{"id":"https://openalex.org/W2762329249","doi":"https://doi.org/10.1109/lra.2018.2861466","title":"Learning a Structured Neural Network Policy for a Hopping Task","display_name":"Learning a Structured Neural Network Policy for a Hopping Task","publication_year":2018,"publication_date":"2018-07-31","ids":{"openalex":"https://openalex.org/W2762329249","doi":"https://doi.org/10.1109/lra.2018.2861466","mag":"2762329249"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2018.2861466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2018.2861466","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1710.00022","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Julian Viereck","orcid":"https://orcid.org/0000-0002-9049-5873"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian Viereck","raw_affiliation_strings":["Tandon School of Engineering, New York University, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-9049-5873","affiliations":[{"raw_affiliation_string":"Tandon School of Engineering, New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jules Kozolinsky","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162280","display_name":"Laboratoire de G\u00e9ologie de l\u2019\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/05vg9cw43","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210148025","https://openalex.org/I4210162280"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jules Kozolinsky","raw_affiliation_strings":["Ecole Normale Sup\u00e9rieure, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Normale Sup\u00e9rieure, Paris, France","institution_ids":["https://openalex.org/I4210162280"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Alexander Herzog","orcid":"https://orcid.org/0000-0001-7671-1878"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Herzog","raw_affiliation_strings":["X, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7671-1878","affiliations":[{"raw_affiliation_string":"X, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Ludovic Righetti","orcid":"https://orcid.org/0000-0002-6458-9112"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ludovic Righetti","raw_affiliation_strings":["Tandon School of Engineering, New York University, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-6458-9112","affiliations":[{"raw_affiliation_string":"Tandon School of Engineering, New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7303,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.70266893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"3","issue":"4","first_page":"4092","last_page":"4099"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.6065000295639038,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.6065000295639038,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.2037999927997589,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.046799998730421066,"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":0.7179999947547913},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6450999975204468},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5914999842643738},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.5235000252723694},{"id":"https://openalex.org/keywords/feedforward-neural-network","display_name":"Feedforward neural network","score":0.4325000047683716},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4000999927520752},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.3637000024318695},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.35910001397132874}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7179999947547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113000154495239},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6450999975204468},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5914999842643738},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.5235000252723694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47360000014305115},{"id":"https://openalex.org/C47702885","wikidata":"https://www.wikidata.org/wiki/Q5441227","display_name":"Feedforward neural network","level":3,"score":0.4325000047683716},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3490999937057495},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3343000113964081},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3192000091075897},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C88337583","wikidata":"https://www.wikidata.org/wiki/Q7883433","display_name":"Underactuation","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2018.2861466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2018.2861466","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1710.00022","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.00022","pdf_url":"https://arxiv.org/pdf/1710.00022","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1710.00022","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.00022","pdf_url":"https://arxiv.org/pdf/1710.00022","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309290","display_name":"New York University","ror":"https://ror.org/0190ak572"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1657213141","https://openalex.org/W1964946446","https://openalex.org/W2003132288","https://openalex.org/W2080184275","https://openalex.org/W2126909264","https://openalex.org/W2145339207","https://openalex.org/W2157720571","https://openalex.org/W2198582666","https://openalex.org/W2257979135","https://openalex.org/W2295431040","https://openalex.org/W2399015533","https://openalex.org/W2411183766","https://openalex.org/W2411442487","https://openalex.org/W2413365548","https://openalex.org/W2766447205","https://openalex.org/W2771691050","https://openalex.org/W6607786297","https://openalex.org/W6638018090","https://openalex.org/W6675999342","https://openalex.org/W6682849425","https://openalex.org/W6740222838","https://openalex.org/W6741002519","https://openalex.org/W6812115717"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"letter,":[2],"we":[3,25,41,95,154],"present":[4],"a":[5,9,13,39,47,51,69,86,90,141,165],"method":[6],"for":[7,12,50,61],"learning":[8],"reactive":[10,81],"policy":[11,82,105,144,159],"simple":[14],"dynamic":[15],"locomotion":[16],"task":[17],"involving":[18],"hard":[19],"impact":[20],"and":[21,30,54,106,124],"switching":[22],"contacts":[23],"where":[24],"assume":[26],"the":[27,58,75,80,103,112,132,135,148,157],"contact":[28,31],"location":[29],"timing":[32],"to":[33,45,78,98,137],"be":[34,127,161],"unknown.":[35],"To":[36],"learn":[37,57,79],"such":[38],"policy,":[40],"use":[42,74],"optimal":[43],"control":[44],"optimize":[46],"local":[48,104],"controller":[49],"fixed":[52],"environment":[53],"contacts.":[55],"We":[56,73],"contact-rich":[59],"dynamics":[60],"our":[62],"underactuated":[63],"systems":[64],"along":[65],"these":[66],"trajectories":[67],"in":[68,83,111,117,151],"sample":[70],"efficient":[71],"manner.":[72],"optimized":[76],"policies":[77],"form":[84],"of":[85,119,134],"neural":[87,92],"network.":[88],"Using":[89],"new":[91],"network":[93],"architecture,":[94],"are":[96],"able":[97],"preserve":[99],"more":[100],"information":[101],"from":[102],"make":[107],"its":[108,115],"output":[109,116],"interpretable":[110],"sense":[113],"that":[114,156],"terms":[118],"desired":[120],"trajectories,":[121],"feedforward":[122],"commands":[123],"gains":[125],"can":[126,160],"interpreted.":[128],"Extensive":[129],"simulations":[130],"demonstrate":[131],"robustness":[133],"approach":[136],"changing":[138],"environments,":[139],"outperforming":[140],"model-free":[142],"gradient":[143],"based":[145],"methods":[146],"on":[147,164],"same":[149],"tasks":[150],"simulation.":[152],"Finally,":[153],"show":[155],"learned":[158],"robustly":[162],"transferred":[163],"real":[166],"robot.":[167]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2017-10-20T00:00:00"}