{"id":"https://openalex.org/W2982306485","doi":"https://doi.org/10.1109/icra40945.2020.9197000","title":"Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization","display_name":"Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W2982306485","doi":"https://doi.org/10.1109/icra40945.2020.9197000","mag":"2982306485"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9197000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/1910.13399","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026401995","display_name":"Matteo Turchetta","orcid":"https://orcid.org/0000-0001-5881-3096"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Matteo Turchetta","raw_affiliation_strings":["Learning and Adaptive Systems Group, ETH Zurich, Z\u00fcrich, Switzerland","ETH Z\u00fcrich"],"affiliations":[{"raw_affiliation_string":"Learning and Adaptive Systems Group, ETH Zurich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003040843","display_name":"Andreas Krause","orcid":"https://orcid.org/0000-0001-7260-9673"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Krause","raw_affiliation_strings":["Learning and Adaptive Systems Group, ETH Zurich, Z\u00fcrich, Switzerland","ETH Z\u00fcrich"],"affiliations":[{"raw_affiliation_string":"Learning and Adaptive Systems Group, ETH Zurich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023990842","display_name":"Sebastian Trimpe","orcid":"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":"funder","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":"Sebastian Trimpe","raw_affiliation_strings":["Intelligent Control Systems Group, Max Planck Institute for Intelligent Systems, Stuttgart, Germany","Max-Planck-Society"],"affiliations":[{"raw_affiliation_string":"Intelligent Control Systems Group, Max Planck Institute for Intelligent Systems, Stuttgart, Germany","institution_ids":["https://openalex.org/I4210135521"]},{"raw_affiliation_string":"Max-Planck-Society","institution_ids":["https://openalex.org/I149899117"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026401995"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":0.5776,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71756694,"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":"10702","last_page":"10708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9968000054359436,"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"}},"topics":[{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9968000054359436,"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"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9955000281333923,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8414040803909302},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7613993883132935},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.7573610544204712},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7112627029418945},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5903376340866089},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5865746736526489},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4881051480770111},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.47180190682411194},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.45872044563293457},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43999406695365906},{"id":"https://openalex.org/keywords/robust-optimization","display_name":"Robust optimization","score":0.4353603720664978},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4139511287212372},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1340784728527069},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11126968264579773}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8414040803909302},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7613993883132935},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.7573610544204712},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7112627029418945},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5903376340866089},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5865746736526489},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4881051480770111},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.47180190682411194},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45872044563293457},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43999406695365906},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.4353603720664978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4139511287212372},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1340784728527069},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11126968264579773},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icra40945.2020.9197000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.rwth-aachen.de:821187","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/821187","pdf_url":null,"source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA) / publisher: IEEE<br/>2020 IEEE International Conference on Robotics and Automation, ICRA 2020, Online, 2020-05-31 - 2020-08-31","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:1910.13399","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.13399","pdf_url":"https://arxiv.org/pdf/1910.13399","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":"doi:10.48550/arxiv.1910.13399","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.13399","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"},{"id":"mag:2982306485","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.13399","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.13399","pdf_url":"https://arxiv.org/pdf/1910.13399","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":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2982306485.pdf","grobid_xml":"https://content.openalex.org/works/W2982306485.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W770013183","https://openalex.org/W1502922572","https://openalex.org/W1509531727","https://openalex.org/W1522531528","https://openalex.org/W1588998206","https://openalex.org/W1763790326","https://openalex.org/W1868559974","https://openalex.org/W1965878388","https://openalex.org/W1989276044","https://openalex.org/W1995320175","https://openalex.org/W1997177885","https://openalex.org/W2027531431","https://openalex.org/W2041357003","https://openalex.org/W2075217007","https://openalex.org/W2105078254","https://openalex.org/W2121863487","https://openalex.org/W2143277772","https://openalex.org/W2165622730","https://openalex.org/W2171395877","https://openalex.org/W2183842689","https://openalex.org/W2192203593","https://openalex.org/W2221104225","https://openalex.org/W2302560253","https://openalex.org/W2346505884","https://openalex.org/W2499548917","https://openalex.org/W2516200644","https://openalex.org/W2592857946","https://openalex.org/W2602963933","https://openalex.org/W2793732783","https://openalex.org/W2904119718","https://openalex.org/W2963090983","https://openalex.org/W2972533062","https://openalex.org/W3105904426","https://openalex.org/W4206212643","https://openalex.org/W4238538572","https://openalex.org/W6675860490","https://openalex.org/W6685023080","https://openalex.org/W6697816282","https://openalex.org/W6735178672","https://openalex.org/W6735677848","https://openalex.org/W6741361698"],"related_works":["https://openalex.org/W2995574330","https://openalex.org/W2145957964","https://openalex.org/W2963179943","https://openalex.org/W3131822805","https://openalex.org/W2988077171","https://openalex.org/W3169796273","https://openalex.org/W3126916000","https://openalex.org/W62417866","https://openalex.org/W3196528513","https://openalex.org/W3170542100","https://openalex.org/W2966481145","https://openalex.org/W3007008008","https://openalex.org/W2732532072","https://openalex.org/W3096519373","https://openalex.org/W2990933479","https://openalex.org/W3133362425","https://openalex.org/W3100201759","https://openalex.org/W2948316777","https://openalex.org/W3131386210","https://openalex.org/W3185083385"],"abstract_inverted_index":{"In":[0,23,53,85],"reinforcement":[1],"learning":[2,66],"(RL),":[3],"an":[4,14],"autonomous":[5],"agent":[6],"learns":[7],"to":[8,47,59,143,166],"perform":[9],"complex":[10],"tasks":[11],"by":[12],"maximizing":[13],"exogenous":[15],"reward":[16,41],"signal":[17],"while":[18,65],"interacting":[19],"with":[20],"its":[21],"environment.":[22],"real":[24],"world":[25],"applications,":[26],"test":[27,51],"conditions":[28],"may":[29,45],"differ":[30],"substantially":[31],"from":[32,131],"the":[33,77,90,102,134,153],"training":[34,44],"scenario":[35],"and,":[36],"therefore,":[37],"focusing":[38],"on":[39],"pure":[40,163],"maximization":[42],"during":[43],"lead":[46],"poor":[48],"results":[49,71],"at":[50],"time.":[52],"these":[54,126],"cases,":[55],"it":[56],"is":[57],"important":[58],"trade-off":[60],"between":[61],"performance":[62],"and":[63,111,162],"robustness":[64,103,115],"a":[67,96,105,168],"policy.":[68],"While":[69],"several":[70],"exist":[72],"for":[73],"robust,":[74,91],"model-based":[75],"RL,":[76],"model-free":[78,92,135],"case":[79],"has":[80],"not":[81],"been":[82],"widely":[83],"investigated.":[84],"this":[86,146],"paper,":[87],"we":[88,107],"cast":[89],"RL":[93],"problem":[94],"as":[95],"multi-objective":[97,139,148],"optimization":[98,141,149],"problem.":[99,150],"To":[100],"quantify":[101],"of":[104,155],"policy,":[106],"use":[108,138],"delay":[109],"margin":[110],"gain":[112],"margin,":[113],"two":[114],"indicators":[116],"that":[117],"are":[118],"common":[119],"in":[120,133,160],"control":[121],"theory.":[122],"We":[123,137,151],"show":[124,152],"how":[125],"metrics":[127],"can":[128],"be":[129],"estimated":[130],"data":[132],"setting.":[136],"Bayesian":[140],"(MOBO)":[142],"solve":[144],"efficiently":[145],"expensive-to-evaluate,":[147],"benefits":[154],"our":[156],"robust":[157],"formulation":[158],"both":[159],"sim-to-real":[161],"hardware":[164],"experiments":[165],"balance":[167],"Furuta":[169],"pendulum.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}