{"id":"https://openalex.org/W2409942531","doi":"https://doi.org/10.1109/icra.2016.7487167","title":"SHIV: Reducing supervisor burden in DAgger using support vectors for efficient learning from demonstrations in high dimensional state spaces","display_name":"SHIV: Reducing supervisor burden in DAgger using support vectors for efficient learning from demonstrations in high dimensional state spaces","publication_year":2016,"publication_date":"2016-05-01","ids":{"openalex":"https://openalex.org/W2409942531","doi":"https://doi.org/10.1109/icra.2016.7487167","mag":"2409942531"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2016.7487167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2016.7487167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"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/A5052716347","display_name":"Michael Laskey","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Laskey","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013245211","display_name":"Sam Staszak","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Staszak","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045809024","display_name":"Wesley Yu-Shu Hsieh","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wesley Yu-Shu Hsieh","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020901032","display_name":"Jeffrey Mahler","orcid":"https://orcid.org/0000-0003-3204-3024"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Mahler","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018027629","display_name":"Florian T. Pokorny","orcid":"https://orcid.org/0000-0003-1114-6040"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian T. Pokorny","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005997281","display_name":"Anca D. Dragan","orcid":"https://orcid.org/0000-0001-6312-5466"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anca D. Dragan","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050342525","display_name":"Ken Goldberg","orcid":"https://orcid.org/0000-0002-2661-4524"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ken Goldberg","raw_affiliation_strings":["Department of Industrial Engineering and Operations Research, University of California Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Operations Research, University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5052716347"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":11.9972,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.98510115,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"462","last_page":"469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9914000034332275,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9914000034332275,"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":0.9911999702453613,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9878000020980835,"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/supervisor","display_name":"Supervisor","score":0.8180081844329834},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.582127571105957},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5427809357643127},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4947487711906433},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48474642634391785},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.48147693276405334},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4743582010269165},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.46863603591918945},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.45944228768348694},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4577729403972626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45359888672828674},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4515473246574402},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3839302062988281},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26027876138687134},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18198555707931519}],"concepts":[{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.8180081844329834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.582127571105957},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5427809357643127},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4947487711906433},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48474642634391785},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.48147693276405334},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4743582010269165},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.46863603591918945},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.45944228768348694},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4577729403972626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45359888672828674},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4515473246574402},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3839302062988281},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26027876138687134},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18198555707931519},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2016.7487167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2016.7487167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6600000262260437,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W33732390","https://openalex.org/W1522963174","https://openalex.org/W1552339598","https://openalex.org/W1560724230","https://openalex.org/W1568139284","https://openalex.org/W1580060102","https://openalex.org/W1606191265","https://openalex.org/W1931877416","https://openalex.org/W1974879849","https://openalex.org/W1980969546","https://openalex.org/W1986014385","https://openalex.org/W1991374750","https://openalex.org/W1999874108","https://openalex.org/W2015731569","https://openalex.org/W2018346149","https://openalex.org/W2101234009","https://openalex.org/W2119388568","https://openalex.org/W2132870739","https://openalex.org/W2137130182","https://openalex.org/W2137233422","https://openalex.org/W2140535827","https://openalex.org/W2142641780","https://openalex.org/W2142828048","https://openalex.org/W2151023586","https://openalex.org/W2151210636","https://openalex.org/W2154018708","https://openalex.org/W2155007355","https://openalex.org/W2167224731","https://openalex.org/W2169209873","https://openalex.org/W2295827790","https://openalex.org/W2912934387","https://openalex.org/W2962957031","https://openalex.org/W2964161785","https://openalex.org/W3144619878","https://openalex.org/W4212883601","https://openalex.org/W4230030242","https://openalex.org/W4285719527","https://openalex.org/W6601361519","https://openalex.org/W6634537505","https://openalex.org/W6640174482","https://openalex.org/W6675354045","https://openalex.org/W6680724558","https://openalex.org/W6680838405","https://openalex.org/W6680878686","https://openalex.org/W6682314434","https://openalex.org/W6682849425","https://openalex.org/W6684338915","https://openalex.org/W6685331716"],"related_works":["https://openalex.org/W4387731985","https://openalex.org/W2755149878","https://openalex.org/W2468425257","https://openalex.org/W2941808082","https://openalex.org/W2528721242","https://openalex.org/W4377009725","https://openalex.org/W4320164562","https://openalex.org/W2356364326","https://openalex.org/W4379086698","https://openalex.org/W2372069567"],"abstract_inverted_index":{"Online":[0],"learning":[1],"from":[2],"demonstration":[3],"algorithms":[4],"such":[5],"as":[6],"DAgger":[7],"can":[8,170],"learn":[9,172],"policies":[10,173],"for":[11],"problems":[12],"where":[13],"the":[14,18,36,67],"system":[15],"dynamics":[16],"and":[17,61,81,94,154],"cost":[19],"function":[20],"are":[21],"unknown.":[22],"However":[23],"they":[24],"impose":[25],"a":[26,78,101,118,132,136,143,149,161],"burden":[27,52,84],"on":[28,100,126],"supervisors":[29],"to":[30,32,77,110,176],"respond":[31],"queries":[33,55,179],"each":[34],"time":[35],"robot":[37],"encounters":[38],"new":[39],"states":[40],"while":[41],"executing":[42],"its":[43],"current":[44],"best":[45],"policy.":[46],"The":[47],"MMD-IL":[48],"algorithm":[49,69],"reduces":[50,82],"supervisor":[51,83],"by":[53,117],"filtering":[54,97],"with":[56,135,148,160,174],"insufficient":[57],"discrepancy":[58],"in":[59,72,85,106,128,145],"distribution":[60],"maintaining":[62],"multiple":[63],"policies.":[64],"We":[65,124],"introduce":[66],"SHIV":[68,169],"(Svm-based":[70],"reduction":[71],"Human":[73],"InterVention),":[74],"which":[75],"converges":[76],"single":[79],"policy":[80],"non-stationary":[86],"high":[87],"dimensional":[88,138,151,163],"state":[89,152,164],"distributions.":[90],"To":[91],"facilitate":[92],"scaling":[93],"outlier":[95],"rejection,":[96],"is":[98],"based":[99],"measure":[102],"of":[103,108],"risk":[104],"defined":[105,116],"terms":[107],"distance":[109],"an":[111],"approximate":[112],"level":[113],"set":[114],"boundary":[115],"One":[119],"Class":[120],"support":[121],"vector":[122],"machine.":[123],"report":[125],"experiments":[127],"three":[129],"contexts:":[130],"1)":[131],"driving":[133],"simulator":[134],"27,936":[137],"visual":[139],"feature":[140],"space,":[141,153],"2)":[142],"push-grasping":[144],"clutter":[146],"simulation":[147],"22":[150],"3)":[155],"physical":[156],"surgical":[157],"needle":[158],"insertion":[159],"16":[162],"space.":[165],"Results":[166],"suggest":[167],"that":[168,180],"efficiently":[171],"up":[175],"70%":[177],"fewer":[178],"DAgger.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}