{"id":"https://openalex.org/W3185291728","doi":"https://doi.org/10.1109/icra48506.2021.9561411","title":"Self-Imitation Learning by Planning","display_name":"Self-Imitation Learning by Planning","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3185291728","doi":"https://doi.org/10.1109/icra48506.2021.9561411","mag":"3185291728"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.rug.nl/en/publications/f675f548-3969-407a-96e8-52f97395e67f","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014099627","display_name":"Sha Luo","orcid":"https://orcid.org/0000-0001-8942-8350"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Sha Luo","raw_affiliation_strings":["Department of Artificial Intelligence, University of Groningen, the Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, University of Groningen, the Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008655688","display_name":"Hamidreza Kasaei","orcid":"https://orcid.org/0000-0001-9408-7730"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hamidreza Kasaei","raw_affiliation_strings":["Department of Artificial Intelligence, University of Groningen, the Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, University of Groningen, the Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028858025","display_name":"Lambert Schomaker","orcid":"https://orcid.org/0000-0003-2351-930X"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lambert Schomaker","raw_affiliation_strings":["Department of Artificial Intelligence, University of Groningen, the Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, University of Groningen, the Netherlands","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014099627"],"corresponding_institution_ids":["https://openalex.org/I169381384"],"apc_list":null,"apc_paid":null,"fwci":2.0794,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.8696549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4823","last_page":"4829"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8571240901947021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7102190256118774},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.6499759554862976},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6422819495201111},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.6359330415725708},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6201735138893127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5896807909011841},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5481517314910889},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5207326412200928},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4731629490852356},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.442434161901474},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.4242090880870819},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4179014563560486},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39938926696777344},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35617631673812866},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14160624146461487},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.10775503516197205}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8571240901947021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7102190256118774},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.6499759554862976},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6422819495201111},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.6359330415725708},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6201735138893127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5896807909011841},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5481517314910889},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5207326412200928},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4731629490852356},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.442434161901474},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4242090880870819},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4179014563560486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39938926696777344},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35617631673812866},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14160624146461487},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.10775503516197205},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra48506.2021.9561411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:rug:oai:pure.rug.nl:publications/f675f548-3969-407a-96e8-52f97395e67f","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/f675f548-3969-407a-96e8-52f97395e67f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA), 4823 - 4829","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"pmh:rug:oai:pure.rug.nl:publications/f675f548-3969-407a-96e8-52f97395e67f","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/f675f548-3969-407a-96e8-52f97395e67f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA), 4823 - 4829","raw_type":"info:eu-repo/semantics/conferencepaper"},"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1931877416","https://openalex.org/W1999874108","https://openalex.org/W2012392077","https://openalex.org/W2068127265","https://openalex.org/W2085583171","https://openalex.org/W2099987996","https://openalex.org/W2118426345","https://openalex.org/W2128990851","https://openalex.org/W2142641780","https://openalex.org/W2142828048","https://openalex.org/W2167117957","https://openalex.org/W2169209873","https://openalex.org/W2173248099","https://openalex.org/W2738669288","https://openalex.org/W2741122588","https://openalex.org/W2781726626","https://openalex.org/W2788862220","https://openalex.org/W2789835518","https://openalex.org/W2804380964","https://openalex.org/W2810785043","https://openalex.org/W2904246096","https://openalex.org/W2912063360","https://openalex.org/W2922572893","https://openalex.org/W2962957031","https://openalex.org/W2963376229","https://openalex.org/W2963411833","https://openalex.org/W2963572779","https://openalex.org/W2963864421","https://openalex.org/W2964001908","https://openalex.org/W2964062135","https://openalex.org/W2967820818","https://openalex.org/W2967969632","https://openalex.org/W2970720334","https://openalex.org/W2994446013","https://openalex.org/W3003852841","https://openalex.org/W3005431655","https://openalex.org/W3022566517","https://openalex.org/W3036170014","https://openalex.org/W3038249833","https://openalex.org/W3069663381","https://openalex.org/W3089353688","https://openalex.org/W3100868156","https://openalex.org/W4256184360","https://openalex.org/W4288331462","https://openalex.org/W4293396018","https://openalex.org/W4300799055","https://openalex.org/W6640174482","https://openalex.org/W6653435097","https://openalex.org/W6675080091","https://openalex.org/W6680724558","https://openalex.org/W6684921986","https://openalex.org/W6685331716","https://openalex.org/W6740801417","https://openalex.org/W6742461812","https://openalex.org/W6744563498","https://openalex.org/W6747473740","https://openalex.org/W6748645729","https://openalex.org/W6751540476","https://openalex.org/W6753243525","https://openalex.org/W6757592117","https://openalex.org/W6764173040","https://openalex.org/W6776438516","https://openalex.org/W6780117753","https://openalex.org/W6782245617"],"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/W1531601525","https://openalex.org/W804484174"],"abstract_inverted_index":{"Imitation":[0],"learning":[1,19,69,103],"(IL)":[2],"enables":[3],"robots":[4],"to":[5,21,41,129,173],"acquire":[6],"skills":[7],"quickly":[8],"by":[9,70,79,92,145],"transferring":[10],"expert":[11],"knowledge,":[12],"which":[13],"is":[14,39,90],"widely":[15],"adopted":[16],"in":[17,25,33,99,108,150,180,184],"reinforcement":[18,102],"(RL)":[20],"initialize":[22],"exploration.":[23],"However,":[24],"long-horizon":[26],"motion":[27,112,153],"planning":[28,71,80,154],"tasks,":[29],"a":[30,185],"challenging":[31],"problem":[32,62],"deploying":[34],"IL":[35,146],"and":[36,43,118,147,168,176,192],"RL":[37,148],"methods":[38,52,149],"how":[40],"generate":[42],"collect":[44],"massive,":[45],"broadly":[46],"distributed":[47],"data":[48,75,141],"such":[49],"that":[50,95,160],"these":[51,130],"can":[53,116],"generalize":[54],"effectively.":[55],"In":[56],"this":[57,61],"work,":[58],"we":[59,115,133],"solve":[60],"using":[63],"our":[64,161],"proposed":[65],"approach":[66],"called":[67],"self-imitation":[68],"(SILP),":[72],"where":[73],"demonstration":[74],"are":[76,105],"collected":[77],"automatically":[78],"on":[81],"the":[82,86,93,100,109,135,139,177],"visited":[83,97],"states":[84,98],"from":[85,138],"current":[87],"policy.":[88],"SILP":[89,162],"inspired":[91],"observation":[94],"successfully":[96],"early":[101],"stage":[104],"collision-free":[106],"nodes":[107],"graph-search":[110],"based":[111],"planner,":[113],"so":[114],"plan":[117],"relabel":[119],"robot's":[120],"own":[121],"trials":[122],"as":[123],"demonstrations":[124],"for":[125],"policy":[126,178],"learning.":[127],"Due":[128],"self-generated":[131],"demonstrations,":[132],"relieve":[134],"human":[136],"operator":[137],"laborious":[140],"preparation":[142],"process":[143],"required":[144],"solving":[151],"complex":[152],"tasks.":[155],"The":[156],"evaluation":[157],"results":[158],"show":[159],"method":[163],"achieves":[164],"higher":[165],"success":[166],"rates":[167],"enhances":[169],"sample":[170],"efficiency":[171],"compared":[172],"selected":[174],"baselines,":[175],"learned":[179],"simulation":[181],"performs":[182],"well":[183],"real-world":[186],"placement":[187],"task":[188],"with":[189],"changing":[190],"goals":[191],"obstacles.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-06T07:47:59.780226","created_date":"2025-10-10T00:00:00"}