex.org/W2970792251","https://openalex.org/W2980200167","https://openalex.org/W3017521908","https://openalex.org/W3135807226","https://openalex.org/W3171752851","https://openalex.org/W4226323948","https://openalex.org/W4250981202","https://openalex.org/W4310520567","https://openalex.org/W4327930463","https://openalex.org/W4380881074","https://openalex.org/W4391136507","https://openalex.org/W4393160882","https://openalex.org/W4407416181"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,23,48,61,64,85,125,138,151],"stagnation":[2],"of":[3,25,47,88],"Moore\u2019s":[4],"Law":[5],"scaling,":[6],"efficient":[7,130],"hardware":[8,92,148],"architectures":[9,27],"employing":[10],"compute-in-memory":[11],"paradigms":[12],"have":[13],"become":[14],"increasingly":[15],"crucial":[16],"to":[17,90,128],"sustain":[18],"AI":[19],"innovations.":[20],"This":[21],"motivates":[22],"development":[24],"high-throughput":[26],"with":[28,105],"balanced":[29],"energy-latency":[30],"profiles":[31],"through":[32],"machine":[33],"learning":[34,80,109],"algorithms.":[35],"However,":[36],"for":[37,51,102,111],"human-in-the-loop":[38],"optimization":[39],"methods,":[40,53],"human":[41],"labor":[42],"is":[43,58,67],"involved":[44],"in":[45,60,145,170],"most":[46],"iterations,":[49],"whereas":[50],"automated":[52],"either":[54],"expert":[55],"domain":[56],"knowledge":[57],"required":[59],"design":[62],"or":[63],"search":[65,132],"space":[66],"relatively":[68],"small.":[69],"To":[70,136],"address":[71],"these":[72],"challenges,":[73],"we":[74],"propose":[75],"ArchERL,":[76],"an":[77,106],"evolutionary":[78,100],"reinforcement":[79,108],"(ERL)":[81],"framework":[82],"that":[83,160],"represents":[84],"first":[86],"application":[87],"ERL":[89],"general":[91],"architecture":[93],"design.":[94],"Specifically,":[95],"ArchERL":[96,116,161],"tightly":[97],"couples":[98],"population-based":[99],"algorithm":[101],"global":[103],"exploration":[104],"actor-critic":[107],"module":[110],"prior-light":[112],"policy":[113],"refinement,":[114],"and":[115,121,133,154,165,173],"employs":[117],"periodic":[118],"weight":[119],"synchronization":[120],"gradient":[122],"feedback":[123],"between":[124],"two":[126],"modules":[127],"achieve":[129],"collaborative":[131],"rapid":[134],"convergence.":[135],"evaluate":[137],"proposed":[139],"method,":[140],"extensive":[141],"experiments":[142],"are":[143],"conducted":[144],"multiple":[146],"simulated":[147],"environments,":[149],"including":[150],"DRAM":[152],"controller":[153],"DNN":[155],"mapping.":[156],"The":[157],"results":[158],"demonstrate":[159],"achieves":[162],"leading":[163],"performance":[164],"outperforms":[166],"widely":[167],"used":[168],"baselines":[169],"both":[171],"efficiency":[172],"effectiveness.":[174]},"counts_by_year":[],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}