{"id":"https://openalex.org/W2946299167","doi":"https://doi.org/10.1109/ijcnn.2019.8852254","title":"Curious Meta-Controller: Adaptive Alternation between Model-Based and Model-Free Control in Deep Reinforcement Learning","display_name":"Curious Meta-Controller: Adaptive Alternation between Model-Based and Model-Free Control in Deep Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2946299167","doi":"https://doi.org/10.1109/ijcnn.2019.8852254","mag":"2946299167"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8852254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","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/1905.01718","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042086036","display_name":"Muhammad Burhan Hafez","orcid":"https://orcid.org/0000-0003-1670-8962"},"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"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Muhammad Burhan Hafez","raw_affiliation_strings":["Knowledge Technology, University of Hamburg, Germany","[Knowledge Technology, University of Hamburg, Germany]"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, University of Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]},{"raw_affiliation_string":"[Knowledge Technology, University of Hamburg, Germany]","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102025003","display_name":"Cornelius Weber","orcid":"https://orcid.org/0000-0001-5163-938X"},"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"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cornelius Weber","raw_affiliation_strings":["Knowledge Technology, University of Hamburg, Germany","[Knowledge Technology, University of Hamburg, Germany]"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, University of Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]},{"raw_affiliation_string":"[Knowledge Technology, University of Hamburg, Germany]","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040045142","display_name":"Matthias Kerzel","orcid":"https://orcid.org/0000-0002-1378-0435"},"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"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Kerzel","raw_affiliation_strings":["Knowledge Technology, University of Hamburg, Germany","[Knowledge Technology, University of Hamburg, Germany]"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, University of Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]},{"raw_affiliation_string":"[Knowledge Technology, University of Hamburg, Germany]","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"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/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]},{"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":["Knowledge Technology, University of Hamburg, Germany","[Knowledge Technology, University of Hamburg, Germany]"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, University of Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]},{"raw_affiliation_string":"[Knowledge Technology, University of Hamburg, Germany]","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5042086036"],"corresponding_institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"],"apc_list":null,"apc_paid":null,"fwci":0.1447,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56094585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T10462","display_name":"Reinforcement Learning in Robotics","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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.991100013256073,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8467115163803101},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7661834359169006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6659854650497437},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5853139162063599},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.5400432348251343},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4920332133769989},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48440390825271606},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.47853121161460876},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4127146005630493},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06873819231987}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8467115163803101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7661834359169006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6659854650497437},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5853139162063599},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.5400432348251343},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4920332133769989},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48440390825271606},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.47853121161460876},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4127146005630493},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06873819231987},{"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/ijcnn.2019.8852254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.soton.ac.uk:495848","is_oa":false,"landing_page_url":"http://doi.org/10.1109/IJCNN.2019.8852254>).","pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:arXiv.org:1905.01718","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.01718","pdf_url":"https://arxiv.org/pdf/1905.01718","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"},{"id":"doi:10.48550/arxiv.1905.01718","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.01718","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"},{"id":"mag:2946299167","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.01718","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.01718","pdf_url":"https://arxiv.org/pdf/1905.01718","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/F4320320875","display_name":"Deutscher Akademischer Austauschdienst","ror":"https://ror.org/039djdh30"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2946299167.pdf","grobid_xml":"https://content.openalex.org/works/W2946299167.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W755046805","https://openalex.org/W779494576","https://openalex.org/W1491843047","https://openalex.org/W1522301498","https://openalex.org/W1989493426","https://openalex.org/W2013830186","https://openalex.org/W2034806191","https://openalex.org/W2082511574","https://openalex.org/W2145339207","https://openalex.org/W2170651797","https://openalex.org/W2228005960","https://openalex.org/W2417786368","https://openalex.org/W2535161073","https://openalex.org/W2561776174","https://openalex.org/W2572640103","https://openalex.org/W2614839826","https://openalex.org/W2733961795","https://openalex.org/W2738669288","https://openalex.org/W2771461682","https://openalex.org/W2774354230","https://openalex.org/W2795756076","https://openalex.org/W2800631177","https://openalex.org/W2898050260","https://openalex.org/W2898417779","https://openalex.org/W2903063684","https://openalex.org/W2962872206","https://openalex.org/W2963477884","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2964036701","https://openalex.org/W2964161785","https://openalex.org/W6622487243","https://openalex.org/W6631190155","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6696324988","https://openalex.org/W6716474083","https://openalex.org/W6730641667","https://openalex.org/W6731917250","https://openalex.org/W6735033012","https://openalex.org/W6740801417","https://openalex.org/W6746581380","https://openalex.org/W6748012927","https://openalex.org/W6750409132","https://openalex.org/W6756760058"],"related_works":["https://openalex.org/W2978069508","https://openalex.org/W3100226171","https://openalex.org/W2743381431","https://openalex.org/W2198225532","https://openalex.org/W2795908317","https://openalex.org/W2951553872","https://openalex.org/W2980297462","https://openalex.org/W3010862467","https://openalex.org/W3104268834","https://openalex.org/W2945500224","https://openalex.org/W3084024636","https://openalex.org/W2966950754","https://openalex.org/W2803743229","https://openalex.org/W3104444496","https://openalex.org/W2945709907","https://openalex.org/W2948198678","https://openalex.org/W2964093801","https://openalex.org/W2626860042","https://openalex.org/W2953084784","https://openalex.org/W2569028745"],"abstract_inverted_index":{"Recent":[0],"success":[1],"in":[2,25,36,98,128],"deep":[3],"reinforcement":[4],"learning":[5,89,119],"for":[6],"continuous":[7],"control":[8,81],"has":[9],"been":[10],"dominated":[11],"by":[12,65],"model-free":[13,80],"approaches":[14,49,64],"which,":[15],"unlike":[16],"model-based":[17,48,78],"approaches,":[18],"do":[19],"not":[20],"suffer":[21],"from":[22,125],"representational":[23],"limitations":[24],"making":[26],"assumptions":[27],"about":[28],"the":[29,59,62,88,96,111],"world":[30],"dynamics":[31,97],"and":[32,79,114,122,131],"model":[33,94],"errors":[34],"inevitable":[35],"complex":[37],"domains.":[38],"However,":[39],"they":[40],"require":[41],"a":[42,83,92,99],"lot":[43],"of":[44,61,91,95],"experiences":[45],"compared":[46],"to":[47,57],"that":[50,105],"are":[51],"typically":[52],"more":[53],"sample-efficient.":[54],"We":[55,103],"propose":[56],"combine":[58],"benefits":[60],"two":[63],"presenting":[66],"an":[67],"integrated":[68],"approach":[69,74,107],"called":[70],"Curious":[71],"Meta-Controller.":[72],"Our":[73],"alternates":[75],"adaptively":[76],"between":[77],"using":[82],"curiosity":[84],"feedback":[85],"based":[86],"on":[87,118],"progress":[90],"neural":[93],"learned":[100],"latent":[101],"space.":[102],"demonstrate":[104],"our":[106],"can":[108],"significantly":[109],"improve":[110],"sample":[112],"efficiency":[113],"achieve":[115],"near-optimal":[116],"performance":[117],"robotic":[120],"reaching":[121],"grasping":[123],"tasks":[124],"raw-pixel":[126],"input":[127],"both":[129],"dense":[130],"sparse":[132],"reward":[133],"settings.":[134]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}