乐胖代购免代理版

{"id":"https://openalex.org/W2605369401","doi":"https://doi.org/10.1609/aaai.v31i1.10796","title":"Transfer Reinforcement Learning with Shared Dynamics","display_name":"Transfer Reinforcement Learning with Shared Dynamics","publication_year":2017,"publication_date":"2017-02-13","ids":{"openalex":"https://openalex.org/W2605369401","doi":"https://doi.org/10.1609/aaai.v31i1.10796","mag":"2605369401"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v31i1.10796","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/10796/10655","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/10796/10655","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089214987","display_name":"Romain Laroche","orcid":"https://orcid.org/0000-0001-7180-2746"},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Romain Laroche","raw_affiliation_strings":["Orange Labs at Ch\u00e2tillon"],"affiliations":[{"raw_affiliation_string":"Orange Labs at Ch\u00e2tillon","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044958229","display_name":"Merwan Barlier","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Merwan Barlier","raw_affiliation_strings":["Orange Labs at Ch\u00e2tillon"],"affiliations":[{"raw_affiliation_string":"Orange Labs at Ch\u00e2tillon","institution_ids":["https://openalex.org/I19370010"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.669,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":65,"citation_normalized_percentile":{"value":0.926817,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"31","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9999,"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":0.9999,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9958,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T12288","display_name":"Optimization and Search Problems","score":0.992,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/dynamics","display_name":"Dynamics","score":0.6134197},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.49396068},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.46524724},{"id":"https://openalex.org/keywords/negative-transfer","display_name":"Negative transfer","score":0.43445098}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.806608},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.76366866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.69490874},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.6134197},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.60294414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5940817},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.53144354},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4940484},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.49396068},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.46524724},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4540518},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.44053718},{"id":"https://openalex.org/C2779178101","wikidata":"https://www.wikidata.org/wiki/Q6987274","display_name":"Negative transfer","level":3,"score":0.43445098},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18233338},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16420668},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12299368},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10377008},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08684516},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v31i1.10796","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/10796/10655","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-01548649","pdf_url":"https://hal.science/hal-01548649/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://hal.science/hal-01548649/file/aaai-multi-task%281%29.pdf","pdf_url":"https://hal.science/hal-01548649/file/aaai-multi-task%281%29.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-01548649/document","pdf_url":"https://hal.archives-ouvertes.fr/hal-01548649/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-01548649/file/aaai-multi-task%281%29.pdf","pdf_url":"https://hal.archives-ouvertes.fr/hal-01548649/file/aaai-multi-task%281%29.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v31i1.10796","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/10796/10655","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":35,"referenced_works":["https://openalex.org/W1542595278","https://openalex.org/W1563853427","https://openalex.org/W158722652","https://openalex.org/W16011919","https://openalex.org/W1701974503","https://openalex.org/W1757796397","https://openalex.org/W2027184806","https://openalex.org/W2048226872","https://openalex.org/W2061562262","https://openalex.org/W2097381042","https://openalex.org/W2097931172","https://openalex.org/W2117629901","https://openalex.org/W2120346334","https://openalex.org/W2121044470","https://openalex.org/W2133040789","https://openalex.org/W2145339207","https://openalex.org/W2160589914","https://openalex.org/W2161966552","https://openalex.org/W2257979135","https://openalex.org/W2294805292","https://openalex.org/W2407709678","https://openalex.org/W2440926996","https://openalex.org/W2476025067","https://openalex.org/W2489939061","https://openalex.org/W2514775068","https://openalex.org/W2951333509","https://openalex.org/W2962767126","https://openalex.org/W2964200634","https://openalex.org/W30493077","https://openalex.org/W4211221179","https://openalex.org/W4245108548","https://openalex.org/W4285719527","https://openalex.org/W4298857966","https://openalex.org/W4299431168","https://openalex.org/W4300554125"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2952841984","https://openalex.org/W2920061524","https://openalex.org/W2619137770","https://openalex.org/W2398668521","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2086122291","https://openalex.org/W2038908348","https://openalex.org/W1977959518"],"abstract_inverted_index":{"This":[0],"article":[1],"addresses":[2],"a":[3,41,59,101,111,127,137,153],"particular":[4],"Transfer":[5,106],"Reinforcement":[6],"Learning":[7],"(RL)":[8],"problem:":[9],"when":[10],"dynamics":[11],"do":[12],"not":[13],"change":[14],"from":[15,40],"one":[16,34],"task":[17,42],"to":[18,46,90],"another,":[19],"and":[20,62,89,117,125,141],"only":[21],"the":[22,32,66,81,84,122,144],"reward":[23,54,67,73,94,113,123,130],"function":[24],"does.":[25],"Our":[26,96],"method":[27,97,151],"relies":[28],"on":[29,48,100,121],"two":[30],"ideas,":[31],"first":[33],"is":[35,56,69,98,133],"that":[36,149,159],"transition":[37],"samples":[38],"obtained":[39],"can":[43],"be":[44],"reused":[45],"learn":[47],"any":[49],"other":[50],"task:":[51],"an":[52],"immediate":[53],"estimator":[55],"learnt":[57],"in":[58,79,83,136],"supervised":[60],"fashion":[61],"for":[63,156],"each":[64],"sample,":[65],"entry":[68],"changed":[70],"by":[71],"its":[72],"estimate.":[74],"The":[75],"second":[76],"idea":[77],"consists":[78],"adopting":[80],"optimism":[82],"face":[85],"of":[86],"uncertainty":[87],"principle":[88],"use":[91],"upper":[92],"bound":[93],"estimates.":[95],"tested":[99],"navigation":[102],"task,":[103],"under":[104],"four":[105],"RL":[107,139],"experimental":[108],"settings:":[109],"with":[110,115,126,143],"known":[112],"function,":[114,124],"strong":[116],"weak":[118],"expert":[119],"knowledge":[120],"completely":[128],"unknown":[129],"function.":[131],"It":[132],"also":[134],"evaluated":[135],"Multi-Task":[138],"experiment":[140],"compared":[142],"state-of-the-art":[145],"algorithms.":[146],"Results":[147],"reveal":[148],"this":[150],"constitutes":[152],"major":[154],"improvement":[155],"transfer/multi-task":[157],"problems":[158],"share":[160],"dynamics.":[161]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2605369401","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":33},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1}],"updated_date":"2025-01-16T11:38:00.533892","created_date":"2017-04-14"}