{"id":"https://openalex.org/W2890253414","doi":"https://doi.org/10.1109/devlrn.2019.8850721","title":"Curriculum goal masking for continuous deep reinforcement learning","display_name":"Curriculum goal masking for continuous deep reinforcement learning","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2890253414","doi":"https://doi.org/10.1109/devlrn.2019.8850721","mag":"2890253414"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2019.8850721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2019.8850721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1809.06146","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050108731","display_name":"Manfred Eppe","orcid":"https://orcid.org/0000-0002-5473-3221"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Manfred Eppe","raw_affiliation_strings":["Department of Informatics, Universit\u00e4t Hamburg, Germany","University of Hamburg"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Universit\u00e4t Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]},{"raw_affiliation_string":"University of Hamburg","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015567592","display_name":"Sven Magg","orcid":"https://orcid.org/0000-0002-0589-6585"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sven Magg","raw_affiliation_strings":["Department of Informatics, Universit\u00e4t Hamburg, Germany","University of Hamburg"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Universit\u00e4t Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]},{"raw_affiliation_string":"University of Hamburg","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["Department of Informatics, Universit\u00e4t Hamburg, Germany","University of Hamburg"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Universit\u00e4t Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]},{"raw_affiliation_string":"University of Hamburg","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050108731"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":0.1445,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54530063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"80","issue":null,"first_page":"183","last_page":"188"},"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":0.9975000023841858,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9776999950408936,"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":0.8466374278068542},{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.8446444272994995},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7271330952644348},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6169606447219849},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5882318615913391},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5713653564453125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.531139075756073},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.49375972151756287},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44219303131103516},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4386339783668518},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35073864459991455},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10875740647315979},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.10694196820259094}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8466374278068542},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.8446444272994995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271330952644348},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6169606447219849},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5882318615913391},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5713653564453125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.531139075756073},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.49375972151756287},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44219303131103516},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4386339783668518},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35073864459991455},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10875740647315979},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.10694196820259094},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/devlrn.2019.8850721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2019.8850721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1809.06146","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.06146","pdf_url":"https://arxiv.org/pdf/1809.06146","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":"","raw_type":"text"},{"id":"mag:2890253414","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1809.06146","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:tore.tuhh.de:11420/12355","is_oa":false,"landing_page_url":"http://hdl.handle.net/11420/12355","pdf_url":null,"source":{"id":"https://openalex.org/S4306401751","display_name":"tub.dok (Hamburg University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I884043246","host_organization_name":"Hamburg University of Technology","host_organization_lineage":["https://openalex.org/I884043246"],"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 Paper"},{"id":"doi:10.48550/arxiv.1809.06146","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1809.06146","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1809.06146","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.06146","pdf_url":"https://arxiv.org/pdf/1809.06146","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2890253414.pdf","grobid_xml":"https://content.openalex.org/works/W2890253414.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1771410628","https://openalex.org/W1777239053","https://openalex.org/W1924762813","https://openalex.org/W2093601273","https://openalex.org/W2105899777","https://openalex.org/W2132984949","https://openalex.org/W2145339207","https://openalex.org/W2256388387","https://openalex.org/W2296073425","https://openalex.org/W2476301537","https://openalex.org/W2731828881","https://openalex.org/W2733961795","https://openalex.org/W2741594138","https://openalex.org/W2810758782","https://openalex.org/W2895806276","https://openalex.org/W2949608212","https://openalex.org/W2962736495","https://openalex.org/W2963293881","https://openalex.org/W2963577640","https://openalex.org/W2963864421","https://openalex.org/W2964001908","https://openalex.org/W2964308564","https://openalex.org/W2964327384","https://openalex.org/W2972758308","https://openalex.org/W2990747716","https://openalex.org/W6616173779","https://openalex.org/W6628764021","https://openalex.org/W6638018090","https://openalex.org/W6638088447","https://openalex.org/W6640253137","https://openalex.org/W6679390333","https://openalex.org/W6684921986","https://openalex.org/W6691895530","https://openalex.org/W6721408278","https://openalex.org/W6735789912","https://openalex.org/W6736021936","https://openalex.org/W6737937804","https://openalex.org/W6740801417","https://openalex.org/W6741302124","https://openalex.org/W6752819221","https://openalex.org/W6762379358"],"related_works":["https://openalex.org/W2978938326","https://openalex.org/W2951001370","https://openalex.org/W2950110427","https://openalex.org/W2890406131","https://openalex.org/W3200054052","https://openalex.org/W3105044139","https://openalex.org/W3000357849","https://openalex.org/W3214727553","https://openalex.org/W3129471596","https://openalex.org/W3105104454","https://openalex.org/W2823112946","https://openalex.org/W2999490157","https://openalex.org/W3094427810","https://openalex.org/W3158799570","https://openalex.org/W2947805761","https://openalex.org/W2971919016","https://openalex.org/W2964464273","https://openalex.org/W2795158776","https://openalex.org/W2970387978","https://openalex.org/W2810531268"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,77],"learning":[2,42,78,153],"has":[3,36],"recently":[4],"gained":[5],"a":[6,37,62,90,94,115],"focus":[7,68],"on":[8,17,40,69,80,112],"problems":[9],"where":[10,138,157],"policy":[11,124],"or":[12],"value":[13,19],"functions":[14],"are":[15,141],"based":[16,79],"universal":[18],"function":[20],"approximators":[21],"(UVFAs)":[22],"which":[23],"renders":[24],"them":[25],"independent":[26],"of":[27,34,47,64,75],"goals.":[28],"Evidence":[29],"exists":[30],"that":[31,67,110],"the":[32,41,45,49,73,132,136,151],"sampling":[33,51,71],"goals":[35,113,140],"strong":[38],"effect":[39],"performance,":[43],"and":[44,98,134],"problem":[46],"optimizing":[48],"goal":[50,70,87],"is":[52,61,119,159],"frequently":[53],"tackled":[54],"with":[55,114,161],"intrinsic":[56],"motivation":[57],"methods.":[58],"However,":[59],"there":[60],"lack":[63],"general":[65],"mechanisms":[66],"in":[72,155],"context":[74],"deep":[76,122],"UVFAs.":[81],"In":[82],"this":[83,101],"work,":[84],"we":[85],"introduce":[86],"masking":[88],"as":[89],"method":[91],"to":[92,99,103,150],"estimate":[93],"goal's":[95],"difficulty":[96,117],"level":[97,118],"exploit":[100],"estimation":[102],"realize":[104],"curriculum":[105],"learning.":[106],"Our":[107],"results":[108],"indicate":[109],"focusing":[111],"medium":[116],"appropriate":[120],"for":[121,131],"deterministic":[123],"gradient":[125],"(DDPG)":[126],"methods,":[127],"while":[128],"an":[129],"\u201caim":[130],"stars":[133],"reach":[135],"moon-strategy\u201d,":[137],"difficult":[139],"sampled":[142],"much":[143],"more":[144],"often":[145],"than":[146],"simple":[147],"goals,":[148],"leads":[149],"best":[152],"performance":[154],"cases":[156],"DDPG":[158],"combined":[160],"hindsight":[162],"experience":[163],"replay":[164],"(HER).":[165]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}