乐胖代购免代理版

{"id":"https://openalex.org/W2151620419","doi":"https://doi.org/10.1111/coin.12016","title":"EFFICIENT ABSTRACTION SELECTION IN REINFORCEMENT LEARNING","display_name":"EFFICIENT ABSTRACTION SELECTION IN REINFORCEMENT LEARNING","publication_year":2013,"publication_date":"2013-08-06","ids":{"openalex":"https://openalex.org/W2151620419","doi":"https://doi.org/10.1111/coin.12016","mag":"2151620419"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1111/coin.12016","pdf_url":null,"source":{"id":"https://openalex.org/S56561474","display_name":"Computational Intelligence","issn_l":"0824-7935","issn":["0824-7935","1467-8640"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/A5049195732","display_name":"Harm van Seijen","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Harm van Seijen","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, AB, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056879203","display_name":"Shimon Whiteson","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Shimon Whiteson","raw_affiliation_strings":["Informatics Institute, University of Amsterdam, Amsterdam, the Netherlands"],"affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam, Amsterdam, the Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071357791","display_name":"Leon Kester","orcid":"https://orcid.org/0000-0002-8565-3902"},"institutions":[{"id":"https://openalex.org/I4210094335","display_name":"Ministry of Defence","ror":"https://ror.org/0079deh61","country_code":"NL","type":"government","lineage":["https://openalex.org/I4210094335","https://openalex.org/I4210140876"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Leon Kester","raw_affiliation_strings":["Distributed Sensor Systems Group, TNO Defence, Security and Safety, The Hague, the Netherlands"],"affiliations":[{"raw_affiliation_string":"Distributed Sensor Systems Group, TNO Defence, Security and Safety, The Hague, the Netherlands","institution_ids":["https://openalex.org/I4210094335"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049195732"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":{"value":3450,"currency":"USD","value_usd":3450,"provenance":"doaj"},"apc_paid":null,"fwci":1.512,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.901239,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":88},"biblio":{"volume":"30","issue":"4","first_page":"657","last_page":"699"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997,"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":0.9997,"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":0.9893,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9889,"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/abstraction","display_name":"Abstraction","score":0.8120711},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.6719279}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8260465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.81209254},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.8120711},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.79103863},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.6719279},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6110468},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5807076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.56439483},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5537},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46067604},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.45869344},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.44388032},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35266888},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.34353808},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.169884},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0875738},{"id":"https://openalex.org/C108170787","wikidata":"https://www.wikidata.org/wiki/Q3951828","display_name":"Agency (philosophy)","level":2,"score":0.0795359},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1111/coin.12016","pdf_url":null,"source":{"id":"https://openalex.org/S56561474","display_name":"Computational Intelligence","issn_l":"0824-7935","issn":["0824-7935","1467-8640"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.66,"display_name":"Peace, justice, and strong institutions"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":52,"referenced_works":["https://openalex.org/W1491843047","https://openalex.org/W1505937442","https://openalex.org/W1515851193","https://openalex.org/W1537180453","https://openalex.org/W1553182805","https://openalex.org/W1554015367","https://openalex.org/W1583380718","https://openalex.org/W1640646391","https://openalex.org/W1650504995","https://openalex.org/W1678414046","https://openalex.org/W183249136","https://openalex.org/W1997477668","https://openalex.org/W2009551863","https://openalex.org/W2020294948","https://openalex.org/W2020609518","https://openalex.org/W2048226872","https://openalex.org/W2058735307","https://openalex.org/W2073384958","https://openalex.org/W2076337359","https://openalex.org/W2097381042","https://openalex.org/W2100677568","https://openalex.org/W2101133635","https://openalex.org/W2107726111","https://openalex.org/W2109910161","https://openalex.org/W2110575115","https://openalex.org/W2112899086","https://openalex.org/W2117423905","https://openalex.org/W2118022839","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2127323769","https://openalex.org/W2138859735","https://openalex.org/W2150339816","https://openalex.org/W2165131254","https://openalex.org/W2168175751","https://openalex.org/W2168405694","https://openalex.org/W2293743194","https://openalex.org/W2341171179","https://openalex.org/W2488247662","https://openalex.org/W2489939061","https://openalex.org/W2519411794","https://openalex.org/W2568646110","https://openalex.org/W2610818722","https://openalex.org/W3041202696","https://openalex.org/W32403112","https://openalex.org/W4211221179","https://openalex.org/W4214717370","https://openalex.org/W4244566287","https://openalex.org/W4245108548","https://openalex.org/W4285719527","https://openalex.org/W46877293","https://openalex.org/W79394677"],"related_works":["https://openalex.org/W4388236136","https://openalex.org/W4255368532","https://openalex.org/W4200250224","https://openalex.org/W2947128950","https://openalex.org/W2807018115","https://openalex.org/W273478400","https://openalex.org/W2285658092","https://openalex.org/W2162286586","https://openalex.org/W2126560268","https://openalex.org/W187740018"],"abstract_inverted_index":{"This":[0],"article":[1],"addresses":[2],"reinforcement":[3],"learning":[4,74],"problems":[5],"based":[6],"on":[7],"factored":[8],"Markov":[9],"decision":[10],"processes":[11],"(MDPs)":[12],"in":[13,102,128],"which":[14],"the":[15,62,73,80,89,110,114,118],"agent":[16],"must":[17],"choose":[18],"among":[19],"a":[20,30,40,103],"set":[21],"of":[22,33,61,68,72,131],"candidate":[23],"abstractions":[24],",":[25],"each":[26],"build":[27],"up":[28],"from":[29],"different":[31],"combination":[32],"state":[34],"components.":[35],"We":[36,93,124],"present":[37],"and":[38,117,139],"evaluate":[39],"new":[41],"approach":[42,63,100,127],"that":[43,49,87,95,122],"can":[44],"perform":[45],"effective":[46],"abstraction":[47,70,90,112],"selection":[48,67],"is":[50,64],"more":[51,54],"resource\u2010efficient":[52],"and/or":[53],"general":[55,140],"than":[56],"existing":[57],"approaches.":[58],"The":[59],"core":[60],"to":[65],"make":[66],"an":[69],"part":[71],"agent's":[75,81],"decision\u2010making":[76],"process":[77],"by":[78],"augmenting":[79],"action":[82],"space":[83],"with":[84,142],"internal":[85],"actions":[86],"select":[88],"it":[91],"uses.":[92],"prove":[94],"under":[96,121],"certain":[97],"conditions":[98],"this":[99],"results":[101],"derived":[104],"MDP":[105,116],"whose":[106],"solution":[107],"yields":[108],"both":[109],"optimal":[111,119],"for":[113],"original":[115],"policy":[120],"abstraction.":[123],"examine":[125],"our":[126],"three":[129],"domains":[130],"increasing":[132],"complexity:":[133],"contextual":[134],"bandit":[135],"problems,":[136],"episodic":[137],"MDPs,":[138],"MDPs":[141],"context\u2010specific":[143],"structure.":[144],"\u00a9":[145],"2013":[146],"Wiley":[147],"Periodicals,":[148],"Inc.":[149]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2151620419","counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2024-12-10T01:52:17.498691","created_date":"2016-06-24"}