{"id":"https://openalex.org/W2172264025","doi":"https://doi.org/10.1177/1059712306076253","title":"Empirical Studies in Action Selection with Reinforcement Learning","display_name":"Empirical Studies in Action Selection with Reinforcement Learning","publication_year":2007,"publication_date":"2007-02-27","ids":{"openalex":"https://openalex.org/W2172264025","doi":"https://doi.org/10.1177/1059712306076253","mag":"2172264025"},"language":"en","primary_location":{"id":"doi:10.1177/1059712306076253","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1059712306076253","pdf_url":null,"source":{"id":"https://openalex.org/S183337005","display_name":"Adaptive Behavior","issn_l":"1059-7123","issn":["1059-7123","1741-2633"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptive Behavior","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/A5056879203","display_name":"Shimon Whiteson","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shimon Whiteson","raw_affiliation_strings":["Department of Computer Sciences, University of Texas, Austin, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Texas, Austin, USA,","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070914351","display_name":"Matthew E. Taylor","orcid":"https://orcid.org/0000-0001-8946-0211"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew E. Taylor","raw_affiliation_strings":["Department of Computer Sciences, University of Texas, Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Texas, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001594330","display_name":"Peter Stone","orcid":"https://orcid.org/0000-0002-6795-420X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Stone","raw_affiliation_strings":["Department of Computer Sciences, University of Texas, Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Texas, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056879203"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":12.5901,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.98612472,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"15","issue":"1","first_page":"33","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9977999925613403,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9886000156402588,"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":0.849411129951477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7948201894760132},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.6780877709388733},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6693713665008545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6576279401779175},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6275763511657715},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6129575967788696},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6031367778778076},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.579867959022522},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.515389084815979},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.46814873814582825},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4519120156764984},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.45008769631385803},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.42021292448043823},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08769521117210388}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.849411129951477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7948201894760132},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.6780877709388733},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6693713665008545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6576279401779175},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6275763511657715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6129575967788696},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6031367778778076},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.579867959022522},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.515389084815979},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.46814873814582825},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4519120156764984},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.45008769631385803},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.42021292448043823},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08769521117210388},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/1059712306076253","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1059712306076253","pdf_url":null,"source":{"id":"https://openalex.org/S183337005","display_name":"Adaptive Behavior","issn_l":"1059-7123","issn":["1059-7123","1741-2633"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptive Behavior","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.91.5314","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.91.5314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://adb.sagepub.com/cgi/reprint/15/1/33.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":82,"referenced_works":["https://openalex.org/W118241712","https://openalex.org/W166862392","https://openalex.org/W178169250","https://openalex.org/W1500080465","https://openalex.org/W1506497862","https://openalex.org/W1515851193","https://openalex.org/W1524100745","https://openalex.org/W1540566633","https://openalex.org/W1543341872","https://openalex.org/W1562393358","https://openalex.org/W1568161011","https://openalex.org/W1574700590","https://openalex.org/W1585546346","https://openalex.org/W1586365389","https://openalex.org/W1601974704","https://openalex.org/W1659842140","https://openalex.org/W1783866091","https://openalex.org/W1914583973","https://openalex.org/W1931792391","https://openalex.org/W1947179618","https://openalex.org/W1974605885","https://openalex.org/W1979356863","https://openalex.org/W1981276685","https://openalex.org/W1990911977","https://openalex.org/W2027475699","https://openalex.org/W2049287437","https://openalex.org/W2076329865","https://openalex.org/W2089052147","https://openalex.org/W2096712730","https://openalex.org/W2099233925","https://openalex.org/W2100188533","https://openalex.org/W2100677568","https://openalex.org/W2104641222","https://openalex.org/W2111935653","https://openalex.org/W2112254845","https://openalex.org/W2113913482","https://openalex.org/W2115931363","https://openalex.org/W2116339921","https://openalex.org/W2117495877","https://openalex.org/W2119053738","https://openalex.org/W2120181489","https://openalex.org/W2121138345","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2124290836","https://openalex.org/W2125074935","https://openalex.org/W2125614502","https://openalex.org/W2128262600","https://openalex.org/W2132862952","https://openalex.org/W2141559645","https://openalex.org/W2144366468","https://openalex.org/W2145351764","https://openalex.org/W2153192722","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2162813238","https://openalex.org/W2164056559","https://openalex.org/W2165713838","https://openalex.org/W2168405694","https://openalex.org/W2169223808","https://openalex.org/W2169659168","https://openalex.org/W2169803171","https://openalex.org/W2171625236","https://openalex.org/W2463810433","https://openalex.org/W2492794003","https://openalex.org/W2605170521","https://openalex.org/W2764433274","https://openalex.org/W2913205451","https://openalex.org/W2913529121","https://openalex.org/W2913668833","https://openalex.org/W2998349125","https://openalex.org/W3004042307","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W3139377883","https://openalex.org/W4212774754","https://openalex.org/W4214717370","https://openalex.org/W4232335189","https://openalex.org/W4244791762","https://openalex.org/W4250406710","https://openalex.org/W4255440400","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2015051472","https://openalex.org/W2145363145","https://openalex.org/W2168501056","https://openalex.org/W2341346307","https://openalex.org/W2120009678","https://openalex.org/W2154399718","https://openalex.org/W2912947802","https://openalex.org/W4321463377","https://openalex.org/W2037601570","https://openalex.org/W2130703626"],"abstract_inverted_index":{"To":[0],"excel":[1,179],"in":[2,22,49,151],"challenging":[3],"tasks,":[4],"intelligent":[5],"agents":[6],"need":[7,14],"sophisticated":[8],"mechanisms":[9,186],"for":[10,223],"action":[11,19],"selection:":[12],"they":[13],"policies":[15,34],"that":[16,46,132,161,231],"dictate":[17],"what":[18],"to":[20,31,44,105,111,116,124,165,175,218],"take":[21],"each":[23,169],"situation.":[24],"Reinforcement":[25],"learning":[26],"(RL)":[27],"algorithms":[28,178],"are":[29,47,52,85],"designed":[30],"learn":[32,58],"such":[33],"given":[35],"only":[36],"positive":[37],"and":[38,61,93,136,155,210,239],"negative":[39],"rewards.":[40],"Two":[41],"contrasting":[42],"approaches":[43,71,150],"RL":[45],"currently":[48],"popular":[50],"use":[51],"temporal":[53],"difference":[54],"(TD)":[55],"methods,":[56,63],"which":[57,64],"value":[59],"functions,":[60],"evolutionary":[62,177,209,240],"optimize":[65],"populations":[66],"of":[67,140,158,168,207],"candidate":[68],"policies.":[69],"Both":[70],"have":[72,79],"had":[73],"practical":[74],"successes":[75],"but":[76],"few":[77,103],"studies":[78,131],"directly":[80],"compared":[81],"them.":[82],"Hence,":[83],"there":[84,97],"no":[86],"general":[87],"guidelines":[88],"describing":[89],"their":[90],"relative":[91],"strengths":[92],"weaknesses.":[94],"In":[95,119],"addition,":[96],"has":[98],"been":[99],"little":[100],"cross-collaboration,":[101],"with":[102],"attempts":[104],"make":[106,176],"them":[107,142],"work":[108,143,213],"together":[109,214],"or":[110],"apply":[112],"ideas":[113],"from":[114],"one":[115],"the":[117,148,159,166],"other.":[118],"this":[120,232],"article":[121],"we":[122,146,172,202],"aim":[123],"address":[125],"these":[126,134],"shortcomings":[127],"via":[128],"three":[129],"empirical":[130,194],"compare":[133,147],"methods":[135,212,241],"investigate":[137,173],"new":[138],"ways":[139,174],"making":[141,208],"together.":[144],"First,":[145],"two":[149],"a":[152,197,204],"benchmark":[153],"task":[154,160],"identify":[156],"variations":[157],"isolate":[162],"factors":[163],"critical":[164],"performance":[167,199],"method.":[170],"Second,":[171],"at":[180],"on-line":[181],"tasks":[182],"by":[183,189,215],"borrowing":[184],"exploratory":[185],"traditionally":[187],"used":[188],"TD":[190,211,224,238],"methods.":[191],"We":[192,227],"present":[193,228],"results":[195,229],"demonstrating":[196,230],"dramatic":[198],"improvement.":[200],"Third,":[201],"explore":[203],"novel":[205,233],"way":[206],"using":[216],"evolution":[217],"automatically":[219],"discover":[220],"good":[221],"representations":[222],"function":[225],"approximators.":[226],"approach":[234],"can":[235],"outperform":[236],"both":[237],"alone.":[242]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2026-05-01T08:36:08.643496","created_date":"2025-10-10T00:00:00"}
