{"id":"https://openalex.org/W2726535717","doi":"https://doi.org/10.1109/devlrn.2017.8329828","title":"A deep reinforcement learning based model supporting object familiarization","display_name":"A deep reinforcement learning based model supporting object familiarization","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2726535717","doi":"https://doi.org/10.1109/devlrn.2017.8329828","mag":"2726535717"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2017.8329828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2017.8329828","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":true,"oa_status":"green","oa_url":"https://pub.uni-bielefeld.de/record/2911974","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019898352","display_name":"Maximilian Panzner","orcid":"https://orcid.org/0000-0001-5607-6168"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Maximilian Panzner","raw_affiliation_strings":["Semantic Computing Group, Bielefeld University"],"affiliations":[{"raw_affiliation_string":"Semantic Computing Group, Bielefeld University","institution_ids":["https://openalex.org/I20121455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056086147","display_name":"Philipp Cimiano","orcid":"https://orcid.org/0000-0002-4771-441X"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Cimiano","raw_affiliation_strings":["Semantic Computing Group, Bielefeld University"],"affiliations":[{"raw_affiliation_string":"Semantic Computing Group, Bielefeld University","institution_ids":["https://openalex.org/I20121455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019898352"],"corresponding_institution_ids":["https://openalex.org/I20121455"],"apc_list":null,"apc_paid":null,"fwci":0.2076,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63287414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"344","last_page":"349"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9896000027656555,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9840999841690063,"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":0.73470139503479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6895951628684998},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5838592052459717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5699795484542847},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.5594134330749512},{"id":"https://openalex.org/keywords/cognitive-robotics","display_name":"Cognitive robotics","score":0.5483038425445557},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5018119812011719},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.415014386177063},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.41082391142845154},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.34701007604599},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.2712451219558716},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14356699585914612}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.73470139503479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6895951628684998},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5838592052459717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5699795484542847},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5594134330749512},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.5483038425445557},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5018119812011719},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.415014386177063},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41082391142845154},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.34701007604599},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2712451219558716},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14356699585914612},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/devlrn.2017.8329828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2017.8329828","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:pub.librecat.org:2911974","is_oa":true,"landing_page_url":"https://pub.uni-bielefeld.de/record/2911974","pdf_url":null,"source":{"id":"https://openalex.org/S4306401671","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Panzner M, Cimiano P. A Deep Reinforcement Learning Based Model Supporting Object Familiarization. In:  <em>Proceedings of the 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics</em>. Lisbon, Portugal;  2017.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pub.librecat.org:2914356","is_oa":true,"landing_page_url":"https://pub.uni-bielefeld.de/record/2914356","pdf_url":null,"source":{"id":"https://openalex.org/S4306401671","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Panzner M, Cimiano P. A Deep Reinforcement Learning Based Model Supporting Object Familiarization. Presented at the International Conference on Development and Learning and on Epigenetic Robotics, Instituto Superior Tecnico (IST), Lisbon, Portugal.","raw_type":"info:eu-repo/semantics/conference_abstract"}],"best_oa_location":{"id":"pmh:oai:pub.librecat.org:2911974","is_oa":true,"landing_page_url":"https://pub.uni-bielefeld.de/record/2911974","pdf_url":null,"source":{"id":"https://openalex.org/S4306401671","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Panzner M, Cimiano P. A Deep Reinforcement Learning Based Model Supporting Object Familiarization. In:  <em>Proceedings of the 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics</em>. Lisbon, Portugal;  2017.","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W172298727","https://openalex.org/W1522301498","https://openalex.org/W1757796397","https://openalex.org/W1836465849","https://openalex.org/W2095705004","https://openalex.org/W2100677568","https://openalex.org/W2115211925","https://openalex.org/W2121863487","https://openalex.org/W2139612737","https://openalex.org/W2145339207","https://openalex.org/W2146502635","https://openalex.org/W2155968351","https://openalex.org/W2171994365","https://openalex.org/W2746553466","https://openalex.org/W2949117887","https://openalex.org/W2963285578","https://openalex.org/W2963864421","https://openalex.org/W2964121744","https://openalex.org/W4298857966","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6674330103","https://openalex.org/W6680292960","https://openalex.org/W6681435938","https://openalex.org/W6684921986","https://openalex.org/W6685562342"],"related_works":["https://openalex.org/W1906023716","https://openalex.org/W2891970620","https://openalex.org/W1969477307","https://openalex.org/W2513760693","https://openalex.org/W1211648536","https://openalex.org/W1990035816","https://openalex.org/W2484031233","https://openalex.org/W4246694033","https://openalex.org/W2021057782","https://openalex.org/W1975212515"],"abstract_inverted_index":{"An":[0],"important":[1,56],"ability":[2,8],"of":[3,15,27,30,61,82,87,128,160,163,167,176],"cognitive":[4,42,74],"systems":[5,43,75],"is":[6,54,98,150],"the":[7,13,28,59,80,85,113,144,158,161,165,174],"to":[9,23,44,76,110,124],"familiarize":[10,45,77],"themselves":[11,78],"with":[12,46,79],"properties":[14,81],"objects":[16,47,83],"and":[17,84,118],"their":[18,31,88,119,129],"environment":[19],"as":[20,22,171,173],"well":[21,172],"develop":[24],"an":[25,55],"understanding":[26],"consequences":[29,121],"own":[32,116],"actions":[33,89,117],"on":[34,90],"physical":[35],"objects.":[36],"Developing":[37],"developmental":[38,62,101],"approaches":[39,170],"that":[40,72,103,105],"allow":[41],"in":[48,92,122,137,142],"this":[49,65],"sense":[50],"via":[51,152],"guided":[52],"self-exploration":[53,94],"challenge":[57],"within":[58],"field":[60],"robotics.":[63],"In":[64],"paper":[66],"we":[67],"present":[68],"a":[69,93,108,133,138,153],"novel":[70],"approach":[71,97,135],"allows":[73],"effects":[86],"them":[91],"fashion.":[95],"Our":[96],"inspired":[99],"by":[100],"studies":[102],"hypothesize":[104],"infants":[106],"have":[107],"propensity":[109],"systematically":[111],"explore":[112],"connection":[114],"between":[115],"perceptual":[120],"order":[123],"support":[125],"inter-modal":[126],"calibration":[127],"bodies.":[130],"We":[131,156],"propose":[132],"reinforcement-based":[134],"operating":[136],"continuous":[139],"state":[140],"space":[141],"which":[143],"function":[145],"predicting":[146],"cumulated":[147],"future":[148],"rewards":[149],"learned":[151],"deep":[154],"Q-network.":[155],"investigate":[157],"impact":[159,166,175],"structure":[162],"rewards,":[164],"different":[168,177],"regularization":[169],"exploration":[178],"strategies.":[179]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}