{"id":"https://openalex.org/W2898417779","doi":"https://doi.org/10.1515/pjbr-2019-0005","title":"Deep intrinsically motivated continuous actor-critic for efficient robotic visuomotor skill learning","display_name":"Deep intrinsically motivated continuous actor-critic for efficient robotic visuomotor skill learning","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2898417779","doi":"https://doi.org/10.1515/pjbr-2019-0005","mag":"2898417779"},"language":"en","primary_location":{"id":"doi:10.1515/pjbr-2019-0005","is_oa":true,"landing_page_url":"https://doi.org/10.1515/pjbr-2019-0005","pdf_url":"https://www.degruyter.com/downloadpdf/journals/pjbr/10/1/article-p14.pdf","source":{"id":"https://openalex.org/S4210226531","display_name":"Paladyn Journal of Behavioral Robotics","issn_l":"2081-4836","issn":["2081-4836"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Paladyn, Journal of Behavioral Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.degruyter.com/downloadpdf/journals/pjbr/10/1/article-p14.pdf","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"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Muhammad Burhan Hafez","raw_affiliation_strings":["Department of Informatics, University of Hamburg , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Hamburg , Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cornelius Weber","raw_affiliation_strings":["Department of Informatics, University of Hamburg , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Hamburg , Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Kerzel","raw_affiliation_strings":["Department of Informatics, University of Hamburg , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Hamburg , Germany","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, University of Hamburg , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Hamburg , Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5042086036"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":{"value":1000,"currency":"EUR","value_usd":1078},"apc_paid":{"value":1000,"currency":"EUR","value_usd":1078},"fwci":2.3214,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.90975449,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"10","issue":"1","first_page":"14","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9948999881744385,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9948999881744385,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7951644659042358},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7207471132278442},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7062539458274841},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6956787705421448},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5850474238395691},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.5379844903945923},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5073515772819519},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4964974522590637},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48588865995407104},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.48090624809265137},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4248512089252472},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4217255413532257},{"id":"https://openalex.org/keywords/physics-engine","display_name":"Physics engine","score":0.4163439869880676},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34136396646499634},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12565600872039795}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7951644659042358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7207471132278442},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7062539458274841},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6956787705421448},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5850474238395691},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.5379844903945923},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5073515772819519},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4964974522590637},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48588865995407104},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.48090624809265137},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4248512089252472},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4217255413532257},{"id":"https://openalex.org/C190390380","wikidata":"https://www.wikidata.org/wiki/Q62505","display_name":"Physics engine","level":2,"score":0.4163439869880676},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34136396646499634},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12565600872039795},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1515/pjbr-2019-0005","is_oa":true,"landing_page_url":"https://doi.org/10.1515/pjbr-2019-0005","pdf_url":"https://www.degruyter.com/downloadpdf/journals/pjbr/10/1/article-p14.pdf","source":{"id":"https://openalex.org/S4210226531","display_name":"Paladyn Journal of Behavioral Robotics","issn_l":"2081-4836","issn":["2081-4836"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Paladyn, Journal of Behavioral Robotics","raw_type":"journal-article"},{"id":"pmh:oai:eprints.soton.ac.uk:495810","is_oa":false,"landing_page_url":"http://doi.org/10.1515/pjbr-2019-0005>).","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:1810.11388","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.11388","pdf_url":"https://arxiv.org/pdf/1810.11388","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":"pmh:oai:doaj.org/article:4ae7b9351faf4e3c984664aeda28b721","is_oa":true,"landing_page_url":"https://doaj.org/article/4ae7b9351faf4e3c984664aeda28b721","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Paladyn, Vol 10, Iss 1, Pp 14-29 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1515/pjbr-2019-0005","is_oa":true,"landing_page_url":"https://doi.org/10.1515/pjbr-2019-0005","pdf_url":"https://www.degruyter.com/downloadpdf/journals/pjbr/10/1/article-p14.pdf","source":{"id":"https://openalex.org/S4210226531","display_name":"Paladyn Journal of Behavioral Robotics","issn_l":"2081-4836","issn":["2081-4836"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Paladyn, Journal of Behavioral Robotics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1819950688","display_name":null,"funder_award_id":"57214224","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6114367821","display_name":null,"funder_award_id":"57214224","funder_id":"https://openalex.org/F4320320875","funder_display_name":"Deutscher Akademischer Austauschdienst"},{"id":"https://openalex.org/G6276684567","display_name":null,"funder_award_id":"TRR 169","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2898417779.pdf","grobid_xml":"https://content.openalex.org/works/W2898417779.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W620953717","https://openalex.org/W755046805","https://openalex.org/W779494576","https://openalex.org/W1522301498","https://openalex.org/W1968962398","https://openalex.org/W1987933853","https://openalex.org/W2010580694","https://openalex.org/W2029514605","https://openalex.org/W2034806191","https://openalex.org/W2057256606","https://openalex.org/W2065971571","https://openalex.org/W2082511574","https://openalex.org/W2100675387","https://openalex.org/W2101524054","https://openalex.org/W2139612737","https://openalex.org/W2145339207","https://openalex.org/W2151834591","https://openalex.org/W2154997814","https://openalex.org/W2181068523","https://openalex.org/W2201581102","https://openalex.org/W2417089653","https://openalex.org/W2417786368","https://openalex.org/W2511906965","https://openalex.org/W2551887912","https://openalex.org/W2594223991","https://openalex.org/W2603088459","https://openalex.org/W2614839826","https://openalex.org/W2738669288","https://openalex.org/W2751973545","https://openalex.org/W2767077819","https://openalex.org/W2771461682","https://openalex.org/W2774354230","https://openalex.org/W2774915412","https://openalex.org/W2783657760","https://openalex.org/W2795520063","https://openalex.org/W2903063684","https://openalex.org/W2950872548","https://openalex.org/W2962730405","https://openalex.org/W2963262099","https://openalex.org/W2963477884","https://openalex.org/W2963523627","https://openalex.org/W2963577640","https://openalex.org/W2963634205","https://openalex.org/W2963639957","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W4293396018","https://openalex.org/W4297804343"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2145836866","https://openalex.org/W2803255133"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"this":[2],"paper,":[3],"we":[4],"present":[5],"a":[6,28,41,133,139],"new":[7],"intrinsically":[8],"motivated":[9],"actor-critic":[10,96,110],"algorithm":[11,121],"for":[12,112,122],"learning":[13,77,126],"continuous":[14,113],"motor":[15],"skills":[16,131],"directly":[17],"from":[18,115],"raw":[19],"visual":[20,51],"input.":[21],"Our":[22,98],"neural":[23],"architecture":[24],"is":[25,46,58,84,100],"composed":[26],"of":[27,40,69,94,125],"critic":[29],"and":[30,103,129,137,161,167],"an":[31,67,79],"actor":[32],"network.":[33],"Both":[34],"networks":[35],"receive":[36],"the":[37,50,54,63,87,92,95,108,123,146,158],"hidden":[38,56],"representation":[39,57],"deep":[42],"convolutional":[43],"autoencoder":[44],"which":[45,83],"trained":[47],"to":[48,61,90],"reconstruct":[49],"input,":[52],"while":[53],"centre-most":[55],"also":[59],"optimized":[60],"estimate":[62],"state":[64],"value.":[65],"Separately,":[66],"ensemble":[68],"predictive":[70],"world":[71],"models":[72],"generates,":[73],"based":[74],"on":[75,132,138],"its":[76],"progress,":[78],"intrinsic":[80],"reward":[81,89],"signal":[82],"combined":[85],"with":[86,150],"extrinsic":[88],"guide":[91],"exploration":[93],"learner.":[97],"approach":[99,152],"more":[101,105],"data-efficient":[102],"inherently":[104],"stable":[106],"than":[107,157],"existing":[109],"methods":[111],"control":[114,147],"pixel":[116],"data.":[117],"We":[118],"evaluate":[119],"our":[120,151],"task":[124],"robotic":[127],"reaching":[128],"grasping":[130],"realistic":[134],"physics":[135],"simulator":[136],"humanoid":[140],"robot.":[141],"The":[142],"results":[143],"show":[144],"that":[145],"policies":[148],"learned":[149],"can":[153],"achieve":[154],"better":[155],"performance":[156],"compared":[159],"state-of-the-art":[160],"baseline":[162],"algorithms":[163],"in":[164],"both":[165],"dense-reward":[166],"challenging":[168],"sparse-reward":[169],"settings.":[170]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2018-11-02T00:00:00"}