{"id":"https://openalex.org/W2883140436","doi":"https://doi.org/10.1177/0278364918784350","title":"SWIRL: A sequential windowed inverse reinforcement learning algorithm for robot tasks with delayed rewards","display_name":"SWIRL: A sequential windowed inverse reinforcement learning algorithm for robot tasks with delayed rewards","publication_year":2018,"publication_date":"2018-07-25","ids":{"openalex":"https://openalex.org/W2883140436","doi":"https://doi.org/10.1177/0278364918784350","mag":"2883140436"},"language":"en","primary_location":{"id":"doi:10.1177/0278364918784350","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0278364918784350","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-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/A5018480426","display_name":"Sanjay Krishnan","orcid":"https://orcid.org/0000-0001-6968-4090"},"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":"Sanjay Krishnan","raw_affiliation_strings":["AUTOLAB, University of California, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AUTOLAB, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061193324","display_name":"Animesh Garg","orcid":"https://orcid.org/0000-0003-0482-4296"},"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"]},{"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":"Animesh Garg","raw_affiliation_strings":["AUTOLAB, University of California, Berkeley, USA","Stanford University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AUTOLAB, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075667645","display_name":"Richard Liaw","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":"Richard Liaw","raw_affiliation_strings":["AUTOLAB, University of California, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AUTOLAB, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055891784","display_name":"Brijen Thananjeyan","orcid":"https://orcid.org/0000-0003-1841-5071"},"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":"Brijen Thananjeyan","raw_affiliation_strings":["AUTOLAB, University of California, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AUTOLAB, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021534233","display_name":"Lauren Miller","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":"Lauren Miller","raw_affiliation_strings":["AUTOLAB, University of California, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AUTOLAB, University of California, Berkeley, 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/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Florian T Pokorny","raw_affiliation_strings":["RPL/CSC, KTH Royal Institute of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RPL/CSC, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"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":["AUTOLAB, University of California, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AUTOLAB, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5018480426"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":5.244,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.96068407,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"38","issue":"2-3","first_page":"126","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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":0.9951000213623047,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7996572256088257},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6915445327758789},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.614925742149353},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5554665327072144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5220546722412109},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.489631712436676},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.45286744832992554},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.4106118083000183},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3204330503940582},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17456179857254028},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.17078319191932678},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11446774005889893}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7996572256088257},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6915445327758789},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.614925742149353},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5554665327072144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5220546722412109},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.489631712436676},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.45286744832992554},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.4106118083000183},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3204330503940582},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17456179857254028},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.17078319191932678},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11446774005889893},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/0278364918784350","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0278364918784350","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320312083","display_name":"Intuitive Surgical","ror":"https://ror.org/05g2n4m79"},{"id":"https://openalex.org/F4320337373","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W158183001","https://openalex.org/W225768461","https://openalex.org/W979233906","https://openalex.org/W1482341360","https://openalex.org/W1507087299","https://openalex.org/W1584687743","https://openalex.org/W1592847719","https://openalex.org/W1777239053","https://openalex.org/W1777783943","https://openalex.org/W1941445455","https://openalex.org/W1963873191","https://openalex.org/W1986014385","https://openalex.org/W1999303932","https://openalex.org/W1999874108","https://openalex.org/W2016482167","https://openalex.org/W2022760091","https://openalex.org/W2054661770","https://openalex.org/W2061417916","https://openalex.org/W2061562262","https://openalex.org/W2066436114","https://openalex.org/W2085679424","https://openalex.org/W2090110089","https://openalex.org/W2091797369","https://openalex.org/W2097856935","https://openalex.org/W2098774185","https://openalex.org/W2101448784","https://openalex.org/W2105947986","https://openalex.org/W2109910161","https://openalex.org/W2113122939","https://openalex.org/W2121517924","https://openalex.org/W2123967136","https://openalex.org/W2127844098","https://openalex.org/W2129202194","https://openalex.org/W2131960487","https://openalex.org/W2135043890","https://openalex.org/W2139688922","https://openalex.org/W2145087262","https://openalex.org/W2145339207","https://openalex.org/W2148606162","https://openalex.org/W2159323809","https://openalex.org/W2161395589","https://openalex.org/W2199215277","https://openalex.org/W2201912979","https://openalex.org/W2211996086","https://openalex.org/W2285373626","https://openalex.org/W2415633882","https://openalex.org/W2528489519","https://openalex.org/W2608651664","https://openalex.org/W2743603832","https://openalex.org/W2963826370","https://openalex.org/W3101780148","https://openalex.org/W4210700398","https://openalex.org/W4214717370","https://openalex.org/W4234230169","https://openalex.org/W4248990817"],"related_works":["https://openalex.org/W962423920","https://openalex.org/W2387968248","https://openalex.org/W2120821724","https://openalex.org/W2350715914","https://openalex.org/W2379529020","https://openalex.org/W2101175215","https://openalex.org/W2893549521","https://openalex.org/W1562157883","https://openalex.org/W2330311678","https://openalex.org/W2352322616"],"abstract_inverted_index":{"We":[0,24,95,136],"present":[1],"sequential":[2],"windowed":[3],"inverse":[4],"reinforcement":[5,82],"learning":[6,27,83],"(SWIRL),":[7],"a":[8,14,29,43,49,67,93,106,149,161,169],"policy":[9,68],"search":[10],"algorithm":[11],"that":[12,69,74],"is":[13],"hybrid":[15],"of":[16,32,51,130,171],"exploration":[17],"and":[18,55,84,105,128,144],"demonstration":[19],"paradigms":[20],"for":[21],"robot":[22],"learning.":[23],"apply":[25],"unsupervised":[26],"to":[28,36,65,91],"small":[30],"number":[31],"initial":[33],"expert":[34,86],"demonstrations":[35,87,131],"structure":[37],"future":[38],"autonomous":[39],"exploration.":[40],"SWIRL":[41,62,75,97,114,159],"approximates":[42],"long":[44],"time":[45],"horizon":[46],"task":[47,121],"as":[48],"sequence":[50],"local":[52],"reward":[53,118,166],"functions":[54],"subtask":[56],"transition":[57],"conditions.":[58],"Over":[59],"this":[60],"approximation,":[61],"applies":[63],"Q-learning":[64],"compute":[66],"maximizes":[70],"rewards.":[71],"Experiments":[72],"suggest":[73],"requires":[76],"significantly":[77],"fewer":[78,85,124],"rollouts":[79,125],"than":[80,88,126],"pure":[81],"behavioral":[89,134,172],"cloning":[90,173],"learn":[92],"policy.":[94],"evaluate":[96],"in":[98,165],"two":[99],"simulated":[100],"control":[101],"tasks,":[102],"parallel":[103,111],"parking":[104,112],"two-link":[107],"pendulum.":[108],"On":[109,154],"the":[110,116,120,155],"task,":[113,158],"achieves":[115,160],"maximum":[117],"on":[119,141],"with":[122,168,174],"85%":[123],"Q-learning,":[127],"one-eight":[129],"needed":[132],"by":[133],"cloning.":[135],"also":[137],"consider":[138],"physical":[139],"experiments":[140],"surgical":[142,152],"tensioning":[143,157],"cutting":[145],"deformable":[146,156],"sheets":[147],"using":[148],"da":[150],"Vinci":[151],"robot.":[153],"36%":[162],"relative":[163],"improvement":[164],"compared":[167],"baseline":[170],"segmentation.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-05-27T09:02:27.158192","created_date":"2025-10-10T00:00:00"}
