{"id":"https://openalex.org/W3096593047","doi":"https://doi.org/10.1109/icra48506.2021.9561982","title":"Policy Transfer via Kinematic Domain Randomization and Adaptation","display_name":"Policy Transfer via Kinematic Domain Randomization and Adaptation","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3096593047","doi":"https://doi.org/10.1109/icra48506.2021.9561982","mag":"3096593047"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561982","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.01891","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020531381","display_name":"Ioannis Exarchos","orcid":"https://orcid.org/0000-0002-5836-4750"},"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":"Ioannis Exarchos","raw_affiliation_strings":["Stanford University,Department of Computer Science,Stanford,CA,94305","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Computer Science,Stanford,CA,94305","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109476553","display_name":"Yifeng Jiang","orcid":null},"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":"Yifeng Jiang","raw_affiliation_strings":["Stanford University,Department of Computer Science,Stanford,CA,94305","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Computer Science,Stanford,CA,94305","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015524477","display_name":"Wenhao Yu","orcid":"https://orcid.org/0000-0001-8263-8224"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"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":"Wenhao Yu","raw_affiliation_strings":["Robotics at Google,Mountain View,CA","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics at Google,Mountain View,CA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048338914","display_name":"C. Karen Liu","orcid":"https://orcid.org/0000-0001-5926-0905"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"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":"C. Karen Liu","raw_affiliation_strings":["Stanford University,Department of Computer Science,Stanford,CA,94305","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Computer Science,Stanford,CA,94305","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.980400025844574,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9797000288963318,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/heuristics","display_name":"Heuristics","score":0.7809081077575684},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.7618069648742676},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6944429278373718},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.568705677986145},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4638652205467224},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4624137878417969},{"id":"https://openalex.org/keywords/inverse-kinematics","display_name":"Inverse kinematics","score":0.43637925386428833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41702800989151},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3792472779750824},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3496151566505432},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3170493245124817},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1816578507423401}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7809081077575684},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.7618069648742676},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6944429278373718},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.568705677986145},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4638652205467224},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4624137878417969},{"id":"https://openalex.org/C17816587","wikidata":"https://www.wikidata.org/wiki/Q1501872","display_name":"Inverse kinematics","level":3,"score":0.43637925386428833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41702800989151},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3792472779750824},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3496151566505432},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3170493245124817},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1816578507423401},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra48506.2021.9561982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561982","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:oai:arXiv.org:2011.01891","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.01891","pdf_url":"https://arxiv.org/pdf/2011.01891","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":"","raw_type":"text"},{"id":"mag:3096593047","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.01891","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.2011.01891","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.01891","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.01891","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.01891","pdf_url":"https://arxiv.org/pdf/2011.01891","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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3096593047.pdf","grobid_xml":"https://content.openalex.org/works/W3096593047.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1746819321","https://openalex.org/W1979328769","https://openalex.org/W2121863487","https://openalex.org/W2477400028","https://openalex.org/W2595845486","https://openalex.org/W2602963933","https://openalex.org/W2605102758","https://openalex.org/W2736601468","https://openalex.org/W2769052358","https://openalex.org/W2784449021","https://openalex.org/W2796290181","https://openalex.org/W2889970038","https://openalex.org/W2911087563","https://openalex.org/W2919616510","https://openalex.org/W2963184939","https://openalex.org/W2963859851","https://openalex.org/W2968116426","https://openalex.org/W2976228896","https://openalex.org/W2981030070","https://openalex.org/W3003647188","https://openalex.org/W3014488508","https://openalex.org/W3032919895","https://openalex.org/W3038194455","https://openalex.org/W3101442004","https://openalex.org/W3105609823","https://openalex.org/W3130568950","https://openalex.org/W6721345134","https://openalex.org/W6734827232","https://openalex.org/W6735677848","https://openalex.org/W6741002519","https://openalex.org/W6754782557","https://openalex.org/W6755353450","https://openalex.org/W6768151236","https://openalex.org/W6841112233","https://openalex.org/W6891797237","https://openalex.org/W6966558720"],"related_works":["https://openalex.org/W3206938627","https://openalex.org/W3126300335","https://openalex.org/W3010612407","https://openalex.org/W2529477964","https://openalex.org/W2790341021","https://openalex.org/W2948443723","https://openalex.org/W2964278684","https://openalex.org/W3088347926","https://openalex.org/W3011973854","https://openalex.org/W3104329975","https://openalex.org/W2128535275","https://openalex.org/W2886730169","https://openalex.org/W3009795828","https://openalex.org/W3164133736","https://openalex.org/W2951948137","https://openalex.org/W2803429660","https://openalex.org/W3102701697","https://openalex.org/W3209810522","https://openalex.org/W2962812027","https://openalex.org/W3119351950"],"abstract_inverted_index":{"Transferring":[0],"reinforcement":[1],"learning":[2],"policies":[3,127],"trained":[4],"in":[5,70,94,157],"physics":[6],"simulation":[7,95],"to":[8,28,67,136],"the":[9,17,51,137],"real":[10],"hardware":[11],"remains":[12],"a":[13,23,106,141,153],"challenge,":[14],"known":[15],"as":[16],"\"sim-to-real\"":[18],"gap.":[19],"Domain":[20],"randomization":[21],"is":[22],"simple":[24],"yet":[25],"effective":[26],"technique":[27],"address":[29],"dynamics":[30],"discrepancies":[31],"across":[32,60],"source":[33],"and":[34,44,133],"target":[35,138,145,160],"domains,":[36],"but":[37],"its":[38],"success":[39],"generally":[40,96],"depends":[41],"on":[42,57,101,129,152],"heuristics":[43],"trial-and-error.":[45],"In":[46],"this":[47,102],"work":[48],"we":[49,82,104],"investigate":[50],"impact":[52],"of":[53,63,125,144,165],"randomized":[54],"parameter":[55],"selection":[56],"policy":[58],"transferability":[59],"different":[61,159,163],"types":[62],"domain":[64,108,146,166],"discrepancies.":[65,167],"Contrary":[66],"common":[68],"practice":[69],"which":[71],"kinematic":[72,87,114,131],"parameters":[73,79,88,115,132],"are":[74,80],"carefully":[75],"measured":[76],"while":[77],"dynamic":[78,98],"randomized,":[81],"found":[83],"that":[84,111],"virtually":[85],"randomizing":[86],"(e.g.,":[89],"link":[90],"lengths)":[91],"during":[92],"training":[93],"outperforms":[97],"randomization.":[99],"Based":[100],"finding,":[103],"introduce":[105],"new":[107],"adaptation":[109],"algorithm":[110],"utilizes":[112],"simulated":[113,154],"variation.":[116],"Our":[117],"algorithm,":[118],"Multi-Policy":[119],"Bayesian":[120],"Optimization,":[121],"trains":[122],"an":[123],"ensemble":[124],"universal":[126],"conditioned":[128],"virtual":[130],"efficiently":[134],"adapts":[135],"environment":[139],"using":[140],"limited":[142],"number":[143],"rollouts.":[147],"We":[148],"showcase":[149],"our":[150],"findings":[151],"quadruped":[155],"robot":[156],"five":[158],"environments":[161],"covering":[162],"aspects":[164]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
