{"id":"https://openalex.org/W3097924667","doi":"https://doi.org/10.1109/icra48506.2021.9561870","title":"Contextual Latent-Movements Off-Policy Optimization for Robotic Manipulation Skills","display_name":"Contextual Latent-Movements Off-Policy Optimization for Robotic Manipulation Skills","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3097924667","doi":"https://doi.org/10.1109/icra48506.2021.9561870","mag":"3097924667"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561870","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.13766","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051476305","display_name":"Samuele Tosatto","orcid":"https://orcid.org/0000-0002-5795-9541"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Samuele Tosatto","raw_affiliation_strings":["Technische Universität Darmstadt,Intelligent Autonomous Systems,Darmstadt,Germany,64289","Technische Universit\u00e4t Darmstadt,Intelligent Autonomous Systems,Darmstadt,Germany,64289"],"affiliations":[{"raw_affiliation_string":"Technische Universität Darmstadt,Intelligent Autonomous Systems,Darmstadt,Germany,64289","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt,Intelligent Autonomous Systems,Darmstadt,Germany,64289","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026055366","display_name":"Georgia Chalvatzaki","orcid":"https://orcid.org/0000-0002-5055-199X"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georgia Chalvatzaki","raw_affiliation_strings":["Technische Universität Darmstadt,Intelligent Autonomous Systems,Darmstadt,Germany,64289","Technische Universit\u00e4t Darmstadt,Intelligent Autonomous Systems,Darmstadt,Germany,64289"],"affiliations":[{"raw_affiliation_string":"Technische Universität Darmstadt,Intelligent Autonomous Systems,Darmstadt,Germany,64289","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt,Intelligent Autonomous Systems,Darmstadt,Germany,64289","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Technische Universität Darmstadt,Intelligent Autonomous Systems,Darmstadt,Germany,64289","Technische Universit\u00e4t Darmstadt,Intelligent Autonomous Systems,Darmstadt,Germany,64289"],"affiliations":[{"raw_affiliation_string":"Technische Universität Darmstadt,Intelligent Autonomous Systems,Darmstadt,Germany,64289","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt,Intelligent Autonomous Systems,Darmstadt,Germany,64289","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051476305"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00917478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10815","last_page":"10821"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9901999831199646,"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/computer-science","display_name":"Computer science","score":0.7329557538032532},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.6667168140411377},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6588281393051147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6540234088897705},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5478061437606812},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5454857349395752},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5248722434043884},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5113295912742615},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5012049674987793},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.45250946283340454},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4424355924129486},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.43998491764068604},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.4227410852909088},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.41582101583480835},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11069080233573914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7329557538032532},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.6667168140411377},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6588281393051147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6540234088897705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5478061437606812},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5454857349395752},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5248722434043884},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5113295912742615},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5012049674987793},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.45250946283340454},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4424355924129486},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.43998491764068604},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.4227410852909088},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.41582101583480835},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11069080233573914},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","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":4,"locations":[{"id":"doi:10.1109/icra48506.2021.9561870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561870","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:2010.13766","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.13766","pdf_url":"https://arxiv.org/pdf/2010.13766","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":null,"raw_type":"text"},{"id":"mag:3097924667","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.13766.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.2010.13766","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.13766","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:2010.13766","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.13766","pdf_url":"https://arxiv.org/pdf/2010.13766","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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3097924667.pdf","grobid_xml":"https://content.openalex.org/works/W3097924667.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W1499669280","https://openalex.org/W1513084430","https://openalex.org/W1771410628","https://openalex.org/W1792818999","https://openalex.org/W1880549478","https://openalex.org/W1929309940","https://openalex.org/W1968876723","https://openalex.org/W1990470929","https://openalex.org/W2012587148","https://openalex.org/W2021004298","https://openalex.org/W2042882799","https://openalex.org/W2051453180","https://openalex.org/W2071444114","https://openalex.org/W2116226448","https://openalex.org/W2119717200","https://openalex.org/W2128677288","https://openalex.org/W2134447392","https://openalex.org/W2136719407","https://openalex.org/W2140801763","https://openalex.org/W2146610201","https://openalex.org/W2149860990","https://openalex.org/W2155027007","https://openalex.org/W2162262334","https://openalex.org/W2213467466","https://openalex.org/W2253356247","https://openalex.org/W2569181534","https://openalex.org/W2735021678","https://openalex.org/W2736601468","https://openalex.org/W2802700851","https://openalex.org/W2803616302","https://openalex.org/W2804930149","https://openalex.org/W2884285175","https://openalex.org/W2897555104","https://openalex.org/W2904246096","https://openalex.org/W2911433325","https://openalex.org/W2955035422","https://openalex.org/W2963106920","https://openalex.org/W2963864421","https://openalex.org/W2964068481","https://openalex.org/W2994446013","https://openalex.org/W3007769740","https://openalex.org/W3029221344","https://openalex.org/W3091497200","https://openalex.org/W3101754927","https://openalex.org/W6638018090","https://openalex.org/W6639342821","https://openalex.org/W6653548176","https://openalex.org/W6680971464","https://openalex.org/W6682093400","https://openalex.org/W6683204974","https://openalex.org/W6684017535","https://openalex.org/W6684921986","https://openalex.org/W6691873557","https://openalex.org/W6704084210","https://openalex.org/W6741002519","https://openalex.org/W6751285671","https://openalex.org/W6752165109","https://openalex.org/W6754490743","https://openalex.org/W6757592117","https://openalex.org/W6764969207","https://openalex.org/W6768771297","https://openalex.org/W6772565584"],"related_works":["https://openalex.org/W3206592106","https://openalex.org/W1929309940","https://openalex.org/W2806332488","https://openalex.org/W3102801549","https://openalex.org/W2910988768","https://openalex.org/W2963403593","https://openalex.org/W3111023388","https://openalex.org/W2959488596","https://openalex.org/W1967736575","https://openalex.org/W3080156643","https://openalex.org/W2803611042","https://openalex.org/W3044290186","https://openalex.org/W2760799532","https://openalex.org/W2963280855","https://openalex.org/W3024201688","https://openalex.org/W2965592025","https://openalex.org/W3134527491","https://openalex.org/W2967129319","https://openalex.org/W2962759351","https://openalex.org/W2967717386"],"abstract_inverted_index":{"Parameterized":[0],"movement":[1,119],"primitives":[2,25,120],"have":[3],"been":[4],"extensively":[5],"used":[6],"for":[7,33,51,114,121],"imitation":[8],"learning":[9,29,34,105,123],"of":[10,16,23,59,100,118,124],"robotic":[11],"tasks.":[12],"However,":[13],"the":[14,17,21,27,48,66],"high-dimensionality":[15],"parameter":[18,68],"space":[19],"hinders":[20],"improvement":[22],"such":[24],"in":[26,103,133,149],"reinforcement":[28],"(RL)":[30],"setting,":[31],"especially":[32],"with":[35],"physical":[36],"robots.":[37],"In":[38],"this":[39],"paper":[40],"we":[41,71],"propose":[42],"a":[43,73,111,137],"novel":[44],"view":[45],"on":[46,65,136],"handling":[47],"demonstrated":[49],"trajectories":[50],"acquiring":[52],"low-dimensional,":[53],"non-linear":[54],"latent":[55],"dynamics,":[56],"using":[57,92],"mixtures":[58],"probabilistic":[60],"principal":[61],"component":[62],"analyzers":[63],"(MPPCA)":[64],"movements'":[67],"space.":[69],"Moreover,":[70],"introduce":[72],"new":[74],"contextual":[75],"off-policy":[76,116],"RL":[77],"algorithm,":[78],"named":[79],"LAtent-Movements":[80],"Policy":[81],"Optimization":[82],"(LAMPO).":[83],"LAMPO":[84,142],"can":[85],"provide":[86,110],"gradient":[87],"estimates":[88],"from":[89],"previous":[90,104],"experience":[91],"self-normalized":[93],"importance":[94],"sampling,":[95],"hence,":[96],"making":[97],"full":[98],"use":[99],"samples":[101],"collected":[102],"iterations.":[106],"These":[107],"advantages":[108],"combined":[109],"complete":[112],"framework":[113],"sample-efficient":[115,144],"optimization":[117],"robot":[122,139],"high-dimensional":[125],"manipulation":[126],"skills.":[127],"Our":[128],"experimental":[129],"results":[130],"conducted":[131],"both":[132],"simulation":[134],"and":[135],"real":[138],"show":[140],"that":[141],"provides":[143],"policies":[145],"against":[146],"common":[147],"approaches":[148],"literature.":[150]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}