{"id":"https://openalex.org/W2756872766","doi":"https://doi.org/10.1109/icra.2018.8461083","title":"Using Parameterized Black-Box Priors to Scale Up Model-Based Policy Search for Robotics","display_name":"Using Parameterized Black-Box Priors to Scale Up Model-Based Policy Search for Robotics","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2756872766","doi":"https://doi.org/10.1109/icra.2018.8461083","mag":"2756872766"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2018.8461083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8461083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1709.06917","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048630321","display_name":"Konstantinos Chatzilygeroudis","orcid":"https://orcid.org/0000-0003-3585-1027"},"institutions":[{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Konstantinos Chatzilygeroudis","raw_affiliation_strings":["Inria, Villers-les-Nancy, Universit\u00e9 de Lorraine, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, Villers-les-Nancy, Universit\u00e9 de Lorraine, France","institution_ids":["https://openalex.org/I90183372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032227198","display_name":"Jean-Baptiste Mouret","orcid":"https://orcid.org/0000-0002-2513-027X"},"institutions":[{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Baptiste Mouret","raw_affiliation_strings":["Inria, Villers-les-Nancy, Universit\u00e9 de Lorraine, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, Villers-les-Nancy, Universit\u00e9 de Lorraine, France","institution_ids":["https://openalex.org/I90183372"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90183372"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":null,"first_page":"5121","last_page":"5128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12288","display_name":"Optimization and Search Problems","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9819999933242798,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/hexapod","display_name":"Hexapod","score":0.7647517919540405},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6349534392356873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6029187440872192},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5914891362190247},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5913181304931641},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5862123966217041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5704222321510315},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5596299171447754},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4581749141216278},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.45551034808158875},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4210430979728699},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4126887321472168},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34782761335372925},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2556529641151428},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22115138173103333},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.07826271653175354}],"concepts":[{"id":"https://openalex.org/C136434205","wikidata":"https://www.wikidata.org/wiki/Q3437269","display_name":"Hexapod","level":3,"score":0.7647517919540405},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6349534392356873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6029187440872192},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5914891362190247},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5913181304931641},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5862123966217041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5704222321510315},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5596299171447754},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4581749141216278},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.45551034808158875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4210430979728699},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4126887321472168},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34782761335372925},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2556529641151428},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22115138173103333},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.07826271653175354},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra.2018.8461083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8461083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1709.06917","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1709.06917","pdf_url":"https://arxiv.org/pdf/1709.06917","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:HAL:hal-01768285v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01768285","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"ICRA 2018 - International Conference on Robotics and Automation, May 2018, brisbane, Australia","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.1709.06917","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1709.06917","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1709.06917","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1709.06917","pdf_url":"https://arxiv.org/pdf/1709.06917","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W56921542","https://openalex.org/W758372786","https://openalex.org/W1498369939","https://openalex.org/W1654016072","https://openalex.org/W1738827650","https://openalex.org/W1746819321","https://openalex.org/W1925816294","https://openalex.org/W1967736575","https://openalex.org/W1972063518","https://openalex.org/W1997543377","https://openalex.org/W1998179438","https://openalex.org/W2012392077","https://openalex.org/W2012587148","https://openalex.org/W2018705428","https://openalex.org/W2071841410","https://openalex.org/W2085627234","https://openalex.org/W2112036188","https://openalex.org/W2121863487","https://openalex.org/W2140907765","https://openalex.org/W2145166323","https://openalex.org/W2145339207","https://openalex.org/W2151965738","https://openalex.org/W2156974606","https://openalex.org/W2159537373","https://openalex.org/W2162717641","https://openalex.org/W2167856595","https://openalex.org/W2173248099","https://openalex.org/W2192203593","https://openalex.org/W2201087437","https://openalex.org/W2400159152","https://openalex.org/W2552644168","https://openalex.org/W2580909119","https://openalex.org/W2606327391","https://openalex.org/W2615735215","https://openalex.org/W2739858255","https://openalex.org/W2793955514","https://openalex.org/W2919115771","https://openalex.org/W2949608212","https://openalex.org/W2951386724","https://openalex.org/W2962822210","https://openalex.org/W2963781688","https://openalex.org/W4205513846","https://openalex.org/W4244912679","https://openalex.org/W6622219343","https://openalex.org/W6629718364","https://openalex.org/W6634911526","https://openalex.org/W6636635099","https://openalex.org/W6638018090","https://openalex.org/W6640290305","https://openalex.org/W6641607987","https://openalex.org/W6642376952","https://openalex.org/W6643267832","https://openalex.org/W6676297131","https://openalex.org/W6680710430","https://openalex.org/W6682262322","https://openalex.org/W6683735925","https://openalex.org/W6684827244","https://openalex.org/W6684921986","https://openalex.org/W6687583017","https://openalex.org/W6687962483","https://openalex.org/W6697126365","https://openalex.org/W6712660418","https://openalex.org/W6729468961","https://openalex.org/W6730260666","https://openalex.org/W6734094730","https://openalex.org/W6736192076","https://openalex.org/W6736446654","https://openalex.org/W6737757103","https://openalex.org/W6741579962","https://openalex.org/W6746498747","https://openalex.org/W6749447860","https://openalex.org/W6763920131"],"related_works":["https://openalex.org/W2962812027","https://openalex.org/W2951948137","https://openalex.org/W2738812390","https://openalex.org/W2948443723","https://openalex.org/W3209983492","https://openalex.org/W2793020180","https://openalex.org/W2751302235","https://openalex.org/W2001095967","https://openalex.org/W3204858865","https://openalex.org/W2961987377","https://openalex.org/W3164133736","https://openalex.org/W2162206751","https://openalex.org/W3128627450","https://openalex.org/W2963184621","https://openalex.org/W3185513303","https://openalex.org/W2886730169","https://openalex.org/W2963960193","https://openalex.org/W3104329975","https://openalex.org/W3153532599","https://openalex.org/W2412669390"],"abstract_inverted_index":{"The":[0,154],"most":[1],"data-efficient":[2,163],"algorithms":[3,169],"for":[4],"reinforcement":[5],"learning":[6,17,92],"in":[7,94,131,187],"robotics":[8],"are":[9,66],"model-based":[10,71,166],"policy":[11,27,72,167],"search":[12,73,168],"algorithms,":[13],"which":[14],"alternate":[15],"between":[16],"a":[18,26,50,89,135,179],"dynamical":[19],"model":[20,35,91],"of":[21,115,123,193],"the":[22,30,34,40,44,116,121,127],"robot":[23,138,182],"and":[24,36,59,108,133,171,174],"optimizing":[25],"to":[28,54,79,101,105,112,147,183,190],"maximize":[29],"expected":[31],"return":[32],"given":[33],"its":[37],"uncertainties.":[38],"Among":[39],"few":[41],"proposed":[42],"approaches,":[43,74],"recently":[45],"introduced":[46],"Black-DROPS":[47,75,95],"algorithm":[48,53,160],"exploits":[49],"black-box":[51,99],"optimization":[52],"achieve":[55],"both":[56],"high":[57,80],"data-efficiency":[58],"good":[60],"computation":[61],"times":[62],"when":[63],"several":[64],"cores":[65],"used;":[67],"nevertheless,":[68],"like":[69],"all":[70],"does":[76],"not":[77],"scale":[78,103],"dimensional":[81],"state/action":[82],"spaces.":[83],"In":[84],"this":[85],"paper,":[86],"we":[87],"introduce":[88],"new":[90,159,185],"procedure":[93],"that":[96,145,157,175],"leverages":[97],"parameterized":[98],"priors":[100],"(1)":[102],"up":[104],"high-dimensional":[106],"systems,":[107],"(2)":[109],"be":[110],"robust":[111],"large":[113],"inaccuracies":[114],"prior":[117],"information.":[118],"We":[119],"demonstrate":[120],"effectiveness":[122],"our":[124,158],"approach":[125],"with":[126,134],"\u201cpendubot\u201d":[128],"swing-up":[129],"task":[130],"simulation":[132],"physical":[136,180],"hexapod":[137],"(48D":[139],"state":[140],"space,":[141],"18D":[142],"action":[143],"space)":[144],"has":[146],"walk":[148],"forward":[149],"as":[150,152],"fast":[151],"possible.":[153],"results":[155],"show":[156],"is":[161],"more":[162],"than":[164],"previous":[165],"(with":[170],"without":[172],"priors)":[173],"it":[176],"can":[177],"allow":[178],"6-legged":[181],"learn":[184],"gaits":[186],"only":[188],"16":[189],"30":[191],"seconds":[192],"interaction":[194],"time.":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}