{"id":"https://openalex.org/W2081710423","doi":"https://doi.org/10.5591/978-1-57735-516-8/ijcai11-245","title":"Q-error as a selection mechanism in modular reinforcement-learning systems","display_name":"Q-error as a selection mechanism in modular reinforcement-learning systems","publication_year":2011,"publication_date":"2011-07-16","ids":{"openalex":"https://openalex.org/W2081710423","doi":"https://doi.org/10.5591/978-1-57735-516-8/ijcai11-245","mag":"2081710423"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.225.4039","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.225.4039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idsia.ch/%7Etom/publications/qerrors.pdf","raw_type":"text"},"type":"article","indexed_in":[],"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/A5105360922","display_name":"Mark Ring","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mark Ring","raw_affiliation_strings":["IDSIA, Galleria 2, Switzerland#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDSIA, Galleria 2, Switzerland#TAB#","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081322018","display_name":"Tom Schaul","orcid":"https://orcid.org/0000-0002-2961-8782"},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Tom Schaul","raw_affiliation_strings":["IDSIA, Galleria 2, Switzerland#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-2961-8782","affiliations":[{"raw_affiliation_string":"IDSIA, Galleria 2, Switzerland#TAB#","institution_ids":["https://openalex.org/I2614128279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2614128279"],"apc_list":null,"apc_paid":null,"fwci":1.8293,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.88416154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1452","last_page":"1457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9980999827384949,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9726999998092651,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8390122652053833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7970913648605347},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7229353785514832},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.6828224658966064},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6525675058364868},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6258602142333984},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6105704307556152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5752641558647156},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5185033082962036},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5056765079498291},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4847802519798279},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4845954179763794},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12310895323753357},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09612864255905151},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.0750611424446106}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8390122652053833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7970913648605347},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7229353785514832},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.6828224658966064},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6525675058364868},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6258602142333984},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6105704307556152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5752641558647156},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5185033082962036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5056765079498291},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4847802519798279},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4845954179763794},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12310895323753357},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09612864255905151},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0750611424446106},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.225.4039","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.225.4039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idsia.ch/%7Etom/publications/qerrors.pdf","raw_type":"text"},{"id":"mag:2081710423","is_oa":false,"landing_page_url":"https://ijcai.org/papers11/Papers/IJCAI11-245.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"International Joint Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W126344362","https://openalex.org/W1515851193","https://openalex.org/W1527476591","https://openalex.org/W1578521162","https://openalex.org/W1597303641","https://openalex.org/W1989101984","https://openalex.org/W2012036715","https://openalex.org/W2097861969","https://openalex.org/W2100677568","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2130005627","https://openalex.org/W2142789491","https://openalex.org/W2160371091","https://openalex.org/W2168342951","https://openalex.org/W2304844603","https://openalex.org/W2312609093","https://openalex.org/W2912185451","https://openalex.org/W3011120880","https://openalex.org/W3139377883"],"related_works":["https://openalex.org/W2741995169","https://openalex.org/W24785488","https://openalex.org/W2807535589","https://openalex.org/W1931792391","https://openalex.org/W2535652371","https://openalex.org/W2121863487","https://openalex.org/W1603565927","https://openalex.org/W2115038009","https://openalex.org/W3103256699","https://openalex.org/W57282082","https://openalex.org/W298069310","https://openalex.org/W197852492","https://openalex.org/W2024877309","https://openalex.org/W1487472306","https://openalex.org/W2911679928","https://openalex.org/W1523133203","https://openalex.org/W2991420892","https://openalex.org/W1925600676","https://openalex.org/W2989941899","https://openalex.org/W1830058461"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,21,71,80,108,118],"novel":[4,72],"multi-modular":[5],"method":[6],"for":[7,90],"reinforcement":[8],"learning.":[9],"A":[10],"multimodular":[11],"system":[12,134],"is":[13,29,115,135],"one":[14],"that":[15],"partitions":[16],"the":[17,33,62,91,112,120,131,143],"learning":[18],"task":[19,35],"among":[20],"set":[22,81],"of":[23,31,82,101],"experts":[24],"(modules),":[25],"where":[26,75],"each":[27,98],"expert":[28],"incapable":[30],"solving":[32],"entire":[34],"by":[36,110],"itself.":[37],"There":[38],"are":[39],"many":[40],"advantages":[41],"to":[42,61,106,137],"splitting":[43],"up":[44,130],"large":[45],"tasks":[46,140],"in":[47],"this":[48],"way,":[49],"but":[50],"existing":[51],"methods":[52],"face":[53],"difficulties":[54],"when":[55,142],"choosing":[56],"which":[57,111],"module(s)":[58],"should":[59],"contribute":[60],"agent\u2019s":[63],"actions":[64],"at":[65],"any":[66],"particular":[67],"moment.":[68],"We":[69],"introduce":[70],"selection":[73,95],"mechanism":[74,96],"every":[76],"module,":[77],"besides":[78],"calculating":[79],"action":[83],"values,":[84],"also":[85],"estimates":[86],"its":[87],"own":[88],"error":[89],"current":[92],"input.":[93],"The":[94,133],"combines":[97],"module\u2019s":[99],"estimate":[100],"long-term":[102],"reward":[103],"and":[104,127],"self-error":[105],"produce":[107],"score":[109],"next":[113],"module":[114],"chosen.":[116],"As":[117],"result,":[119],"modules":[121,145],"can":[122],"use":[123,146],"their":[124],"resources":[125],"effectively":[126],"efficiently":[128],"divide":[129],"task.":[132],"shown":[136],"learn":[138],"complex":[139],"even":[141],"individual":[144],"only":[147],"linear":[148],"function":[149],"approximators.":[150],"1":[151]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}