{"id":"https://openalex.org/W2795520063","doi":"https://doi.org/10.1109/devlrn.2017.8329785","title":"Curiosity-driven exploration enhances motor skills of continuous actor-critic learner","display_name":"Curiosity-driven exploration enhances motor skills of continuous actor-critic learner","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2795520063","doi":"https://doi.org/10.1109/devlrn.2017.8329785","mag":"2795520063"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2017.8329785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2017.8329785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","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/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, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, University of Hamburg, 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, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, University of Hamburg, 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/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":"Stefan Wermter","raw_affiliation_strings":["Knowledge Technology, University of Hamburg, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":3.1155,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.93572768,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T11178","display_name":"Receptor Mechanisms and Signaling","score":0.9764999747276306,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11685","display_name":"Zebrafish Biomedical Research Applications","score":0.9573000073432922,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.9037990570068359},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7853884696960449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6718007922172546},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5906643867492676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5345204472541809},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5010573863983154},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.4998915195465088},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4591805636882782},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36276328563690186},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22279787063598633},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11562180519104004}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.9037990570068359},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7853884696960449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6718007922172546},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5906643867492676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5345204472541809},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5010573863983154},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.4998915195465088},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4591805636882782},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36276328563690186},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22279787063598633},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11562180519104004},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/devlrn.2017.8329785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2017.8329785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.soton.ac.uk:495807","is_oa":false,"landing_page_url":"http://doi.org/10.1109/DEVLRN.2017.8329785>).","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320875","display_name":"Deutscher Akademischer Austauschdienst","ror":"https://ror.org/039djdh30"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W326419249","https://openalex.org/W1491843047","https://openalex.org/W1982376520","https://openalex.org/W1989493426","https://openalex.org/W1991848143","https://openalex.org/W2004303440","https://openalex.org/W2034806191","https://openalex.org/W2098877457","https://openalex.org/W2100675387","https://openalex.org/W2100677568","https://openalex.org/W2101524054","https://openalex.org/W2101539915","https://openalex.org/W2105899777","https://openalex.org/W2107726111","https://openalex.org/W2116086091","https://openalex.org/W2138754805","https://openalex.org/W2139612737","https://openalex.org/W2140332127","https://openalex.org/W2145339207","https://openalex.org/W2150923691","https://openalex.org/W2161966552","https://openalex.org/W2189414631","https://openalex.org/W2280163991","https://openalex.org/W2417786368","https://openalex.org/W2771461682","https://openalex.org/W2962730405","https://openalex.org/W2963639957","https://openalex.org/W2963864421","https://openalex.org/W2963938771","https://openalex.org/W3041202696","https://openalex.org/W4285719527","https://openalex.org/W4307347247","https://openalex.org/W6611171155","https://openalex.org/W6629406372","https://openalex.org/W6680294583","https://openalex.org/W6683603353","https://openalex.org/W6684921986","https://openalex.org/W6685757253","https://openalex.org/W6695011786","https://openalex.org/W6716474083"],"related_works":["https://openalex.org/W3094054656","https://openalex.org/W4285676344","https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2120009678","https://openalex.org/W2037601570","https://openalex.org/W2912947802","https://openalex.org/W2123856982","https://openalex.org/W2108112111","https://openalex.org/W2060421996"],"abstract_inverted_index":{"Guiding":[0],"the":[1,42,53,69,92,97,103,109,134],"action":[2,73],"selection":[3],"mechanism":[4],"of":[5,44,55,58,72,91,99,118],"an":[6,64,88],"autonomous":[7],"agent":[8,139],"for":[9,67,81,133],"learning":[10,25,57,79],"control":[11,126],"behaviors":[12],"is":[13],"a":[14,76,129],"crucial":[15],"issue":[16],"in":[17,61],"reinforcement":[18,24,78],"learning.":[19],"While":[20],"classical":[21],"approaches":[22,36],"to":[23,27,111,141],"seem":[26],"be":[28],"deeply":[29],"dependent":[30],"on":[31,121],"external":[32],"feedback,":[33],"intrinsically":[34,135],"motivated":[35,136,146],"are":[37,144],"more":[38],"natural":[39],"and":[40,74,107,114,123],"follow":[41],"principles":[43],"infant":[45],"sensorimotor":[46],"development.":[47],"In":[48],"this":[49],"work,":[50],"we":[51],"investigate":[52],"role":[54],"incremental":[56],"predictive":[59,105],"models":[60,106],"generating":[62],"curiosity,":[63],"intrinsic":[65,115],"motivation,":[66],"directing":[68],"agent's":[70],"choice":[71],"propose":[75],"curiosity-driven":[77],"algorithm":[80,86,120],"continuous":[82],"motor":[83],"control.":[84],"Our":[85],"builds":[87],"internal":[89],"representation":[90],"state":[93],"space":[94],"that":[95,143],"handles":[96],"computation":[98],"curiosity":[100],"signals":[101],"using":[102],"learned":[104],"extends":[108],"Continuous-Actor-Critic-Learning-Automaton":[110],"use":[112],"extrinsic":[113,148],"feedback.":[116],"Evaluation":[117],"our":[119],"simple":[122],"complex":[124],"robotic":[125],"tasks":[127],"shows":[128],"significant":[130],"performance":[131],"gain":[132],"goal":[137],"reaching":[138],"compared":[140],"agents":[142],"only":[145],"by":[147],"rewards.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
