{"id":"https://openalex.org/W1967736575","doi":"https://doi.org/10.1109/icra.2014.6907422","title":"Policy search for learning robot control using sparse data","display_name":"Policy search for learning robot control using sparse data","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1967736575","doi":"https://doi.org/10.1109/icra.2014.6907422","mag":"1967736575"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2014.6907422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2014.6907422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://mediatum.ub.tum.de/node?id=1281556","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080277992","display_name":"Bastian Bischoff","orcid":"https://orcid.org/0000-0001-8604-8432"},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"B. Bischoff","raw_affiliation_strings":["Cognitive Systems, Bosch Corporate Research, Germany"],"affiliations":[{"raw_affiliation_string":"Cognitive Systems, Bosch Corporate Research, Germany","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038068581","display_name":"Duy Nguyen-Tuong","orcid":null},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"D. Nguyen-Tuong","raw_affiliation_strings":["Cognitive Systems, Bosch Corporate Research, Germany"],"affiliations":[{"raw_affiliation_string":"Cognitive Systems, Bosch Corporate Research, Germany","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057277609","display_name":"Herke van Hoof","orcid":"https://orcid.org/0000-0002-1583-3692"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"H. van Hoof","raw_affiliation_strings":["Intelligent Autonomous Systems, TU Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems, TU Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051038777","display_name":"Andrew McHutchon","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"A. McHutchon","raw_affiliation_strings":["Computational and Biological Learning Lab, Univ. of Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Computational and Biological Learning Lab, Univ. of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108711177","display_name":"Carl Edward Rasmussen","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"C. E. Rasmussen","raw_affiliation_strings":["Computational and Biological Learning Lab, Univ. of Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Computational and Biological Learning Lab, Univ. of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063781430","display_name":"Alois Knoll","orcid":"https://orcid.org/0000-0003-4840-076X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A. Knoll","raw_affiliation_strings":["Technische Universitat Munchen, Munchen, Bayern, DE"],"affiliations":[{"raw_affiliation_string":"Technische Universitat Munchen, Munchen, Bayern, DE","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"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"]},{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J. Peters","raw_affiliation_strings":["Intelligent Autonomous Systems, TU Darmstadt, Germany","Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems, TU Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210135521"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108385961","display_name":"Mark Deisenroth","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]},{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"M.P. Deisenroth","raw_affiliation_strings":["Department of Computing, Imperial College London, UK","Intelligent Autonomous Systems, TU Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Intelligent Autonomous Systems, TU Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5080277992"],"corresponding_institution_ids":["https://openalex.org/I889804353"],"apc_list":null,"apc_paid":null,"fwci":2.9541,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91830591,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3882","last_page":"3887"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9994999766349792,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9994999766349792,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9965000152587891,"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":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.7370529770851135},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6878101825714111},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.6858927011489868},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6692938804626465},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6639994382858276},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6117140650749207},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6008549928665161},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5722244381904602},{"id":"https://openalex.org/keywords/instance-based-learning","display_name":"Instance-based learning","score":0.5228317379951477},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.521798849105835},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47633224725723267},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.46285074949264526},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44844114780426025},{"id":"https://openalex.org/keywords/programming-by-demonstration","display_name":"Programming by demonstration","score":0.4396648705005646},{"id":"https://openalex.org/keywords/online-machine-learning","display_name":"Online machine learning","score":0.42480647563934326},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4231262803077698},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.28097787499427795},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.16643604636192322},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09644508361816406},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09060660004615784}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7370529770851135},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6878101825714111},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.6858927011489868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6692938804626465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6639994382858276},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6117140650749207},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6008549928665161},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5722244381904602},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.5228317379951477},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.521798849105835},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47633224725723267},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.46285074949264526},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44844114780426025},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.4396648705005646},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.42480647563934326},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4231262803077698},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.28097787499427795},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.16643604636192322},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09644508361816406},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09060660004615784},{"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},{"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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1109/icra.2014.6907422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2014.6907422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.641.2751","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.641.2751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ias.tu-darmstadt.de/uploads/Publications/Bischoff_ICRA_2014.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.708.6813","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.708.6813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mlg.eng.cam.ac.uk/pub/pdf/BisNguHooetal14.pdf","raw_type":"text"},{"id":"pmh:oai:generic.eprints.org:680756","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/680756/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1281556","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1281556","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"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":"","raw_type":"article"},{"id":"pmh:oai:pure.mpg.de:item_2110032","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0025-B5EB-A","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2014 IEEE International Conference on Robotics and Automation (ICRA 2014)","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/12813","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/12813","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2014 IEEE International Conference on Robotics and Automation (ICRA 2014)","raw_type":"Conference Paper"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:107842","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/107842/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1281556","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1281556","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"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":"","raw_type":"article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5985747416","display_name":null,"funder_award_id":"EP/J012300/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W58266590","https://openalex.org/W170770739","https://openalex.org/W1520597402","https://openalex.org/W1746819321","https://openalex.org/W1949804828","https://openalex.org/W1977655452","https://openalex.org/W1998179438","https://openalex.org/W2012587148","https://openalex.org/W2018705428","https://openalex.org/W2121863487","https://openalex.org/W2140135625","https://openalex.org/W2151250975","https://openalex.org/W2154893459","https://openalex.org/W2179284380","https://openalex.org/W4211049957","https://openalex.org/W4211089519","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W6653548176"],"related_works":["https://openalex.org/W4205569898","https://openalex.org/W155730701","https://openalex.org/W2171128163","https://openalex.org/W2557627605","https://openalex.org/W1487472306","https://openalex.org/W2143680741","https://openalex.org/W4297094728","https://openalex.org/W4246584857","https://openalex.org/W3217547743","https://openalex.org/W1967736575"],"abstract_inverted_index":{"In":[0,28,80],"many":[1],"complex":[2],"robot":[3,185],"applications,":[4],"such":[5,29],"as":[6,19,172,174],"grasping":[7],"and":[8,25,45,72,162],"manipulation,":[9],"it":[10],"is":[11,64,117,129,168],"difficult":[12],"to":[13,69,102,110,118],"program":[14],"desired":[15],"task":[16],"solutions":[17],"beforehand,":[18],"robots":[20],"are":[21],"within":[22],"an":[23,193],"uncertain":[24],"dynamic":[26],"environment.":[27],"cases,":[30],"learning":[31,44,76,95,125,192,206],"tasks":[32],"from":[33],"experience":[34],"can":[35,77,99,140,207],"be":[36,100,141,208],"a":[37,42,149,176],"useful":[38],"alternative.":[39],"To":[40],"obtain":[41],"sound":[43],"generalization":[46],"performance,":[47],"machine":[48],"learning,":[49,52,67,88],"especially,":[50],"reinforcement":[51,75,87],"usually":[53],"requires":[54],"sufficient":[55],"data.":[56,215],"However,":[57],"in":[58,89,159,170,211],"cases":[59],"where":[60],"only":[61],"little":[62],"data":[63,109],"available":[65],"for":[66,94,191],"due":[68],"system":[70,138],"constraints":[71],"practical":[73],"issues,":[74],"act":[78],"suboptimally.":[79],"this":[81],"paper,":[82],"we":[83,187],"investigate":[84],"how":[85],"model-based":[86],"particular":[90],"the":[91,105,124,132,179,184,189],"probabilistic":[92,133],"inference":[93],"control":[96],"method":[97],"(Pilco),":[98],"tailored":[101],"cope":[103],"with":[104],"case":[106],"of":[107,213],"sparse":[108,214],"speed":[111],"up":[112,210],"learning.":[113],"The":[114,154,165,197],"basic":[115],"idea":[116],"include":[119],"further":[120],"prior":[121,146,203],"knowledge":[122,139],"into":[123],"process.":[126],"As":[127],"Pilco":[128,156],"built":[130],"on":[131,175],"Gaussian":[134,152],"processes":[135],"framework,":[136],"additional":[137],"incorporated":[142],"by":[143,201],"defining":[144],"appropriate":[145],"distributions,":[147],"e.g.":[148],"linear":[150],"mean":[151],"prior.":[153],"resulting":[155],"formulation":[157],"remains":[158],"closed":[160],"form":[161],"analytically":[163],"tractable.":[164],"proposed":[166],"approach":[167,190],"evaluated":[169],"simulation":[171],"well":[173],"physical":[177],"robot,":[178],"Festo":[180],"Robotino":[181],"XT.":[182],"For":[183],"evaluation,":[186],"employ":[188],"object":[194],"pick-up":[195],"task.":[196],"results":[198],"show":[199],"that":[200],"including":[202],"knowledge,":[204],"policy":[205],"sped":[209],"presence":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
