{"id":"https://openalex.org/W4404652920","doi":"https://doi.org/10.1109/tro.2025.3539192","title":"Simulation-Aided Policy Tuning for Black-Box Robot Learning","display_name":"Simulation-Aided Policy Tuning for Black-Box Robot Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4404652920","doi":"https://doi.org/10.1109/tro.2025.3539192"},"language":"en","primary_location":{"id":"doi:10.1109/tro.2025.3539192","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tro.2025.3539192","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tro.2025.3539192","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shiming He","orcid":"https://orcid.org/0000-0003-4461-4795"},"institutions":[{"id":"https://openalex.org/I4400573310","display_name":"Hangzhou City University","ror":"https://ror.org/01wck0s05","country_code":null,"type":"education","lineage":["https://openalex.org/I4400573310"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiming He","raw_affiliation_strings":["School of Information and Electrical Engineering, Hangzhou City University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4461-4795","affiliations":[{"raw_affiliation_string":"School of Information and Electrical Engineering, Hangzhou City University, Hangzhou, China","institution_ids":["https://openalex.org/I4400573310"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045257122","display_name":"Alexander von Rohr","orcid":"https://orcid.org/0000-0002-0005-0310"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander von Rohr","raw_affiliation_strings":["Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-0005-0310","affiliations":[{"raw_affiliation_string":"Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029621528","display_name":"Dominik Baumann","orcid":"https://orcid.org/0000-0001-7340-2180"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Dominik Baumann","raw_affiliation_strings":["Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0001-7340-2180","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100718017","display_name":"Xiang Ji","orcid":"https://orcid.org/0000-0002-7234-6460"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Xiang","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7234-6460","affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"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/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Trimpe","raw_affiliation_strings":["Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2785-2487","affiliations":[{"raw_affiliation_string":"Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4417,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82202625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"41","issue":null,"first_page":"2533","last_page":"2548"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9973999857902527,"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":0.9973999857902527,"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":0.992900013923645,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9884999990463257,"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/robot","display_name":"Robot","score":0.7804983258247375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7505030632019043},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.6371432542800903},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5725190043449402},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.547344982624054},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.512839138507843},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5126653909683228},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49222055077552795},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39702850580215454},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.25613343715667725},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11529842019081116}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7804983258247375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505030632019043},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.6371432542800903},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5725190043449402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.547344982624054},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.512839138507843},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5126653909683228},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49222055077552795},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39702850580215454},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.25613343715667725},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11529842019081116},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/tro.2025.3539192","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tro.2025.3539192","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},{"id":"pmh:oai:publications.rwth-aachen.de:1006237","is_oa":true,"landing_page_url":"https://publications.rwth-aachen.de/record/1006237","pdf_url":null,"source":{"id":"https://openalex.org/S4306401033","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on robotics 41, 2533-2548 (2025). doi:10.1109/TRO.2025.3539192","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:arXiv.org:2411.14246","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.14246","pdf_url":"https://arxiv.org/pdf/2411.14246","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":"pmh:oai:DiVA.org:uu-555387","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-555387","pdf_url":"https://uu.diva-portal.org/smash/get/diva2:1954843/FULLTEXT01","source":{"id":"https://openalex.org/S4306400653","display_name":"Diva portal (Dalarna University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/134325","is_oa":true,"landing_page_url":"http://adsabs.harvard.edu/abs/2024arXiv241114246H","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"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":null,"raw_type":"A1 Alkuper\u00e4isartikkeli tieteellisess\u00e4 aikakauslehdess\u00e4"},{"id":"pmh:doi:10.18154/rwth-2025-02355","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Journal article"}],"best_oa_location":{"id":"doi:10.1109/tro.2025.3539192","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tro.2025.3539192","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6257368980","display_name":null,"funder_award_id":"RWTH1205","funder_id":"https://openalex.org/F4320324232","funder_display_name":"RWTH Aachen University"}],"funders":[{"id":"https://openalex.org/F4320324232","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1510052597","https://openalex.org/W2110304639","https://openalex.org/W2136719407","https://openalex.org/W2143277772","https://openalex.org/W2346505884","https://openalex.org/W2592857946","https://openalex.org/W2604883922","https://openalex.org/W2605102758","https://openalex.org/W2737488931","https://openalex.org/W2767050701","https://openalex.org/W2962736495","https://openalex.org/W2964050632","https://openalex.org/W2990747716","https://openalex.org/W2997896361","https://openalex.org/W3004240582","https://openalex.org/W3093922502","https://openalex.org/W3104307775","https://openalex.org/W3120906468","https://openalex.org/W3126321819","https://openalex.org/W3164709982","https://openalex.org/W3175937615","https://openalex.org/W3206230600","https://openalex.org/W3212380917","https://openalex.org/W4230942370","https://openalex.org/W4285102614","https://openalex.org/W4317889697","https://openalex.org/W4401416214","https://openalex.org/W6629021139","https://openalex.org/W6637591494","https://openalex.org/W6680657880","https://openalex.org/W6680971464","https://openalex.org/W6728925229","https://openalex.org/W6729429149","https://openalex.org/W6736469832","https://openalex.org/W6740023956","https://openalex.org/W6742184374","https://openalex.org/W6751494529","https://openalex.org/W6753264383","https://openalex.org/W6754787993","https://openalex.org/W6764053384","https://openalex.org/W6764988152","https://openalex.org/W6765121789","https://openalex.org/W6766900132","https://openalex.org/W6791245825","https://openalex.org/W6803169502","https://openalex.org/W6846395486","https://openalex.org/W6849766918","https://openalex.org/W6849783222","https://openalex.org/W6853276975"],"related_works":["https://openalex.org/W2047881532","https://openalex.org/W4389072557","https://openalex.org/W4319452366","https://openalex.org/W2943623134","https://openalex.org/W2494523064","https://openalex.org/W2215759665","https://openalex.org/W2030292806","https://openalex.org/W3213722473","https://openalex.org/W2110944602","https://openalex.org/W2913184176"],"abstract_inverted_index":{"How":[0],"can":[1,108],"robots":[2],"learn":[3],"and":[4,9,16,45,75,131,151],"adapt":[5],"to":[6,53],"new":[7],"tasks":[8,130],"situations":[10],"with":[11,101,111,159],"little":[12],"data?":[13],"Systematic":[14],"exploration":[15],"simulation":[17,47],"are":[18],"crucial":[19],"tools":[20],"for":[21,114],"efficient":[22],"robot":[23,44,77,145,157],"learning.":[24,122],"We":[25,123],"present":[26],"a":[27,65,94,143,156],"novel":[28],"black-box":[29],"policy":[30,36,73,116],"search":[31],"algorithm":[32,39,126],"focused":[33],"on":[34,42,85,127,155],"data-efficient":[35],"improvements.":[37],"The":[38],"learns":[40,68],"directly":[41],"the":[43,56,60,63,69,72,76,86,102,105,133,136,160],"treats":[46],"as":[48],"an":[49,163],"additional":[50],"information":[51],"source":[52,139],"speed":[54],"up":[55],"learning":[57,78,146,154],"process.":[58],"At":[59],"core":[61],"of":[62,135,162],"algorithm,":[64],"probabilistic":[66],"model":[67],"dependence":[70],"between":[71],"parameters":[74],"objective":[79],"not":[80],"only":[81],"by":[82,90],"performing":[83],"experiments":[84],"robot,":[87],"but":[88],"also":[89],"leveraging":[91],"data":[92],"from":[93],"simulator.":[95,165],"This":[96],"substantially":[97],"reduces":[98],"interaction":[99],"time":[100],"robot.":[103],"Using":[104],"model,":[106],"we":[107,148],"guarantee":[109],"improvements":[110],"high":[112],"probability":[113],"each":[115],"update,":[117],"thereby":[118],"facilitating":[119],"fast,":[120],"goal-oriented":[121],"evaluate":[124],"our":[125],"simulated":[128],"fine-tuning":[129],"demonstrate":[132],"data-efficiency":[134],"proposed":[137],"dual-information":[138],"optimization":[140],"algorithm.":[141],"In":[142],"real":[144],"experiment,":[147],"show":[149],"fast":[150],"successful":[152],"task":[153],"manipulator":[158],"aid":[161],"imperfect":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-04T07:58:01.006859","created_date":"2025-10-10T00:00:00"}