{"id":"https://openalex.org/W2979216345","doi":"https://doi.org/10.1109/devlrn.2019.8850723","title":"Efficient Intrinsically Motivated Robotic Grasping with Learning-Adaptive Imagination in Latent Space","display_name":"Efficient Intrinsically Motivated Robotic Grasping with Learning-Adaptive Imagination in Latent Space","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2979216345","doi":"https://doi.org/10.1109/devlrn.2019.8850723","mag":"2979216345"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2019.8850723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2019.8850723","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.04729","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Muhammad Burhan Hafez","orcid":null},"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"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cornelius Weber","orcid":null},"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"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Matthias Kerzel","orcid":null},"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"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":null,"display_name":"Stefan Wermter","orcid":null},"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"],"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":[],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":0.434,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.72417601,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9943000078201294,"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/T10982","display_name":"Motor Control and Adaptation","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6079999804496765},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5357000231742859},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5282999873161316},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.46480000019073486},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.41519999504089355},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.40290001034736633},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.37139999866485596}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6553999781608582},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6079999804496765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5997999906539917},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5357000231742859},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5282999873161316},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.46480000019073486},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.41519999504089355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40700000524520874},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.37139999866485596},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C100279318","wikidata":"https://www.wikidata.org/wiki/Q467440","display_name":"Sample space","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/devlrn.2019.8850723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2019.8850723","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:eprints.soton.ac.uk:495849","is_oa":false,"landing_page_url":"http://doi.org/10.1109/DEVLRN.2019.8850723>).","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:1910.04729","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.04729","pdf_url":"https://arxiv.org/pdf/1910.04729","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.04729","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.04729","pdf_url":"https://arxiv.org/pdf/1910.04729","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W755046805","https://openalex.org/W1491843047","https://openalex.org/W1964125855","https://openalex.org/W1989493426","https://openalex.org/W2004601027","https://openalex.org/W2013830186","https://openalex.org/W2065971571","https://openalex.org/W2082511574","https://openalex.org/W2100675387","https://openalex.org/W2141086920","https://openalex.org/W2145339207","https://openalex.org/W2621075271","https://openalex.org/W2738669288","https://openalex.org/W2771461682","https://openalex.org/W2795520063","https://openalex.org/W2803790180","https://openalex.org/W2898417779","https://openalex.org/W2932752459","https://openalex.org/W2962872206","https://openalex.org/W2963523627","https://openalex.org/W2978069508","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6696324988","https://openalex.org/W6730641667","https://openalex.org/W6740801417","https://openalex.org/W6746581380","https://openalex.org/W6751720535","https://openalex.org/W6752200371","https://openalex.org/W6756760058"],"related_works":[],"abstract_inverted_index":{"Combining":[0],"model-based":[1],"and":[2,79,126,134],"model-free":[3],"deep":[4],"reinforcement":[5],"learning":[6,86,122],"has":[7],"shown":[8],"great":[9],"promise":[10],"for":[11,62],"improving":[12],"sample":[13,132],"efficiency":[14,133],"on":[15,85,121],"complex":[16],"control":[17],"tasks":[18],"while":[19],"still":[20],"retaining":[21],"high":[22],"performance.":[23],"Incorporating":[24],"imagination":[25,45],"is":[26],"a":[27,43,139],"recent":[28],"effort":[29],"in":[30,76,138],"this":[31],"direction":[32],"inspired":[33],"by":[34],"human":[35],"mental":[36],"simulation":[37],"of":[38,56,71,114],"motor":[39],"behavior.":[40],"We":[41,117],"propose":[42],"learning-adaptive":[44],"approach":[46,67,120],"which,":[47],"unlike":[48],"previous":[49],"approaches,":[50],"takes":[51],"into":[52],"account":[53],"the":[54,57,64,89,99,111],"reliability":[55],"learned":[58,102],"dynamics":[59,74],"model":[60],"used":[61,105],"imagining":[63],"future.":[65],"Our":[66],"learns":[68],"an":[69,81],"ensemble":[70],"disjoint":[72],"local":[73],"models":[75,103],"latent":[77],"space":[78],"derives":[80],"intrinsic":[82],"reward":[83,141],"based":[84],"progress,":[87],"motivating":[88],"controller":[90],"to":[91,95,106],"take":[92],"actions":[93],"leading":[94],"data":[96],"that":[97,128],"improves":[98,131],"models.":[100],"The":[101],"are":[104],"generate":[107],"imagined":[108],"experiences,":[109],"augmenting":[110],"training":[112],"set":[113],"real":[115],"experiences.":[116],"evaluate":[118],"our":[119],"vision-based":[123],"robotic":[124],"grasping":[125],"show":[127],"it":[129],"significantly":[130],"achieves":[135],"near-optimal":[136],"performance":[137],"sparse":[140],"environment.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-10-10T00:00:00"}