{"id":"https://openalex.org/W4386132080","doi":"https://doi.org/10.1109/tai.2023.3308099","title":"Reinforcement Learning for Selecting Custom Instructions Under Area Constraint","display_name":"Reinforcement Learning for Selecting Custom Instructions Under Area Constraint","publication_year":2023,"publication_date":"2023-08-24","ids":{"openalex":"https://openalex.org/W4386132080","doi":"https://doi.org/10.1109/tai.2023.3308099"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2023.3308099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2023.3308099","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Transactions on Artificial Intelligence","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/A5100406282","display_name":"Shanshan Wang","orcid":"https://orcid.org/0009-0004-1322-3032"},"institutions":[{"id":"https://openalex.org/I32574673","display_name":"Shantou University","ror":"https://ror.org/01a099706","country_code":"CN","type":"education","lineage":["https://openalex.org/I32574673"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shanshan Wang","raw_affiliation_strings":["Department of Computer Science, Shantou University, Shantou, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Shantou University, Shantou, China","institution_ids":["https://openalex.org/I32574673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049047722","display_name":"Chenglong Xiao","orcid":"https://orcid.org/0000-0001-7013-4985"},"institutions":[{"id":"https://openalex.org/I32574673","display_name":"Shantou University","ror":"https://ror.org/01a099706","country_code":"CN","type":"education","lineage":["https://openalex.org/I32574673"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Xiao","raw_affiliation_strings":["Department of Computer Science, Shantou University, Shantou, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Shantou University, Shantou, China","institution_ids":["https://openalex.org/I32574673"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100406282"],"corresponding_institution_ids":["https://openalex.org/I32574673"],"apc_list":null,"apc_paid":null,"fwci":1.8378,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.88418007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"5","issue":"4","first_page":"1882","last_page":"1894"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9498000144958496,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.9498000144958496,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9402999877929688,"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":0.8299763202667236},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.69366854429245},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5387753844261169},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.514577329158783},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.49012574553489685},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4686994254589081},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.45991674065589905},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4543165862560272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45297709107398987},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4004132151603699},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.337501585483551},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.21551421284675598},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21475577354431152},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20879963040351868}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8299763202667236},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.69366854429245},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5387753844261169},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.514577329158783},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.49012574553489685},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4686994254589081},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.45991674065589905},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4543165862560272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45297709107398987},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4004132151603699},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.337501585483551},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.21551421284675598},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21475577354431152},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20879963040351868},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2023.3308099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2023.3308099","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G5412885698","display_name":null,"funder_award_id":"2023A1515010077","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G936899955","display_name":null,"funder_award_id":"2022A1515110712","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1484728941","https://openalex.org/W1972804619","https://openalex.org/W2020903821","https://openalex.org/W2039979393","https://openalex.org/W2059432803","https://openalex.org/W2067239435","https://openalex.org/W2101637975","https://openalex.org/W2110350195","https://openalex.org/W2111488604","https://openalex.org/W2121507132","https://openalex.org/W2131264876","https://openalex.org/W2145339207","https://openalex.org/W2147405597","https://openalex.org/W2160450201","https://openalex.org/W2165892109","https://openalex.org/W2171507906","https://openalex.org/W2389761592","https://openalex.org/W2406293284","https://openalex.org/W2429120270","https://openalex.org/W2556941761","https://openalex.org/W2570773108","https://openalex.org/W2579592432","https://openalex.org/W2591182809","https://openalex.org/W2683470288","https://openalex.org/W2789928742","https://openalex.org/W2891305971","https://openalex.org/W2904420091","https://openalex.org/W2998327136","https://openalex.org/W3006559397","https://openalex.org/W3018195242","https://openalex.org/W3026844281","https://openalex.org/W3033543607","https://openalex.org/W3036554530","https://openalex.org/W3045811008","https://openalex.org/W3090136530","https://openalex.org/W3117927252","https://openalex.org/W3120016072","https://openalex.org/W3135712736","https://openalex.org/W3159444988","https://openalex.org/W3187550742","https://openalex.org/W3196755144","https://openalex.org/W3199371879","https://openalex.org/W3206621799","https://openalex.org/W4214717370","https://openalex.org/W4232751114","https://openalex.org/W4244080578","https://openalex.org/W4249006057","https://openalex.org/W4251886783","https://openalex.org/W4285114951","https://openalex.org/W4307230233","https://openalex.org/W4313291093","https://openalex.org/W6677067356","https://openalex.org/W6752725515","https://openalex.org/W6776921880","https://openalex.org/W6791113163"],"related_works":["https://openalex.org/W2504004674","https://openalex.org/W1595229445","https://openalex.org/W2498744856","https://openalex.org/W4390482104","https://openalex.org/W322408318","https://openalex.org/W149041114","https://openalex.org/W2963177394","https://openalex.org/W1965815883","https://openalex.org/W4313359513","https://openalex.org/W2259967567"],"abstract_inverted_index":{"Extensible":[0],"processors,":[1],"which":[2],"combine":[3],"programma-bility":[4],"and":[5,95,112,123,141,158,208],"efficiency,":[6],"are":[7],"emerging":[8],"as":[9,77],"a":[10,29,48,58,78,109],"promising":[11],"approach":[12],"in":[13,33,149],"the":[14,34,69,100,120,124,138,146,152,162,167,172,179,184,200,206,209,212],"field":[15],"of":[16,21,36,51,114,117,151,211],"embedded":[17],"computing.":[18],"Automated":[19],"synthesis":[20],"custom":[22,41,45,70,101],"instructions":[23,46],"from":[24,47],"high-level":[25],"application":[26],"descriptions":[27],"is":[28,56,198],"vital":[30],"step":[31],"involved":[32],"design":[35],"extensible":[37],"processors.":[38],"In":[39,63],"automated":[40],"instruction":[42,71,102],"synthesis,":[43],"selecting":[44],"large":[49],"set":[50],"candidates":[52],"under":[53],"area":[54],"constraint":[55],"essentially":[57],"difficult":[59],"combinatorial":[60],"optimization":[61],"problem.":[62,81,104],"this":[64,84],"paper,":[65],"we":[66,86,106],"show":[67],"that":[68,137,183],"selection":[72,103],"problem":[73],"can":[74],"be":[75],"formulated":[76],"sequential":[79],"decision-making":[80],"Based":[82],"on":[83],"formulation,":[85],"present":[87],"three":[88,163],"reinforcement":[89,164,175],"learning-based":[90],"approaches,":[91],"namely":[92],"SARSA,":[93,139],"Q-learning,":[94,140],"Double":[96,142],"Q-Learning,":[97],"for":[98,127,204],"solving":[99],"Moreover,":[105],"also":[107],"perform":[108],"comprehensive":[110],"analysis":[111],"com-parison":[113],"various":[115],"combinations":[116],"learning":[118,165,176,213],"specifications:":[119],"algorithm":[121,148,169],"type":[122],"update":[125],"strategy":[126,185],"\u03b5-greedy":[128],"policy.":[129],"The":[130],"experiments":[131],"with":[132],"45":[133],"test":[134],"instances":[135],"reveal":[136],"Q-Learning":[143],"algorithms":[144],"outperform":[145],"meta-heuristic":[147],"terms":[150],"overall":[153],"performance":[154],"gains":[155],"by":[156],"26.9%,26.1%":[157],"26.4%":[159],"respectively.":[160],"Among":[161],"algorithms,":[166],"SARSA":[168],"slightly":[170],"overwhelms":[171],"other":[173],"two":[174],"algorithms.":[177],"Furthermore,":[178],"experimental":[180],"results":[181],"suggest":[182],"<inline-formula":[186],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[187],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[188],"notation=\"LaTeX\">$F_3":[189],":":[190],"\u03b5":[191],"=":[192],"\u03ba^i,0":[193],"&lt;":[194,196],"\u03ba":[195],"1$</tex-math></inline-formula>":[197],"generally":[199],"most":[201],"effective":[202],"one":[203],"controlling":[205],"exploration":[207],"exploitation":[210],"processes.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}