乐胖代购免代理版

{"id":"https://openalex.org/W3150177537","doi":"https://doi.org/10.1109/lra.2021.3068655","title":"Batch Exploration With Examples for Scalable Robotic Reinforcement Learning","display_name":"Batch Exploration With Examples for Scalable Robotic Reinforcement Learning","publication_year":2021,"publication_date":"2021-03-24","ids":{"openalex":"https://openalex.org/W3150177537","doi":"https://doi.org/10.1109/lra.2021.3068655","mag":"3150177537"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3068655","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://arxiv.org/pdf/2010.11917","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028653594","display_name":"Annie S. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Annie S. Chen","raw_affiliation_strings":["Computer Science Department, Stanford University, Boulder, CO, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University, Boulder, CO, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075990123","display_name":"Hyunji Alex Nam","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"HyunJi Nam","raw_affiliation_strings":["Computer Science Department, Stanford University, Boulder, CO, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University, Boulder, CO, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101603882","display_name":"Suraj Nair","orcid":"https://orcid.org/0000-0002-3999-2436"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suraj Nair","raw_affiliation_strings":["Computer Science Department, Stanford University, Boulder, CO, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University, Boulder, CO, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005431772","display_name":"Chelsea Finn","orcid":"https://orcid.org/0000-0001-6298-0874"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chelsea Finn","raw_affiliation_strings":["Computer Science Department, Stanford University, Boulder, CO, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University, Boulder, CO, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.711,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":17,"citation_normalized_percentile":{"value":0.999972,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":92,"max":93},"biblio":{"volume":"6","issue":"3","first_page":"4401","last_page":"4408"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998,"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":0.9998,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9987,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9914,"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":0.65388054},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6514291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5991366},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.57295847},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5580972},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.55442876},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.46749178},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.46640885},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.44165656},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4338121},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13793194},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10865247},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.083732784},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07923517},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3068655","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11917","pdf_url":"http://arxiv.org/pdf/2010.11917","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2010.11917","pdf_url":"https://arxiv.org/pdf/2010.11917","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.2010.11917","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11917","pdf_url":"http://arxiv.org/pdf/2010.11917","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":["https://openalex.org/W3094387578","https://openalex.org/W3150177537"],"referenced_works_count":74,"referenced_works":["https://openalex.org/W106792269","https://openalex.org/W1502364872","https://openalex.org/W2034806191","https://openalex.org/W2108598243","https://openalex.org/W2158782408","https://openalex.org/W2160589914","https://openalex.org/W2201912979","https://openalex.org/W2336902217","https://openalex.org/W2340307996","https://openalex.org/W2417786368","https://openalex.org/W2528489519","https://openalex.org/W2561776174","https://openalex.org/W2751973545","https://openalex.org/W2765407302","https://openalex.org/W2788781499","https://openalex.org/W2789073708","https://openalex.org/W2806130867","https://openalex.org/W2810785043","https://openalex.org/W2884247313","https://openalex.org/W2886380958","https://openalex.org/W2896457183","https://openalex.org/W2896868419","https://openalex.org/W2902125520","https://openalex.org/W2914261249","https://openalex.org/W2937206389","https://openalex.org/W2938421504","https://openalex.org/W2949475445","https://openalex.org/W2952154767","https://openalex.org/W2952267586","https://openalex.org/W2952411203","https://openalex.org/W2953326529","https://openalex.org/W2953772919","https://openalex.org/W2962736495","https://openalex.org/W2962793652","https://openalex.org/W2962936820","https://openalex.org/W2963030226","https://openalex.org/W2963276097","https://openalex.org/W2963341956","https://openalex.org/W2963399829","https://openalex.org/W2963435596","https://openalex.org/W2963484919","https://openalex.org/W2963516265","https://openalex.org/W2963523627","https://openalex.org/W2963639957","https://openalex.org/W2964001908","https://openalex.org/W2964067469","https://openalex.org/W2964091568","https://openalex.org/W2964112890","https://openalex.org/W2964118020","https://openalex.org/W2966564143","https://openalex.org/W2974778612","https://openalex.org/W2981344907","https://openalex.org/W2997563738","https://openalex.org/W3004815632","https://openalex.org/W3012812419","https://openalex.org/W3014232838","https://openalex.org/W3022566517","https://openalex.org/W3028676366","https://openalex.org/W3032377877","https://openalex.org/W3034431214","https://openalex.org/W3035717769","https://openalex.org/W3035847478","https://openalex.org/W3040490156","https://openalex.org/W3090369311","https://openalex.org/W3099554858","https://openalex.org/W3101775375","https://openalex.org/W3107575247","https://openalex.org/W3113994363","https://openalex.org/W3130857053","https://openalex.org/W3153900373","https://openalex.org/W4235910938","https://openalex.org/W4287779179","https://openalex.org/W4298443378","https://openalex.org/W4300799055"],"related_works":["https://openalex.org/W4380318855","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4297873223","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2350784623","https://openalex.org/W2138720691","https://openalex.org/W2126211886","https://openalex.org/W2031695474"],"abstract_inverted_index":{"Learning":[0],"from":[1,111],"diverse":[2,208],"offline":[3,275],"datasets":[4],"is":[5,48,224],"a":[6,16,34,62,121,170,199,237],"promising":[7],"path":[8],"towards":[9],"learning":[10],"general":[11],"purpose":[12],"robotic":[13,106],"agents.":[14],"However,":[15],"core":[17],"challenge":[18,47,109],"in":[19,23,36,84,99,120,198,233,272],"this":[20,46,128],"paradigm":[21],"lies":[22],"collecting":[24],"large":[25],"amounts":[26],"of":[27,95,139,165,173,176,191,201],"meaningful":[28],"data,":[29],"while":[30],"not":[31],"depending":[32],"on":[33,135,236],"human":[35,147],"the":[37,92,96,136,140,166,189],"loop":[38],"for":[39,73],"data":[40,68,192],"collection.":[41],"One":[42],"way":[43],"to":[44,59,90,132,184,205,226,247],"address":[45],"through":[49],"task-agnostic":[52],"exploration":[53],",":[54],"where":[55],"an":[56,112,153],"agent":[57],"attempts":[58],"explore":[60,91],"without":[61],"task-specific":[63],"reward":[64],"function,":[65],"and":[66,194,235,243,249,264],"collect":[67,207],"that":[69,114,161,222,245],"can":[70,195,211],"be":[71,185,196,213],"useful":[72],"any":[74,216],"subsequent":[75,267],"task.":[76],"While":[77],"these":[78],"approaches":[79],"have":[80],"shown":[81],"some":[82],"promise":[83],"simple":[85],"domains,":[86],"they":[87],"often":[88,260],"struggle":[89],"relevant":[93,163,262],"regions":[94,164],"state":[97,124,141],"space":[98,142],"more":[100,256],"challenging":[101,228],"settings,":[102],"such":[103],"as":[104,259],"vision-based":[105,229],"manipulation.":[107],"This":[108],"stems":[110],"objective":[113],"encourages":[115],"exploring":[116],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">everything":[119],"potentially":[122],"vast":[123],"space.":[125],"To":[126],"mitigate":[127],"challenge,":[129],"we":[130,151],"propose":[131,152],"focus":[133],"exploration":[134,154,251],"important":[137,177],"parts":[138],"using":[143],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">weak":[146],"supervision":[148],".":[149],"Concretely,":[150],"technique,":[155],"Batch":[156],"Exploration":[157],"with":[158,215,261,274],"Examples":[159],"(BEE),":[160],"explores":[162],"state-space,":[167],"guided":[168],"by":[169],"modest":[171],"number":[172],"human-provided":[174,180],"images":[175,181],"states.":[178],"These":[179],"only":[182],"need":[183],"provided":[186],"once":[187],"at":[188],"beginning":[190],"collection":[193],"acquired":[197],"matter":[200],"minutes,":[202],"allowing":[203],"us":[204],"scalably":[206],"datasets,":[209],"which":[210],"then":[212],"combined":[214],"batch":[217],"RL":[218],"algorithm.":[219],"We":[220],"find":[221],"BEE":[223],"able":[225],"tackle":[227],"manipulation":[230],"tasks":[231],"both":[232],"simulation":[234],"real":[238],"Franka":[239],"Emika":[240],"Panda":[241],"robot,":[242],"observe":[244],"compared":[246],"task-agnostic":[248],"weakly-supervised":[250],"techniques,":[252],"it":[253],"(1)":[254],"interacts":[255],"than":[257],"twice":[258],"objects,":[263],"(2)":[265],"improves":[266],"task":[268],"performance":[269],"when":[270],"used":[271],"conjunction":[273],"RL.":[276]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3150177537","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2}],"updated_date":"2024-12-08T22:20:52.770771","created_date":"2021-04-13"}