{"id":"https://openalex.org/W2808533106","doi":"https://doi.org/10.1109/icra.2019.8794206","title":"BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning","display_name":"BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2808533106","doi":"https://doi.org/10.1109/icra.2019.8794206","mag":"2808533106"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2019.8794206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1806.06161","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091869385","display_name":"Boris Ivanovic","orcid":"https://orcid.org/0000-0002-8698-202X"},"institutions":[{"id":"https://openalex.org/I13805885","display_name":"Vaughn College of Aeronautics and Technology","ror":"https://ror.org/056e22e24","country_code":"US","type":"education","lineage":["https://openalex.org/I13805885"]},{"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":"Boris Ivanovic","raw_affiliation_strings":["Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA","Department of Aeronautics and Astronautics; Stanford University; Stanford; CA; 94305; USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I13805885","https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Aeronautics and Astronautics; Stanford University; Stanford; CA; 94305; USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031821299","display_name":"J. Michael Harrison","orcid":"https://orcid.org/0000-0002-3657-2639"},"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":"James Harrison","raw_affiliation_strings":["Department of Mechanical Engineering, Stanford University, Stanford, CA, USA","#N#Department of Mechanical Engineering, Stanford University, Stanford, CA 94305,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"#N#Department of Mechanical Engineering, Stanford University, Stanford, CA 94305,USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101730120","display_name":"Apoorva Sharma","orcid":"https://orcid.org/0000-0003-0904-8847"},"institutions":[{"id":"https://openalex.org/I13805885","display_name":"Vaughn College of Aeronautics and Technology","ror":"https://ror.org/056e22e24","country_code":"US","type":"education","lineage":["https://openalex.org/I13805885"]},{"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":"Apoorva Sharma","raw_affiliation_strings":["Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA","Department of Aeronautics and Astronautics; Stanford University; Stanford; CA; 94305; USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I13805885","https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Aeronautics and Astronautics; Stanford University; Stanford; CA; 94305; USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387244","display_name":"Mo Chen","orcid":"https://orcid.org/0000-0001-8506-3665"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mo Chen","raw_affiliation_strings":["School of Computing Science, Simon Fraser University, Burnaby, BC, Canada","School of Computing Science, Simon Fraser University, Burnaby BC, V5A 1S6, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Science, Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]},{"raw_affiliation_string":"School of Computing Science, Simon Fraser University, Burnaby BC, V5A 1S6, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050003000","display_name":"Marco Pavone","orcid":"https://orcid.org/0000-0002-0206-4337"},"institutions":[{"id":"https://openalex.org/I13805885","display_name":"Vaughn College of Aeronautics and Technology","ror":"https://ror.org/056e22e24","country_code":"US","type":"education","lineage":["https://openalex.org/I13805885"]},{"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":"Marco Pavone","raw_affiliation_strings":["Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA","Department of Aeronautics and Astronautics; Stanford University; Stanford; CA; 94305; USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I13805885","https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Aeronautics and Astronautics; Stanford University; Stanford; CA; 94305; USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1446,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.54750948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"15","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9703999757766724,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9506999850273132,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.8551325798034668},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.738287627696991},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6511977910995483},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5905914902687073},{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.5478385090827942},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5188661813735962},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47902077436447144},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4767545163631439},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.44082069396972656},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37992486357688904},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3544524908065796},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.24976983666419983},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.18505322933197021},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09832710027694702}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8551325798034668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.738287627696991},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6511977910995483},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5905914902687073},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.5478385090827942},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5188661813735962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47902077436447144},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4767545163631439},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.44082069396972656},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37992486357688904},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3544524908065796},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.24976983666419983},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.18505322933197021},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09832710027694702},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra.2019.8794206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1806.06161","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1806.06161","pdf_url":"https://arxiv.org/pdf/1806.06161","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2808533106","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1806.06161","pdf_url":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1806.06161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1806.06161","pdf_url":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1806.06161","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1806.06161","pdf_url":"https://arxiv.org/pdf/1806.06161","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":null},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2808533106.pdf"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W315739085","https://openalex.org/W1424654272","https://openalex.org/W1581407678","https://openalex.org/W1757796397","https://openalex.org/W1864112212","https://openalex.org/W1969160376","https://openalex.org/W2001331101","https://openalex.org/W2004303440","https://openalex.org/W2054585537","https://openalex.org/W2067265108","https://openalex.org/W2104733512","https://openalex.org/W2121103318","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2285664202","https://openalex.org/W2296073425","https://openalex.org/W2298907094","https://openalex.org/W2417786368","https://openalex.org/W2492473950","https://openalex.org/W2604960773","https://openalex.org/W2605102758","https://openalex.org/W2612689742","https://openalex.org/W2736601468","https://openalex.org/W2737215407","https://openalex.org/W2737223130","https://openalex.org/W2739211902","https://openalex.org/W2807455070","https://openalex.org/W2951948137","https://openalex.org/W2952606116","https://openalex.org/W2962730259","https://openalex.org/W2963184939","https://openalex.org/W2963606896","https://openalex.org/W2963864421","https://openalex.org/W2963938771","https://openalex.org/W2964040381","https://openalex.org/W2964161785","https://openalex.org/W2964327384","https://openalex.org/W2964333597","https://openalex.org/W3105818906","https://openalex.org/W6634906388","https://openalex.org/W6637967152","https://openalex.org/W6675999342","https://openalex.org/W6678367057","https://openalex.org/W6680657880","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6695011786","https://openalex.org/W6696324988","https://openalex.org/W6716474083","https://openalex.org/W6731923558","https://openalex.org/W6735939104","https://openalex.org/W6736021936","https://openalex.org/W6736742618","https://openalex.org/W6741002519","https://openalex.org/W6741302124","https://openalex.org/W6741909845","https://openalex.org/W6744321392","https://openalex.org/W6752474918","https://openalex.org/W6753073282"],"related_works":["https://openalex.org/W2968917487","https://openalex.org/W2925234320","https://openalex.org/W2513578279","https://openalex.org/W2966735560","https://openalex.org/W2097797606","https://openalex.org/W2997735228","https://openalex.org/W2756826236","https://openalex.org/W2995706821","https://openalex.org/W2558251412","https://openalex.org/W3213789840","https://openalex.org/W3167965394","https://openalex.org/W3090106354","https://openalex.org/W3014975158","https://openalex.org/W3046755562","https://openalex.org/W3123748881","https://openalex.org/W3127984962","https://openalex.org/W3190671243","https://openalex.org/W1601640269","https://openalex.org/W3035457745","https://openalex.org/W2290354866"],"abstract_inverted_index":{"Model-free":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"offers":[4],"an":[5,83],"attractive":[6],"approach":[7,191],"to":[8,60,88,115,173,205],"learn":[9],"control":[10,159],"policies":[11],"for":[12,41,45,92],"high":[13],"dimensional":[14],"systems,":[15],"but":[16],"its":[17],"relatively":[18],"poor":[19],"sample":[20],"complexity":[21],"often":[22],"necessitates":[23],"training":[24,105,146,175],"in":[25,29,50,79,126,141],"simulated":[26],"environments.":[27],"Even":[28],"simulation,":[30],"goal-directed":[31,157],"tasks":[32,52],"whose":[33],"natural":[34],"reward":[35],"function":[36],"is":[37,53,139,164],"sparse":[38],"remain":[39],"intractable":[40],"state-of-the-art":[42],"model-free":[43,94,149,185],"algorithms":[44],"continuous":[46,158],"control.":[47],"The":[48],"bottleneck":[49],"these":[51],"the":[54,66,70,80,117,121,131,178,184],"prohibitive":[55],"amount":[56],"of":[57,69,82,113,147,156,183],"exploration":[58,212],"required":[59],"obtain":[61],"a":[62,90,93,110,127,153],"learning":[63,197],"signal":[64],"from":[65,106],"initial":[67,122],"state":[68,123],"system.":[71],"In":[72],"this":[73],"work,":[74],"we":[75],"leverage":[76],"physical":[77,171],"priors":[78,172],"form":[81],"approximate":[84],"system":[85],"dynamics":[86],"model":[87],"design":[89],"curriculum":[91,162,207],"policy":[95,104,132],"optimization":[96,133],"algorithm.":[97,187],"Our":[98],"Backward":[99],"Reachability":[100],"Curriculum":[101],"(BaRC)":[102],"begins":[103],"states":[107],"that":[108,142],"require":[109],"small":[111],"number":[112],"actions":[114],"accomplish":[116],"task,":[118],"and":[119,168,181,199,210],"expands":[120],"distribution":[124],"backwards":[125],"dynamically-consistent":[128],"manner":[129],"once":[130],"algorithm":[134,151],"demonstrates":[135],"sufficient":[136],"performance.":[137],"BaRC":[138],"general,":[140],"it":[143],"can":[144],"accelerate":[145,174],"any":[148],"RL":[150,186],"on":[152,192],"broad":[154],"class":[155],"MDPs.":[160],"Its":[161],"strategy":[163],"physically":[165],"intuitive,":[166],"easy-to-tune,":[167],"allows":[169],"incorporating":[170],"without":[176],"hindering":[177],"performance,":[179],"flexibility,":[180],"applicability":[182],"We":[188],"evaluate":[189],"our":[190],"two":[193],"representative":[194],"dynamic":[195],"robotic":[196],"problems":[198],"find":[200],"substantial":[201],"performance":[202],"improvement":[203],"relative":[204],"previous":[206],"generation":[208],"techniques":[209],"naive":[211],"strategies.":[213]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}