{"id":"https://openalex.org/W2963973319","doi":"https://doi.org/10.48550/arxiv.1907.10383","title":"Classified Regression for Bayesian Optimization: Robot Learning with Unknown Penalties","display_name":"Classified Regression for Bayesian Optimization: Robot Learning with Unknown Penalties","publication_year":2019,"publication_date":"2019-07-24","ids":{"openalex":"https://openalex.org/W2963973319","doi":"https://doi.org/10.48550/arxiv.1907.10383","mag":"2963973319"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1907.10383","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.10383","pdf_url":"https://arxiv.org/pdf/1907.10383","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.10383","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014762489","display_name":"Alonso Marco","orcid":"https://orcid.org/0000-0002-5764-6713","observed_orcids":["https://orcid.org/0000-0002-5764-6713"]},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marco, Alonso","raw_affiliation_strings":[". Intelligent Control Systems Max Planck Institute for Intelligent Systems Heisenbergstr. 3 70569 Stuttgart , Germany","Max-Planck-Society"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Intelligent Control Systems Max Planck Institute for Intelligent Systems Heisenbergstr. 3 70569 Stuttgart , Germany","institution_ids":["https://openalex.org/I4210135521"]},{"raw_affiliation_string":"Max-Planck-Society","institution_ids":["https://openalex.org/I149899117"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029621528","display_name":"Dominik Baumann","orcid":"https://orcid.org/0000-0001-7340-2180","observed_orcids":["https://orcid.org/0000-0001-7340-2180"]},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Baumann, Dominik","raw_affiliation_strings":[". Intelligent Control Systems Max Planck Institute for Intelligent Systems Heisenbergstr. 3 70569 Stuttgart , Germany","Max-Planck-Society"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Intelligent Control Systems Max Planck Institute for Intelligent Systems Heisenbergstr. 3 70569 Stuttgart , Germany","institution_ids":["https://openalex.org/I4210135521"]},{"raw_affiliation_string":"Max-Planck-Society","institution_ids":["https://openalex.org/I149899117"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022872779","display_name":"Philipp Hennig","orcid":"https://orcid.org/0000-0001-7293-6092","observed_orcids":["https://orcid.org/0000-0001-7293-6092"]},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hennig, Philipp","raw_affiliation_strings":[". Computer Science Department , University of T\u00fcbingen and","Max-Planck-Society"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Computer Science Department , University of T\u00fcbingen and","institution_ids":["https://openalex.org/I8087733"]},{"raw_affiliation_string":"Max-Planck-Society","institution_ids":["https://openalex.org/I149899117"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023990842","display_name":"Sebastian Trimpe","orcid":"https://orcid.org/0000-0002-2785-2487","observed_orcids":["https://orcid.org/0000-0002-2785-2487"]},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Trimpe, Sebastian","raw_affiliation_strings":[". Intelligent Control Systems Max Planck Institute for Intelligent Systems Heisenbergstr. 3 70569 Stuttgart , Germany","Max Planck Institute for Intelligent Systems Maria von Linden Str. 6 72076 T\u00fcbingen , Germany","Max-Planck-Society"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Intelligent Control Systems Max Planck Institute for Intelligent Systems Heisenbergstr. 3 70569 Stuttgart , Germany","institution_ids":["https://openalex.org/I4210135521"]},{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems Maria von Linden Str. 6 72076 T\u00fcbingen , Germany","institution_ids":["https://openalex.org/I4210135521"]},{"raw_affiliation_string":"Max-Planck-Society","institution_ids":["https://openalex.org/I149899117"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9375,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9375,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.03790000081062317,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.0044999998062849045,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/bayesian-optimization","display_name":"Bayesian optimization","score":0.9850000143051147},{"id":"https://openalex.org/keywords/robot-learning","display_name":"robot learning","score":0.8569999933242798},{"id":"https://openalex.org/keywords/gaussian-processes","display_name":"Gaussian processes","score":0.4580000042915344},{"id":"https://openalex.org/keywords/controller-stability","display_name":"controller stability","score":0.7590000033378601},{"id":"https://openalex.org/keywords/black-box-optimization","display_name":"black-box optimization","score":0.6940000057220459}],"concepts":[{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.8019077777862549},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6312258243560791},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.604171097278595},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5391865372657776},{"id":"https://openalex.org/C37903108","wikidata":"https://www.wikidata.org/wiki/Q4874474","display_name":"Bayesian linear regression","level":4,"score":0.4945034682750702},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4843617379665375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47110655903816223},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4610876441001892},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46040666103363037},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.43771740794181824},{"id":"https://openalex.org/C81692654","wikidata":"https://www.wikidata.org/wiki/Q225926","display_name":"Kriging","level":2,"score":0.4303266704082489},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.421889066696167},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.41217613220214844},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3346083462238312},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.32286950945854187},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22213292121887207},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11118060350418091},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1907.10383","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.10383","pdf_url":"https://arxiv.org/pdf/1907.10383","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.1907.10383","doi":"https://doi.org/10.48550/arxiv.1907.10383","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.10383","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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:1907.10383","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.10383","pdf_url":"https://arxiv.org/pdf/1907.10383","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[{"display_name":"Peace, justice, and strong institutions","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1088019354","display_name":null,"funder_award_id":"TR 1433/1-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320322434","display_name":"Max-Planck-Gesellschaft","ror":"https://ror.org/01hhn8329"},{"id":"https://openalex.org/F4320327553","display_name":"International Max Planck Research School for Advanced Methods in Process and Systems Engineering","ror":"https://ror.org/04hazks31"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W202805564","https://openalex.org/W770013183","https://openalex.org/W1491420040","https://openalex.org/W1510052597","https://openalex.org/W1522531528","https://openalex.org/W1530718350","https://openalex.org/W1562793886","https://openalex.org/W1588959569","https://openalex.org/W1693986406","https://openalex.org/W1701825639","https://openalex.org/W1746819321","https://openalex.org/W1879130152","https://openalex.org/W1934021597","https://openalex.org/W2100484286","https://openalex.org/W2134117233","https://openalex.org/W2139943902","https://openalex.org/W2143277772","https://openalex.org/W2147162091","https://openalex.org/W2167789032","https://openalex.org/W2186013251","https://openalex.org/W2192203593","https://openalex.org/W2346505884","https://openalex.org/W2593660867","https://openalex.org/W2595142274","https://openalex.org/W2728797307","https://openalex.org/W2737488931","https://openalex.org/W2754108308","https://openalex.org/W2755801529","https://openalex.org/W2772449134","https://openalex.org/W2776811469","https://openalex.org/W2874746074","https://openalex.org/W2891993609","https://openalex.org/W2951665052"],"related_works":["https://openalex.org/W2826306652","https://openalex.org/W2775829694","https://openalex.org/W3206718757","https://openalex.org/W3106885804","https://openalex.org/W2131792768","https://openalex.org/W1792865576","https://openalex.org/W2949535390","https://openalex.org/W2143203060","https://openalex.org/W2886703017","https://openalex.org/W2949369530","https://openalex.org/W2917021820","https://openalex.org/W2293119424","https://openalex.org/W3136489196","https://openalex.org/W2271183928","https://openalex.org/W3007058329","https://openalex.org/W323712777","https://openalex.org/W2509717476","https://openalex.org/W2910872742","https://openalex.org/W2896830491","https://openalex.org/W2185709919"],"abstract_inverted_index":{"Learning":[0],"robot":[1],"controllers":[2,83],"by":[3],"minimizing":[4],"a":[5,69,94,104,152,163,181],"black-box":[6],"objective":[7],"cost":[8,46,80,109],"using":[9],"Bayesian":[10,70,100],"optimization":[11,189],"(BO)":[12],"can":[13],"be":[14,93],"time-consuming":[15],"and":[16,143,147,160],"challenging.":[17],"It":[18],"is":[19,40,52,174],"very":[20],"often":[21,53],"the":[22,38,49,61,79,122,125,134,137],"case":[23],"that":[24,59,72,90],"some":[25],"roll-outs":[26],"result":[27],"in":[28,111,140,149],"failure":[29],"behaviors,":[30],"causing":[31],"premature":[32],"experiment":[33],"detention.":[34],"In":[35,119,156],"such":[36],"cases,":[37],"designer":[39],"forced":[41],"to":[42,85,117,167,185],"decide":[43],"on":[44,151],"heuristic":[45],"penalties":[47],"because":[48],"acquired":[50],"data":[51,86],"scarce,":[54],"or":[55],"not":[56],"comparable":[57],"with":[58,103],"of":[60,81,130,136,177],"stable":[62],"policies.":[63],"To":[64],"overcome":[65],"this,":[66],"we":[67,76,158],"propose":[68,159],"model":[71,123,139],"captures":[73],"exactly":[74],"what":[75],"know":[77],"about":[78],"unstable":[82],"prior":[84],"collection:":[87],"Nothing,":[88],"except":[89],"it":[91],"should":[92],"somewhat":[95],"large":[96],"number.":[97],"The":[98],"resulting":[99],"model,":[101],"approximated":[102],"Gaussian":[105],"process,":[106],"predicts":[107],"high":[108],"values":[110],"regions":[112,129],"where":[113],"failures":[114],"are":[115],"likely":[116],"occur.":[118],"this":[120],"way,":[121],"guides":[124],"BO":[126,165],"exploration":[127],"toward":[128],"stability.":[131],"We":[132],"demonstrate":[133],"benefits":[135],"proposed":[138],"several":[141],"illustrative":[142],"statistical":[144],"synthetic":[145],"benchmarks,":[146],"also":[148],"experiments":[150],"real":[153],"robotic":[154],"platform.":[155],"addition,":[157],"experimentally":[161],"validate":[162],"new":[164],"method":[166,173],"account":[168],"for":[169],"unknown":[170],"constraints.":[171],"Such":[172],"an":[175],"extension":[176],"Max-Value":[178],"Entropy":[179],"Search,":[180],"recent":[182],"information-theoretic":[183],"method,":[184],"solve":[186],"unconstrained":[187],"global":[188],"problems.":[190]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2022-07-28T00:00:00"}