{"id":"https://openalex.org/W2795341696","doi":"https://doi.org/10.1109/simpar.2018.8376268","title":"Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system","display_name":"Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2795341696","doi":"https://doi.org/10.1109/simpar.2018.8376268","mag":"2795341696"},"language":"en","primary_location":{"id":"doi:10.1109/simpar.2018.8376268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/simpar.2018.8376268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR)","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/1803.10371","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059445103","display_name":"Kendall Lowrey","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kendall Lowrey","raw_affiliation_strings":["University of Washington","University of Washington ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University of Washington ;","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054807108","display_name":"Svetoslav Kolev","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Svetoslav Kolev","raw_affiliation_strings":["University of Washington","University of Washington ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University of Washington ;","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025328125","display_name":"Jeremy Dao","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy Dao","raw_affiliation_strings":["University of Washington","University of Washington ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University of Washington ;","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040732794","display_name":"Aravind Rajeswaran","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aravind Rajeswaran","raw_affiliation_strings":["University of Washington","University of Washington ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University of Washington ;","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108520754","display_name":"Emanuel Todorov","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emanuel Todorov","raw_affiliation_strings":["University of Washington","University of Washington ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University of Washington ;","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":1.3518,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85510893,"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":"35","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9986000061035156,"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":0.9883000254631042,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8799127340316772},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6933358907699585},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6491977572441101},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5672667026519775},{"id":"https://openalex.org/keywords/prehensile-tail","display_name":"Prehensile tail","score":0.5445823669433594},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5319908857345581},{"id":"https://openalex.org/keywords/physical-system","display_name":"Physical system","score":0.4838827848434448},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.471633642911911},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3801290988922119},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.36400845646858215},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3363647162914276}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8799127340316772},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6933358907699585},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6491977572441101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5672667026519775},{"id":"https://openalex.org/C136380597","wikidata":"https://www.wikidata.org/wiki/Q10508905","display_name":"Prehensile tail","level":2,"score":0.5445823669433594},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5319908857345581},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.4838827848434448},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.471633642911911},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3801290988922119},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.36400845646858215},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3363647162914276},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/simpar.2018.8376268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/simpar.2018.8376268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1803.10371","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1803.10371","pdf_url":"https://arxiv.org/pdf/1803.10371","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:2795341696","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1803.10371.pdf","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.1803.10371","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1803.10371","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:1803.10371","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1803.10371","pdf_url":"https://arxiv.org/pdf/1803.10371","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":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2795341696.pdf","grobid_xml":"https://content.openalex.org/works/W2795341696.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1555368087","https://openalex.org/W1594783240","https://openalex.org/W1676686791","https://openalex.org/W1820821744","https://openalex.org/W1964946446","https://openalex.org/W1966784014","https://openalex.org/W1970789124","https://openalex.org/W1975230295","https://openalex.org/W1977655452","https://openalex.org/W1997543377","https://openalex.org/W1998172110","https://openalex.org/W2042408133","https://openalex.org/W2042520683","https://openalex.org/W2087617385","https://openalex.org/W2107726111","https://openalex.org/W2119717200","https://openalex.org/W2124695578","https://openalex.org/W2130801532","https://openalex.org/W2132602063","https://openalex.org/W2140135625","https://openalex.org/W2144351850","https://openalex.org/W2158782408","https://openalex.org/W2158796564","https://openalex.org/W2165693128","https://openalex.org/W2172968643","https://openalex.org/W2186601217","https://openalex.org/W2198582666","https://openalex.org/W2205975260","https://openalex.org/W2209762605","https://openalex.org/W2416477367","https://openalex.org/W2528734395","https://openalex.org/W2529477964","https://openalex.org/W2529601334","https://openalex.org/W2529658650","https://openalex.org/W2575705757","https://openalex.org/W2615735215","https://openalex.org/W2736601468","https://openalex.org/W2757631751","https://openalex.org/W2949608212","https://openalex.org/W3101442004","https://openalex.org/W6627932998","https://openalex.org/W6635508374","https://openalex.org/W6638018090","https://openalex.org/W6653435097","https://openalex.org/W6679257226","https://openalex.org/W6680657880","https://openalex.org/W6686786811","https://openalex.org/W6734129231","https://openalex.org/W6744563498","https://openalex.org/W6966558720"],"related_works":["https://openalex.org/W3101442004","https://openalex.org/W2735268712","https://openalex.org/W2894383471","https://openalex.org/W2922299896","https://openalex.org/W3003777383","https://openalex.org/W2963859851","https://openalex.org/W2953129341","https://openalex.org/W3004070224","https://openalex.org/W2950268955","https://openalex.org/W2964310273","https://openalex.org/W2944714385","https://openalex.org/W2759034818","https://openalex.org/W2918049070","https://openalex.org/W2950600380","https://openalex.org/W3132089310","https://openalex.org/W1523133203","https://openalex.org/W3149922422","https://openalex.org/W2968652061","https://openalex.org/W3109409708","https://openalex.org/W2610395436"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,40],"has":[2,53],"emerged":[3],"as":[4],"a":[5,25,77,95,108],"promising":[6],"methodology":[7],"for":[8,24,104,151],"training":[9,134],"robot":[10],"controllers.":[11],"However,":[12],"most":[13],"results":[14,157],"have":[15],"been":[16,54],"limited":[17],"to":[18,21,45,76,88,107,146],"simulation":[19,72,111],"due":[20],"the":[22,31,50,55,58,61,99,123,141,161],"need":[23],"large":[26],"number":[27],"of":[28,33,81,98,138],"samples":[29],"and":[30,60],"lack":[32],"automated-yet-safe":[34],"data":[35],"collection":[36],"methods.":[37],"Model-based":[38],"reinforcement":[39],"methods":[41],"provide":[42],"an":[43,86,136],"avenue":[44],"circumvent":[46],"these":[47],"challenges,":[48],"but":[49],"traditional":[51],"concern":[52],"mismatch":[56],"between":[57],"simulator":[59],"real":[62],"world.":[63],"Here,":[64],"we":[65,131],"show":[66,132],"that":[67,133],"control":[68],"policies":[69,143],"learned":[70,142],"in":[71,118,153,160],"can":[73],"successfully":[74],"transfer":[75],"physical":[78,124],"system,":[79],"composed":[80],"three":[82],"Phantom":[83],"robots":[84],"pushing":[85],"object":[87],"various":[89],"desired":[90],"target":[91],"positions.":[92],"We":[93],"use":[94],"modified":[96],"form":[97],"natural":[100],"policy":[101],"gradient":[102],"algorithm":[103],"learning,":[105],"applied":[106],"carefully":[109],"identified":[110],"model.":[112],"The":[113,156],"resulting":[114],"policies,":[115],"trained":[116],"entirely":[117],"simulation,":[119],"work":[120],"well":[121],"on":[122],"system":[125,154],"without":[126],"additional":[127],"training.":[128],"In":[129],"addition,":[130],"with":[135],"ensemble":[137],"models":[139],"makes":[140],"more":[144],"robust":[145],"modeling":[147],"errors,":[148],"thus":[149],"compensating":[150],"difficulties":[152],"identification.":[155],"are":[158],"illustrated":[159],"accompanying":[162],"video.":[163]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}