{"id":"https://openalex.org/W2613462707","doi":"https://doi.org/10.1109/icra.2017.7989761","title":"Layered direct policy search for learning hierarchical skills","display_name":"Layered direct policy search for learning hierarchical skills","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2613462707","doi":"https://doi.org/10.1109/icra.2017.7989761","mag":"2613462707"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2017.7989761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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":"https://figshare.com/articles/conference_contribution/Layered_direct_policy_search_for_learning_hierarchical_skills/25171835","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082649343","display_name":"Felix End","orcid":null},"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":true,"raw_author_name":"Felix End","raw_affiliation_strings":["Felix End is a computer science student at the TU, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Felix End is a computer science student at the TU, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075701789","display_name":"Riad Akrour","orcid":"https://orcid.org/0000-0002-8735-6960"},"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":"Riad Akrour","raw_affiliation_strings":["Riad Akrour is with the CLAS lab, TU Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Riad Akrour is with the CLAS lab, TU Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"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/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["IAS lab, Max Planck Institute for Intelligent Systems, TU Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"IAS lab, Max Planck Institute for Intelligent Systems, TU Darmstadt, Germany","institution_ids":["https://openalex.org/I4210135521","https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110467801","display_name":"Gerhard Neumann","orcid":"https://orcid.org/0000-0002-5483-4225"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerhard Neumann","raw_affiliation_strings":["Gerhard Neumann is with the School of Computer Science, CLAS lab, TU Darmstadt, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Gerhard Neumann is with the School of Computer Science, CLAS lab, TU Darmstadt, United Kingdom","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082649343"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.8306,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.80032318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"13","issue":null,"first_page":"6442","last_page":"6448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.995199978351593,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9890000224113464,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8368862867355347},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7700231075286865},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7171393632888794},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6951044201850891},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.577090859413147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5618142485618591},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5589964389801025},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4554460048675537},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42195743322372437},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07895070314407349}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8368862867355347},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7700231075286865},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7171393632888794},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6951044201850891},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.577090859413147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5618142485618591},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5589964389801025},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4554460048675537},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42195743322372437},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07895070314407349},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icra.2017.7989761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.lincoln.ac.uk:26737","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196275","display_name":"Lincoln Repository (University of Lincoln)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I51532219","host_organization_name":"University of Lincoln","host_organization_lineage":["https://openalex.org/I51532219"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop contribution"},{"id":"pmh:oai:figshare.com:article/25171835","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Layered_direct_policy_search_for_learning_hierarchical_skills/25171835","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/25171835","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Layered_direct_policy_search_for_learning_hierarchical_skills/25171835","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W130216483","https://openalex.org/W1499669280","https://openalex.org/W1977655452","https://openalex.org/W2012204020","https://openalex.org/W2012587148","https://openalex.org/W2111967991","https://openalex.org/W2121103318","https://openalex.org/W2121517924","https://openalex.org/W2125612430","https://openalex.org/W2139394304","https://openalex.org/W2158548602","https://openalex.org/W2167647761","https://openalex.org/W2185709919","https://openalex.org/W4205513846","https://openalex.org/W4249441547","https://openalex.org/W4250589301","https://openalex.org/W6629881138","https://openalex.org/W6676560026","https://openalex.org/W6678367057","https://openalex.org/W6680606377","https://openalex.org/W6683443546","https://openalex.org/W6686239993"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2768698792"],"abstract_inverted_index":{"Solutions":[0],"to":[1,45,84,126,144,147,169],"real":[2],"world":[3],"robotic":[4],"tasks":[5,163],"often":[6,28],"require":[7],"complex":[8],"behaviors":[9,26],"in":[10],"high":[11,160],"dimensional":[12,161],"continuous":[13,162],"state":[14],"and":[15,92,104,134,138,164],"action":[16],"spaces.":[17],"Reinforcement":[18],"Learning":[19],"(RL)":[20],"is":[21,105],"aimed":[22],"at":[23],"learning":[24,98,122,129],"such":[25,61],"but":[27],"fails":[29],"for":[30],"lack":[31],"of":[32,49,65,90,110,113,120,131,151,175],"scalability.":[33],"To":[34],"address":[35],"this":[36,71],"issue,":[37],"Hierarchical":[38],"RL":[39],"(HRL)":[40],"algorithms":[41,55],"leverage":[42],"hierarchical":[43,118],"policies":[44],"exploit":[46],"the":[47,97,101,121,128,132,135,149,152],"structure":[48,103,119],"a":[50,63,75,87,111,172],"task.":[51],"However,":[52],"many":[53],"HRL":[54,77],"rely":[56],"on":[57,80,158],"task":[58],"specific":[59,140],"knowledge":[60],"as":[62],"set":[64,89,112,174],"predefined":[66],"sub-policies":[67,91,133],"or":[68],"sub-goals.":[69],"In":[70],"paper":[72],"we":[73],"propose":[74],"new":[76],"algorithm":[78,157],"based":[79],"information":[81,141],"theoretic":[82,142],"principles":[83],"autonomously":[85,170],"uncover":[86],"diverse":[88],"their":[93],"activation":[94],"policies.":[95],"Moreover,":[96],"process":[99,123],"mirrors":[100],"policys":[102],"thus":[106],"also":[107],"hierarchical,":[108],"consisting":[109],"independent":[114],"optimization":[115],"problems.":[116],"The":[117],"allows":[124],"us":[125],"control":[127],"rate":[130],"gating":[136],"individually":[137],"add":[139],"constraints":[143],"each":[145],"layer":[146],"ensure":[148],"diversification":[150],"sub-policies.":[153,176],"We":[154],"evaluate":[155],"our":[156],"two":[159],"experimentally":[165],"demonstrate":[166],"its":[167],"ability":[168],"discover":[171],"rich":[173]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}