{"id":"https://openalex.org/W1547532156","doi":"https://doi.org/10.1109/icmla.2004.1383495","title":"Satisficing Q-learning: efficient learning in problems with dichotomous attributes","display_name":"Satisficing Q-learning: efficient learning in problems with dichotomous attributes","publication_year":2005,"publication_date":"2005-04-06","ids":{"openalex":"https://openalex.org/W1547532156","doi":"https://doi.org/10.1109/icmla.2004.1383495","mag":"1547532156"},"language":"en","primary_location":{"id":"doi:10.1109/icmla.2004.1383495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla.2004.1383495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 International Conference on Machine Learning and Applications, 2004. Proceedings.","raw_type":"proceedings-article"},"type":"conference-paper","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/A5077345598","display_name":"Michael A. Goodrich","orcid":"https://orcid.org/0000-0002-2489-5705"},"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":"M.A. Goodrich","raw_affiliation_strings":["Computer Science Department, Brigham Young University, USA","Computer Science Department, Brigham Young University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Brigham Young University, USA","institution_ids":["https://openalex.org/I100005738"]},{"raw_affiliation_string":"Computer Science Department, Brigham Young University","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013155801","display_name":"Morgan Quigley","orcid":null},"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":"M. Quigley","raw_affiliation_strings":["Computer Science Department, Brigham Young University, USA","Computer Science Department, Brigham Young University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Brigham Young University, USA","institution_ids":["https://openalex.org/I100005738"]},{"raw_affiliation_string":"Computer Science Department, Brigham Young University","institution_ids":["https://openalex.org/I100005738"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I100005738"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"65","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/satisficing","display_name":"Satisficing","score":0.986197829246521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6837835311889648},{"id":"https://openalex.org/keywords/balance","display_name":"Balance (ability)","score":0.4957922399044037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47610247135162354},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44776850938796997},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0983235239982605}],"concepts":[{"id":"https://openalex.org/C94822996","wikidata":"https://www.wikidata.org/wiki/Q1777902","display_name":"Satisficing","level":2,"score":0.986197829246521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6837835311889648},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.4957922399044037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47610247135162354},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44776850938796997},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0983235239982605},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icmla.2004.1383495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla.2004.1383495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 International Conference on Machine Learning and Applications, 2004. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:ADA451568","is_oa":false,"landing_page_url":"http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA451568","pdf_url":null,"source":{"id":"https://openalex.org/S4406923043","display_name":"Defense Technical Information Center (DTIC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"DTIC","raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1545257123","https://openalex.org/W2006946956","https://openalex.org/W2012661833","https://openalex.org/W2091579301","https://openalex.org/W2104981588","https://openalex.org/W2106354437","https://openalex.org/W2121863487","https://openalex.org/W2122410182","https://openalex.org/W2171781007","https://openalex.org/W2623293810","https://openalex.org/W2885790575","https://openalex.org/W2913433435","https://openalex.org/W4214717370","https://openalex.org/W6753257663"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"In":[0,35],"some":[1],"environments,":[2],"a":[3,14,33,40,46,67,128,133],"learning":[4,127],"agent":[5,16,25],"must":[6],"learn":[7,20],"to":[8,19,26,32,82,87,92,96,111,126],"balance":[9],"competing":[10,63],"objectives.":[11],"For":[12],"example,":[13],"Q-learner":[15],"may":[17],"need":[18],"which":[21,29],"choices":[22,30],"expose":[23],"the":[24,62,78,101,107,124],"risk":[27],"and":[28,55,121],"lead":[31],"goal.":[34],"this":[36,58],"paper,":[37],"we":[38],"present":[39],"variant":[41],"of":[42,48,77,118],"Q-learning":[43],"that":[44,57,106,136],"learns":[45],"pair":[47],"utilities":[49],"for":[50,132],"worlds":[51,117],"with":[52],"dichotomous":[53],"attributes":[54],"show":[56],"algorithm":[59,102,108,125],"properly":[60],"balances":[61],"objectives":[64],"and,":[65],"as":[66],"result,":[68],"efficiently":[69],"identifies":[70],"satisficing":[71],"solutions.":[72],"This":[73],"occurs":[74],"because":[75],"exploration":[76],"environment":[79],"is":[80],"restricted":[81],"those":[83],"options":[84],"which,":[85],"according":[86],"current":[88],"knowledge,":[89],"are":[90],"likely":[91],"avoid":[93,139],"unjustifiable":[94],"exposure":[95],"risk.":[97],"We":[98],"empirically":[99],"validate":[100],"by":[103],"(a)":[104],"showing":[105],"quickly":[109],"converges":[110],"good":[112],"policies":[113],"in":[114],"several":[115],"simulated":[116],"various":[119],"complexities":[120],"(b)":[122],"applying":[123],"force":[129],"feedback":[130],"profile":[131],"gas":[134],"pedal":[135],"helps":[137],"drivers":[138],"risky":[140],"situations.":[141]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}