{"id":"https://openalex.org/W2162220785","doi":"https://doi.org/10.1109/iat.2003.1241048","title":"Integrating reinforcement learning, bidding and genetic algorithms","display_name":"Integrating reinforcement learning, bidding and genetic algorithms","publication_year":2004,"publication_date":"2004-03-02","ids":{"openalex":"https://openalex.org/W2162220785","doi":"https://doi.org/10.1109/iat.2003.1241048","mag":"2162220785"},"language":"en","primary_location":{"id":"doi:10.1109/iat.2003.1241048","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iat.2003.1241048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC International Conference on Intelligent Agent Technology, 2003. IAT 2003.","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/A5108533805","display_name":"Dehun Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I177898655","display_name":"Lamar University","ror":"https://ror.org/008ms5s18","country_code":"US","type":"education","lineage":["https://openalex.org/I177898655"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dehun Qi","raw_affiliation_strings":["Computer Science Department, Lamar University, Beaumont, TX, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Lamar University, Beaumont, TX, USA","institution_ids":["https://openalex.org/I177898655"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102061872","display_name":"Ron Sun","orcid":"https://orcid.org/0000-0001-9006-9746"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron Sun","raw_affiliation_strings":["CECS Department, University of Missouri, Columbia, Columbia, MO, USA"],"affiliations":[{"raw_affiliation_string":"CECS Department, University of Missouri, Columbia, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5108533805"],"corresponding_institution_ids":["https://openalex.org/I177898655"],"apc_list":null,"apc_paid":null,"fwci":2.7728,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.91480108,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"53","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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":0.9977999925613403,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9915000200271606,"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/T11182","display_name":"Auction Theory and Applications","score":0.9828000068664551,"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/bidding","display_name":"Bidding","score":0.9273683428764343},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9194928407669067},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.734390139579773},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"Genetic algorithm","score":0.566875696182251},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5180509090423584},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.47796937823295593},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4695373773574829},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45062899589538574},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43252211809158325},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30584147572517395},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12794125080108643}],"concepts":[{"id":"https://openalex.org/C9233905","wikidata":"https://www.wikidata.org/wiki/Q3276328","display_name":"Bidding","level":2,"score":0.9273683428764343},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9194928407669067},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.734390139579773},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.566875696182251},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5180509090423584},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.47796937823295593},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4695373773574829},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45062899589538574},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43252211809158325},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30584147572517395},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12794125080108643},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iat.2003.1241048","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iat.2003.1241048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC International Conference on Intelligent Agent Technology, 2003. IAT 2003.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.7.2822","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.7.2822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cecs.missouri.edu/~rsun/sun-qi.IAT2003.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W188606012","https://openalex.org/W1513468570","https://openalex.org/W1521196763","https://openalex.org/W1521817025","https://openalex.org/W1679907412","https://openalex.org/W1963805119","https://openalex.org/W1972688571","https://openalex.org/W1986464489","https://openalex.org/W2024000119","https://openalex.org/W2033016725","https://openalex.org/W2041367235","https://openalex.org/W2044676734","https://openalex.org/W2096154177","https://openalex.org/W2100677568","https://openalex.org/W2103626435","https://openalex.org/W2112180705","https://openalex.org/W2124754061","https://openalex.org/W2131600418","https://openalex.org/W2145351764","https://openalex.org/W2170788637","https://openalex.org/W2546966825","https://openalex.org/W2787259794","https://openalex.org/W3041202696","https://openalex.org/W4285719527","https://openalex.org/W6607721934","https://openalex.org/W6630520071","https://openalex.org/W6631254968","https://openalex.org/W6681818515"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915","https://openalex.org/W2089415692","https://openalex.org/W4294873804"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,36,42,97,120],"GA-based":[4,107],"multi-agent":[5,13,29],"reinforcement":[6,14,18],"learning":[7],"bidding":[8,20,103],"approach":[9],"(GMARLB)":[10],"for":[11],"performing":[12],"learning.":[15],"GMARLB":[16,108,117],"integrates":[17],"learning,":[19],"and":[21,54],"genetic":[22],"algorithms.":[23,104],"The":[24,113],"general":[25],"idea":[26],"of":[27,38,46,123],"our":[28],"systems":[30],"is":[31,100],"as":[32],"follows:":[33],"There":[34],"are":[35,69],"number":[37],"individual":[39],"agents":[40],"in":[41,125],"team,":[43],"each":[44,66,81],"agent":[45,58,85,93,99],"the":[47,72,76,84,110,130],"team":[48],"has":[49],"two":[50],"modules:":[51],"Q":[52,73],"module":[53,78],"CQ":[55,77],"module.":[56,74],"Each":[57],"can":[59,118],"select":[60],"actions":[61],"to":[62,109],"be":[63],"performed":[64],"at":[65,80],"step,":[67],"which":[68],"done":[70],"by":[71,102],"While":[75],"determines":[79],"step":[82],"whether":[83],"should":[86],"continue":[87],"or":[88],"relinquish":[89],"control.":[90],"Once":[91],"an":[92],"relinquishes":[94],"its":[95],"control,":[96],"new":[98],"selected":[101],"We":[105],"applied":[106],"Backgammon":[111],"game.":[112],"experimental":[114],"results":[115],"show":[116],"achieve":[119],"superior":[121],"level":[122],"performance":[124],"game-playing,":[126],"outperforming":[127],"PubEval,":[128],"while":[129],"system":[131],"uses":[132],"zero":[133],"built-in":[134],"knowledge.":[135]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}