{"id":"https://openalex.org/W1966795461","doi":"https://doi.org/10.1145/1900008.1900072","title":"Generating three binary addition algorithms using reinforcement programming","display_name":"Generating three binary addition algorithms using reinforcement programming","publication_year":2010,"publication_date":"2010-04-15","ids":{"openalex":"https://openalex.org/W1966795461","doi":"https://doi.org/10.1145/1900008.1900072","mag":"1966795461"},"language":"en","primary_location":{"id":"doi:10.1145/1900008.1900072","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1900008.1900072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th Annual Southeast Regional Conference","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/A5048245665","display_name":"Spencer White","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Spencer White","raw_affiliation_strings":["Duvall, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duvall, WA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111465095","display_name":"Tony Martinez","orcid":"https://orcid.org/0009-0009-5855-5459"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tony Martinez","raw_affiliation_strings":["Brigham Young University, Provo, UT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brigham Young University, Provo, UT","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065138542","display_name":"George Rudolph","orcid":"https://orcid.org/0009-0001-1047-3683"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Rudolph","raw_affiliation_strings":["Department of Mathematics and Computer Science, Charleston, SC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, Charleston, SC","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3984,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.84005535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9969000220298767,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9822999835014343,"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":0.8617841005325317},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7708330750465393},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.752381443977356},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5992013812065125},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5636519193649292},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5437355041503906},{"id":"https://openalex.org/keywords/adder","display_name":"Adder","score":0.5386509895324707},{"id":"https://openalex.org/keywords/binary-code","display_name":"Binary code","score":0.5171908140182495},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.49622541666030884},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4936455488204956},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4778865575790405},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.44291698932647705},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4426896870136261},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4302639961242676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4289209842681885},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4260704219341278},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3368052840232849},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.23869627714157104},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18836146593093872},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12923264503479004},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.0828862190246582}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8617841005325317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7708330750465393},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.752381443977356},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5992013812065125},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5636519193649292},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5437355041503906},{"id":"https://openalex.org/C164620267","wikidata":"https://www.wikidata.org/wiki/Q376953","display_name":"Adder","level":3,"score":0.5386509895324707},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.5171908140182495},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49622541666030884},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4936455488204956},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4778865575790405},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.44291698932647705},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4426896870136261},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4302639961242676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4289209842681885},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4260704219341278},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3368052840232849},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.23869627714157104},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18836146593093872},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12923264503479004},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0828862190246582},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1900008.1900072","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1900008.1900072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th Annual Southeast Regional Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.182.5206","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.182.5206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://axon.cs.byu.edu/papers/Spencer.ACMSE10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.550000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W162879410","https://openalex.org/W1515851193","https://openalex.org/W1568906816","https://openalex.org/W2121863487","https://openalex.org/W2160067530","https://openalex.org/W2169257920","https://openalex.org/W3011120880","https://openalex.org/W4212774754","https://openalex.org/W6738852829"],"related_works":["https://openalex.org/W4390550886","https://openalex.org/W3217463396","https://openalex.org/W2790557758","https://openalex.org/W2516396101","https://openalex.org/W3204929712","https://openalex.org/W4295102875","https://openalex.org/W2765199869","https://openalex.org/W2034043169","https://openalex.org/W1638297612","https://openalex.org/W2161708016"],"abstract_inverted_index":{"Reinforcement":[0],"Programming":[1],"(RP)":[2],"is":[3,47,93,99],"a":[4,10,32,37,71],"new":[5],"technique":[6],"for":[7,26,133],"automatically":[8],"generating":[9],"computer":[11],"program":[12],"using":[13],"reinforcement":[14],"learning":[15],"methods.":[16],"This":[17,98],"paper":[18],"describes":[19],"how":[20],"RP":[21],"learned":[22],"to":[23,56,62,95,113],"generate":[24],"code":[25],"three":[27,137],"binary":[28,38,43],"addition":[29],"problems:":[30],"simulate":[31],"full":[33],"adder":[34],"circuit,":[35],"increment":[36],"number,":[39],"and":[40,87,127],"add":[41],"two":[42],"numbers.":[44],"Each":[45,68],"problem":[46],"presented":[48,132],"as":[49],"an":[50,60],"extension":[51],"of":[52,66,75,129,135],"the":[53,63,83,91,136],"one":[54],"previous":[55],"it,":[57],"which":[58],"provides":[59],"introduction":[61],"practical":[64],"application":[65],"RP.":[67],"solution":[69],"uses":[70],"dynamic,":[72],"episodic":[73],"form":[74],"delayed":[76],"Q-Learning":[77,102],"algorithm.":[78],"\"Dynamic\"":[79],"means":[80],"that":[81,104],"grows":[82],"policy":[84,92],"during":[85],"learning,":[86],"prunes":[88],"it":[89],"before":[90],"translated":[94],"source":[96],"code.":[97],"different":[100],"from":[101],"models":[103],"use":[105],"fixed-size":[106],"tables":[107],"or":[108],"neural":[109],"net":[110],"function":[111],"approximators":[112],"store":[114],"q-values":[115],"associated":[116],"with":[117],"(state,":[118],"action)":[119],"pairs.":[120],"The":[121],"states,":[122],"actions,":[123],"rewards,":[124],"other":[125],"parameters,":[126],"results":[128],"experiments":[130],"are":[131],"each":[134],"problems.":[138]},"counts_by_year":[{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}