{"id":"https://openalex.org/W2001798070","doi":"https://doi.org/10.1109/humanoids.2014.7041414","title":"ROCK* \u2014 Efficient black-box optimization for policy learning","display_name":"ROCK* \u2014 Efficient black-box optimization for policy learning","publication_year":2014,"publication_date":"2014-11-01","ids":{"openalex":"https://openalex.org/W2001798070","doi":"https://doi.org/10.1109/humanoids.2014.7041414","mag":"2001798070"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids.2014.7041414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2014.7041414","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE-RAS International Conference on Humanoid Robots","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080397455","display_name":"Jemin Hwangbo","orcid":"https://orcid.org/0000-0002-3444-8079"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jemin Hwangbo","raw_affiliation_strings":["The initial research to this study has been done while the first author was at the Agile &amp; Dexterous Robotics Lab","Agile & Dexterous Robotics Lab"],"affiliations":[{"raw_affiliation_string":"The initial research to this study has been done while the first author was at the Agile &amp; Dexterous Robotics Lab","institution_ids":[]},{"raw_affiliation_string":"Agile & Dexterous Robotics Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010702403","display_name":"Christian Gehring","orcid":"https://orcid.org/0000-0003-2432-8767"},"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"]},{"id":"https://openalex.org/I4210137357","display_name":"Walt Disney (Switzerland)","ror":"https://ror.org/04h1x1p54","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210137357","https://openalex.org/I4210142140"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Christian Gehring","raw_affiliation_strings":["Autonomous Systems Lab (ASL), ETH Zurich, Switzerland","Disney Research Zurich, Switzerland","ETH Zurich, Autonomous Systems Lab (ASL), Switzerland"],"affiliations":[{"raw_affiliation_string":"Autonomous Systems Lab (ASL), ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Disney Research Zurich, Switzerland","institution_ids":["https://openalex.org/I4210137357"]},{"raw_affiliation_string":"ETH Zurich, Autonomous Systems Lab (ASL), Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090037182","display_name":"Hannes Sommer","orcid":null},"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":"Hannes Sommer","raw_affiliation_strings":["Autonomous Systems Lab (ASL), ETH Zurich, Switzerland","ETH Zurich, Autonomous Systems Lab (ASL), Switzerland"],"affiliations":[{"raw_affiliation_string":"Autonomous Systems Lab (ASL), ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Zurich, Autonomous Systems Lab (ASL), Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083003222","display_name":"Roland Siegwart","orcid":"https://orcid.org/0000-0002-2760-7983"},"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":"Roland Siegwart","raw_affiliation_strings":["Autonomous Systems Lab (ASL), ETH Zurich, Switzerland","ETH Zurich, Autonomous Systems Lab (ASL), Switzerland"],"affiliations":[{"raw_affiliation_string":"Autonomous Systems Lab (ASL), ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Zurich, Autonomous Systems Lab (ASL), Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077279214","display_name":"Jonas Buchli","orcid":"https://orcid.org/0000-0001-7494-8492"},"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":"Jonas Buchli","raw_affiliation_strings":["Agile &amp; Dexterous Robotics Lab (ADRL), ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Agile &amp; Dexterous Robotics Lab (ADRL), ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080397455"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5321,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.90739039,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"19","issue":null,"first_page":"535","last_page":"540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9945999979972839,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.7067146897315979},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.641292929649353},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.6148092150688171},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5714125633239746},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5289841890335083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4881053864955902},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.43244442343711853},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11241146922111511}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7067146897315979},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.641292929649353},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.6148092150688171},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5714125633239746},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5289841890335083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4881053864955902},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.43244442343711853},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11241146922111511},{"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/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/humanoids.2014.7041414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2014.7041414","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE-RAS International Conference on Humanoid Robots","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.700.5796","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.700.5796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.adrl.ethz.ch/archive/Humanoid2014_ROCKSTAR.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.800000011920929}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321652","display_name":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich","ror":"https://ror.org/05a28rw58"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1481631336","https://openalex.org/W1502364872","https://openalex.org/W1549072606","https://openalex.org/W1925816294","https://openalex.org/W1963515231","https://openalex.org/W1977655452","https://openalex.org/W2009797711","https://openalex.org/W2020113631","https://openalex.org/W2082297462","https://openalex.org/W2085627234","https://openalex.org/W2098524868","https://openalex.org/W2111904757","https://openalex.org/W2112036188","https://openalex.org/W2119717200","https://openalex.org/W2123967136","https://openalex.org/W2133224499","https://openalex.org/W2133932631","https://openalex.org/W2152526632","https://openalex.org/W2157701998","https://openalex.org/W2171996789","https://openalex.org/W2172968643","https://openalex.org/W2734870733","https://openalex.org/W3005581722","https://openalex.org/W4205918232","https://openalex.org/W4232288152","https://openalex.org/W4250087872","https://openalex.org/W4253187718","https://openalex.org/W6628685483","https://openalex.org/W6640290305","https://openalex.org/W6674872077","https://openalex.org/W6678157427","https://openalex.org/W6678231874","https://openalex.org/W6741320478"],"related_works":["https://openalex.org/W2047881532","https://openalex.org/W2285795935","https://openalex.org/W4389072557","https://openalex.org/W4319452366","https://openalex.org/W4293695278","https://openalex.org/W3013663659","https://openalex.org/W3213722473","https://openalex.org/W2110944602","https://openalex.org/W40488765","https://openalex.org/W108140644"],"abstract_inverted_index":{"Robotic":[0],"learning":[1,84],"on":[2,29,85,94,106],"real":[3,86,112],"hardware":[4,24,87],"requires":[5],"an":[6,18,37],"efficient":[7],"algorithm":[8,61,93],"which":[9],"minimizes":[10],"the":[11,30],"number":[12],"of":[13,23,99,110,127],"trials":[14],"needed":[15],"to":[16,72],"learn":[17],"optimal":[19],"policy.":[20],"Prolonged":[21],"use":[22],"causes":[25],"wear":[26],"and":[27,32,54,69,82,105],"tear":[28],"system":[31],"demands":[33],"more":[34],"attention":[35],"from":[36],"operator.":[38],"To":[39],"this":[40],"end,":[41],"we":[42],"present":[43],"a":[44,66,75,100,107,111,125],"novel":[45],"black-box":[46],"optimization":[47],"algorithm,":[48],"Reward":[49],"Optimization":[50],"with":[51],"Compact":[52],"Kernels":[53],"fast":[55,81],"natural":[56],"gradient":[57],"regression":[58],"(ROCK\u2217).":[59],"Our":[60],"immediately":[62],"updates":[63],"knowledge":[64],"after":[65],"single":[67],"trial":[68],"is":[70],"able":[71],"extrapolate":[73],"in":[74,121],"controlled":[76],"manner.":[77],"These":[78],"features":[79],"make":[80],"safe":[83],"possible.":[88],"We":[89],"have":[90],"evaluated":[91],"our":[92],"two":[95],"simulated":[96],"reaching":[97],"tasks":[98,123],"50":[101],"degree-of-freedom":[102],"robot":[103],"arm":[104],"hopping":[108],"task":[109],"articulated":[113],"legged":[114],"system.":[115],"ROCK\u2217":[116],"outperformed":[117],"current":[118],"state-of-the-art":[119],"algorithms":[120],"all":[122],"by":[124],"factor":[126],"three":[128],"or":[129],"more.":[130]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
