{"id":"https://openalex.org/W3047120541","doi":"https://doi.org/10.1109/iros45743.2020.9341187","title":"Active Improvement of Control Policies with Bayesian Gaussian Mixture Model","display_name":"Active Improvement of Control Policies with Bayesian Gaussian Mixture Model","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3047120541","doi":"https://doi.org/10.1109/iros45743.2020.9341187","mag":"3047120541"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/2008.02540","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050199260","display_name":"Hakan Girgin","orcid":"https://orcid.org/0000-0002-4776-7888"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Hakan Girgin","raw_affiliation_strings":["Idiap Research Institute, Switzerland","IDIAP Research Institute, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080609835","display_name":"Emmanuel Pignat","orcid":"https://orcid.org/0000-0001-6612-5322"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Emmanuel Pignat","raw_affiliation_strings":["Idiap Research Institute, Switzerland","IDIAP RESEARCH INSTITUTE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP RESEARCH INSTITUTE","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064146907","display_name":"No\u00e9mie Jaquier","orcid":"https://orcid.org/0000-0003-3565-9414"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Noemie Jaquier","raw_affiliation_strings":["Idiap Research Institute, Switzerland","IDIAP Research Institute, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048780399","display_name":"Sylvain Calinon","orcid":"https://orcid.org/0000-0002-9036-6799"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Sylvain Calinon","raw_affiliation_strings":["Idiap Research Institute, Switzerland","IDIAP Research Institute, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":0.3903,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68676447,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"5395","last_page":"5401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9983000159263611,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9983000159263611,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9940000176429749,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9922999739646912,"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/generalization","display_name":"Generalization","score":0.7080680727958679},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6964857578277588},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.692082941532135},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5785719156265259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5783595442771912},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5116344094276428},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.503621518611908},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.49687865376472473},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49264222383499146},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4691449701786041},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.45616915822029114},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.4275061786174774},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.42684996128082275},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.4197401702404022},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4160059094429016},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3799397051334381},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1914196014404297}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7080680727958679},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6964857578277588},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.692082941532135},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5785719156265259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5783595442771912},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5116344094276428},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.503621518611908},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49687865376472473},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49264222383499146},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4691449701786041},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.45616915822029114},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.4275061786174774},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.42684996128082275},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.4197401702404022},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4160059094429016},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3799397051334381},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1914196014404297},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/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}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1109/iros45743.2020.9341187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.02540","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.02540","pdf_url":"https://arxiv.org/pdf/2008.02540","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:3047120541","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2008.02540","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":"pmh:oai:infoscience.epfl.ch:285025","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/177310","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"},{"id":"pmh:oai:zenodo.org:4041422","is_oa":true,"landing_page_url":"https://zenodo.org/record/4041422","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"doi:10.48550/arxiv.2008.02540","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.02540","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"},{"id":"doi:10.5281/zenodo.4041421","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4041421","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.5281/zenodo.4041422","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4041422","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.02540","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.02540","pdf_url":"https://arxiv.org/pdf/2008.02540","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1506806321","https://openalex.org/W1597173708","https://openalex.org/W1807380328","https://openalex.org/W1977655452","https://openalex.org/W2012479417","https://openalex.org/W2012587148","https://openalex.org/W2041242313","https://openalex.org/W2070678636","https://openalex.org/W2123967136","https://openalex.org/W2128677288","https://openalex.org/W2129202194","https://openalex.org/W2140801763","https://openalex.org/W2775751232","https://openalex.org/W2914331073","https://openalex.org/W2963895143","https://openalex.org/W2964161785","https://openalex.org/W2965133842","https://openalex.org/W3012384939","https://openalex.org/W3104787446","https://openalex.org/W4205513846","https://openalex.org/W4206723194","https://openalex.org/W4241649586","https://openalex.org/W6638365234","https://openalex.org/W6678157427","https://openalex.org/W6680971464","https://openalex.org/W6682849425","https://openalex.org/W6747136208","https://openalex.org/W6765580494"],"related_works":["https://openalex.org/W3041638738","https://openalex.org/W2593143642","https://openalex.org/W3104787446","https://openalex.org/W1714604093","https://openalex.org/W2968029133","https://openalex.org/W2738812390","https://openalex.org/W2134540127","https://openalex.org/W3023404305","https://openalex.org/W2153667689","https://openalex.org/W1781089932","https://openalex.org/W2951948137","https://openalex.org/W2873705236","https://openalex.org/W2886730169","https://openalex.org/W2899131640","https://openalex.org/W2509546504","https://openalex.org/W3048771073","https://openalex.org/W3007674363","https://openalex.org/W3129243175","https://openalex.org/W2793908792","https://openalex.org/W2793020180"],"abstract_inverted_index":{"Learning":[0],"from":[1],"demonstration":[2],"(LfD)":[3],"is":[4,56],"an":[5,131],"intuitive":[6],"framework":[7,42,118],"allowing":[8],"non-expert":[9],"users":[10],"to":[11,45,88,94,101],"easily":[12],"(re-)program":[13],"robots.":[14],"However,":[15],"the":[16,27,47,59,70,83,103,120],"quality":[17],"and":[18,93,135],"quantity":[19],"of":[20,30,50,62,122],"demonstrations":[21],"have":[22],"a":[23,38,77,108,123,127,136,140],"great":[24],"influence":[25],"on":[26,58,82],"generalization":[28,48],"performances":[29],"LfD":[31],"approaches.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36,99],"introduce":[37],"novel":[39],"active":[40,104,116],"learning":[41,105,117],"in":[43,119,126],"order":[44],"improve":[46],"capabilities":[49],"control":[51],"policies.":[52],"The":[53],"proposed":[54],"approach":[55],"based":[57,81],"epistemic":[60],"uncertainties":[61],"Bayesian":[63],"Gaussian":[64,109],"mixture":[65,110],"models":[66],"(BGMMs).":[67],"We":[68,113],"determine":[69],"new":[71],"query":[72],"point":[73],"location":[74],"by":[75],"optimizing":[76],"closed-form":[78],"information-density":[79],"cost":[80,106],"quadratic":[84],"R\u00e9nyi":[85],"entropy.":[86],"Furthermore,":[87],"better":[89],"represent":[90],"uncertain":[91],"regions":[92],"avoid":[95],"local":[96],"optima":[97],"problem,":[98],"propose":[100],"approximate":[102],"with":[107,130,139],"model":[111],"(GMM).":[112],"demonstrate":[114],"our":[115],"context":[121],"reaching":[124],"task":[125],"cluttered":[128],"environment":[129],"illustrative":[132],"toy":[133],"example":[134],"real":[137],"experiment":[138],"Panda":[141],"robot.":[142]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}