乐胖代购免代理版

{"id":"https://openalex.org/W2996784529","doi":"https://doi.org/10.1609/aaai.v34i03.5636","title":"Learning to Interactively Learn and Assist","display_name":"Learning to Interactively Learn and Assist","publication_year":2020,"publication_date":"2020-04-03","ids":{"openalex":"https://openalex.org/W2996784529","doi":"https://doi.org/10.1609/aaai.v34i03.5636","mag":"2996784529"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v34i03.5636","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5636/5492","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_indexed_in_scopus":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":"gold","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5636/5492","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054619000","display_name":"Mark P. Woodward","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"funder","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Woodward","raw_affiliation_strings":["Google Brain"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005431772","display_name":"Chelsea Finn","orcid":"https://orcid.org/0000-0001-6298-0874"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"funder","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chelsea Finn","raw_affiliation_strings":["Google Brain"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088777896","display_name":"Karol Hausman","orcid":"https://orcid.org/0000-0002-1504-6197"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"funder","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karol Hausman","raw_affiliation_strings":["Google Brain"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.356,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":20,"citation_normalized_percentile":{"value":0.999916,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":92},"biblio":{"volume":"34","issue":"03","first_page":"2535","last_page":"2543"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9856,"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":0.9856,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9729,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.965,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72244936},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6745875},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6623101},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5864592},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.58093256},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5622807},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5577578},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.51838595},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.48115695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38873723},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10481593},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v34i03.5636","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5636/5492","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_indexed_in_scopus":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://arxiv.org/abs/1906.10187","pdf_url":"https://arxiv.org/pdf/1906.10187","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v34i03.5636","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5636/5492","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_indexed_in_scopus":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":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.6}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":45,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1555689267","https://openalex.org/W1931877416","https://openalex.org/W197704362","https://openalex.org/W1999874108","https://openalex.org/W2116372557","https://openalex.org/W2121092017","https://openalex.org/W2123399796","https://openalex.org/W2166302491","https://openalex.org/W2395575420","https://openalex.org/W2410842990","https://openalex.org/W2578206533","https://openalex.org/W2601322194","https://openalex.org/W2602275733","https://openalex.org/W2604726708","https://openalex.org/W2604763608","https://openalex.org/W2617547828","https://openalex.org/W2698595662","https://openalex.org/W2734878594","https://openalex.org/W2745881055","https://openalex.org/W2768629321","https://openalex.org/W2787053496","https://openalex.org/W2788862220","https://openalex.org/W2893649979","https://openalex.org/W2898621619","https://openalex.org/W2951262671","https://openalex.org/W2951799221","https://openalex.org/W2963391602","https://openalex.org/W2963489214","https://openalex.org/W2963571918","https://openalex.org/W2964774183","https://openalex.org/W2966994213","https://openalex.org/W3011120880","https://openalex.org/W3089050900","https://openalex.org/W4214717370","https://openalex.org/W4288593469","https://openalex.org/W4289288058","https://openalex.org/W4293407356","https://openalex.org/W4295846245","https://openalex.org/W4298857966","https://openalex.org/W4299802797","https://openalex.org/W4300971732","https://openalex.org/W4321392130","https://openalex.org/W4387725652","https://openalex.org/W4394651137"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W2665305151","https://openalex.org/W1531601525"],"abstract_inverted_index":{"When":[0],"deploying":[1],"autonomous":[2],"agents":[3],"in":[4],"the":[5,32,38,41,76,86,164,174,231],"real":[6],"world,":[7],"we":[8,131,147,172,190],"need":[9],"effective":[10],"ways":[11],"of":[12,34,100,104,170,176,179,201,211],"communicating":[13],"objectives":[14,93],"to":[15,53,116,139,157],"them.":[16],"Traditional":[17],"skill":[18],"learning":[19,135,181,202],"has":[20],"revolved":[21],"around":[22],"reinforcement":[23],"and":[24,40,55,65,70,110,186,218],"imitation":[25],"learning,":[26,114],"each":[27,95],"with":[28,94,125,224],"rigid":[29],"constraints":[30],"on":[31],"format":[33],"information":[35,59,83],"exchanged":[36],"between":[37],"human":[39,77,206,226,229],"agent.":[42,87],"While":[43],"scalar":[44],"rewards":[45,64],"carry":[46,57],"little":[47],"information,":[48],"demonstrations":[49,66,213],"require":[50],"significant":[51],"effort":[52],"provide":[54],"may":[56],"more":[58],"than":[60,227],"is":[61,78,199],"necessary.":[62],"Furthermore,":[63],"are":[67],"often":[68,111],"defined":[69],"collected":[71],"before":[72],"training":[73,151],"begins,":[74],"when":[75,90],"most":[79],"uncertain":[80],"about":[81],"what":[82],"would":[84],"help":[85],"In":[88,119,128],"contrast,":[89],"humans":[91,122],"communicate":[92,112,123],"other,":[96],"they":[97],"make":[98],"use":[99],"a":[101,149,168,177,205,209,215,225,228],"large":[102],"vocabulary":[103],"informative":[105],"behaviors,":[106,182],"including":[107,183],"non-verbal":[108],"communication,":[109],"throughout":[113],"responding":[115],"observed":[117],"behavior.":[118],"this":[120,129],"way,":[121],"intent":[124],"minimal":[126],"effort.":[127],"paper,":[130],"propose":[132],"such":[133],"interactive":[134,180],"as":[136],"an":[137,155,196],"alternative":[138],"reward":[140,216],"or":[141,214],"demonstration-driven":[142],"learning.":[143],"To":[144],"accomplish":[145],"this,":[146],"introduce":[148],"multi-agent":[150],"framework":[152],"that":[153,192,198],"enables":[154],"agent":[156,161,197],"learn":[158],"from":[159,204],"another":[160],"who":[162],"knows":[163],"current":[165],"task.":[166],"Through":[167],"series":[169],"experiments,":[171],"demonstrate":[173],"emergence":[175],"variety":[178],"information-sharing,":[184],"information-seeking,":[185],"question-answering.":[187],"Most":[188],"importantly,":[189],"find":[191],"our":[193],"approach":[194],"produces":[195],"capable":[200],"interactively":[203],"user,":[207],"without":[208],"set":[210],"explicit":[212],"function,":[217],"achieving":[219],"significantly":[220],"better":[221],"performance":[222],"cooperatively":[223],"performing":[230],"task":[232],"alone.":[233]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2996784529","counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4}],"updated_date":"2025-04-17T11:27:49.309603","created_date":"2020-01-10"}