{"id":"https://openalex.org/W2547065907","doi":"https://doi.org/10.1109/iros.2016.7759581","title":"Improved deep reinforcement learning for robotics through distribution-based experience retention","display_name":"Improved deep reinforcement learning for robotics through distribution-based experience retention","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2547065907","doi":"https://doi.org/10.1109/iros.2016.7759581","mag":"2547065907"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2016.7759581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2016.7759581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://resolver.tudelft.nl/uuid:1f7633c7-d884-4947-8aef-0538a6cf8f74","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033347648","display_name":"Tim de Bruin","orcid":"https://orcid.org/0000-0003-1741-0850"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Tim de Bruin","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035229829","display_name":"Jens Kober","orcid":"https://orcid.org/0000-0001-7257-5434"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jens Kober","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008547992","display_name":"Karl Tuyls","orcid":"https://orcid.org/0000-0001-7929-1944"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["GB","NL"],"is_corresponding":false,"raw_author_name":"Karl Tuyls","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology","Department of Computer Science, University of Liverpool"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Department of Computer Science, University of Liverpool","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084264842","display_name":"Robert Babu\u0161ka","orcid":"https://orcid.org/0000-0001-9578-8598"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Robert Babuska","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3947","last_page":"3952"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.965499997138977,"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":0.8008817434310913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7565706968307495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7276037931442261},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7155187129974365},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6843266487121582},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6573144197463989},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6063955426216125},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5816823244094849},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5534600019454956},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.515489399433136},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1359556019306183},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12114942073822021}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8008817434310913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7565706968307495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7276037931442261},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7155187129974365},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6843266487121582},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6573144197463989},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6063955426216125},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5816823244094849},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5534600019454956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.515489399433136},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1359556019306183},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12114942073822021},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2016.7759581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2016.7759581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:tud:oai:tudelft.nl:uuid:1f7633c7-d884-4947-8aef-0538a6cf8f74","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:1f7633c7-d884-4947-8aef-0538a6cf8f74","pdf_url":"http://resolver.tudelft.nl/uuid:1f7633c7-d884-4947-8aef-0538a6cf8f74","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"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":"Proceedings of the 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS): IROS 2016","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"pmh:tud:oai:tudelft.nl:uuid:1f7633c7-d884-4947-8aef-0538a6cf8f74","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:1f7633c7-d884-4947-8aef-0538a6cf8f74","pdf_url":"http://resolver.tudelft.nl/uuid:1f7633c7-d884-4947-8aef-0538a6cf8f74","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"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":"Proceedings of the 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS): IROS 2016","raw_type":"info:eu-repo/semantics/conferencepaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2547065907.pdf","grobid_xml":"https://content.openalex.org/works/W2547065907.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1576278180","https://openalex.org/W1977655452","https://openalex.org/W2113839990","https://openalex.org/W2118020555","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2148828700","https://openalex.org/W2155007355","https://openalex.org/W2165150801","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2963477884","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964161785","https://openalex.org/W3148685027","https://openalex.org/W4302570325","https://openalex.org/W6682849425","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6692846177"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W3162204513","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"seen":[3],"a":[4,47,53],"growing":[5],"interest":[6],"in":[7,17,76],"the":[8,32,35,44,61,64,104,108,124,131,137,143],"use":[9],"of":[10,34,43,107,135],"deep":[11],"neural":[12],"networks":[13],"as":[14,86],"function":[15],"approximators":[16],"reinforcement":[18],"learning.":[19,71,96,118],"In":[20],"this":[21],"paper,":[22],"an":[23,150],"experience":[24,122,144],"replay":[25],"method":[26,62,98,125],"is":[27,40,58,81,99],"proposed":[28,133],"that":[29,31,42,60],"ensures":[30],"distribution":[33],"experiences":[36],"used":[37],"for":[38,66,87,93,116,120,153],"training":[39],"between":[41],"policy":[45],"and":[46,92],"uniform":[48],"distribution.":[49],"Through":[50],"experiments":[51],"on":[52],"magnetic":[54],"manipulation":[55],"task":[56],"it":[57,74,114,149],"shown":[59,101],"reduces":[63],"need":[65],"sustained":[67,79],"exhaustive":[68],"exploration":[69,80],"during":[70],"This":[72],"makes":[73,148],"attractive":[75,115,151],"scenarios":[77],"where":[78],"in-feasible":[82],"or":[83],"undesirable,":[84],"such":[85],"physical":[88],"systems":[89],"like":[90],"robots":[91,154],"life":[94],"long":[95],"The":[97],"also":[100],"to":[102,130,141],"improve":[103],"generalization":[105],"performance":[106],"trained":[109],"policy,":[110],"which":[111,147],"can":[112],"make":[113],"transfer":[117],"Finally,":[119],"small":[121],"databases":[123],"performs":[126],"favorably":[127],"when":[128],"compared":[129],"recently":[132],"alternative":[134],"using":[136],"temporal":[138],"difference":[139],"error":[140],"determine":[142],"sample":[145],"distribution,":[146],"option":[152],"with":[155],"limited":[156],"memory":[157],"capacity.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-11-11T00:00:00"}