{"id":"https://openalex.org/W2920806842","doi":"https://doi.org/10.1109/cdc40024.2019.9029503","title":"Deep Reinforcement Learning with Feedback-based Exploration","display_name":"Deep Reinforcement Learning with Feedback-based Exploration","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2920806842","doi":"https://doi.org/10.1109/cdc40024.2019.9029503","mag":"2920806842"},"language":"en","primary_location":{"id":"doi:10.1109/cdc40024.2019.9029503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.06151","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036678008","display_name":"Jan Scholten","orcid":null},"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":true,"raw_author_name":"Jan Scholten","raw_affiliation_strings":["Cognitive Robotics Department, Delft University of Technology"],"affiliations":[{"raw_affiliation_string":"Cognitive Robotics Department, Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026397338","display_name":"Daan Wout","orcid":null},"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":"Daan Wout","raw_affiliation_strings":["Cognitive Robotics Department, Delft University of Technology"],"affiliations":[{"raw_affiliation_string":"Cognitive Robotics Department, Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028010633","display_name":"Carlos Celemin","orcid":"https://orcid.org/0000-0001-8880-0966"},"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":"Carlos Celemin","raw_affiliation_strings":["Cognitive Robotics Department, Delft University of Technology"],"affiliations":[{"raw_affiliation_string":"Cognitive Robotics Department, Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","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":["Cognitive Robotics Department, Delft University of Technology"],"affiliations":[{"raw_affiliation_string":"Cognitive Robotics Department, Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036678008"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":0.4329,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70575387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"803","last_page":"808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9908000230789185,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9847999811172485,"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":0.7685986757278442},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.757337212562561},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.712466835975647},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.6406705379486084},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6186146140098572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.603447675704956},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6028753519058228},{"id":"https://openalex.org/keywords/corrective-feedback","display_name":"Corrective feedback","score":0.5887512564659119},{"id":"https://openalex.org/keywords/feedback-control","display_name":"Feedback control","score":0.5395359992980957},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4557885229587555},{"id":"https://openalex.org/keywords/incremental-learning","display_name":"Incremental learning","score":0.42734163999557495},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.1647433638572693},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1550808548927307},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11855438351631165}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7685986757278442},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.757337212562561},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.712466835975647},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.6406705379486084},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6186146140098572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.603447675704956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6028753519058228},{"id":"https://openalex.org/C2779305910","wikidata":"https://www.wikidata.org/wiki/Q5172809","display_name":"Corrective feedback","level":2,"score":0.5887512564659119},{"id":"https://openalex.org/C3018651601","wikidata":"https://www.wikidata.org/wiki/Q183635","display_name":"Feedback control","level":2,"score":0.5395359992980957},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4557885229587555},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.42734163999557495},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.1647433638572693},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1550808548927307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11855438351631165},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cdc40024.2019.9029503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.06151","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.06151","pdf_url":"https://arxiv.org/pdf/1903.06151","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:tudelft.nl:uuid:acb6ea20-5e74-457e-84cd-56e33dd72979","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:acb6ea20-5e74-457e-84cd-56e33dd72979","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},{"id":"pmh:oai:tudelft.nl:uuid:f0be4b85-7957-445c-b226-c0754ee05ae1","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:f0be4b85-7957-445c-b226-c0754ee05ae1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.06151","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.06151","pdf_url":"https://arxiv.org/pdf/1903.06151","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1522301498","https://openalex.org/W1977655452","https://openalex.org/W2098441518","https://openalex.org/W2116157560","https://openalex.org/W2121863487","https://openalex.org/W2129659607","https://openalex.org/W2135721773","https://openalex.org/W2145339207","https://openalex.org/W2156682402","https://openalex.org/W2156737235","https://openalex.org/W2280163991","https://openalex.org/W2294422333","https://openalex.org/W2336416123","https://openalex.org/W2557519264","https://openalex.org/W2620777928","https://openalex.org/W2741122588","https://openalex.org/W2754517384","https://openalex.org/W2756826236","https://openalex.org/W2761873684","https://openalex.org/W2781726626","https://openalex.org/W2801182767","https://openalex.org/W2806174881","https://openalex.org/W2885467852","https://openalex.org/W2893649979","https://openalex.org/W2921379287","https://openalex.org/W2962853428","https://openalex.org/W2963099939","https://openalex.org/W2963423916","https://openalex.org/W2963864421","https://openalex.org/W2963938771","https://openalex.org/W2964263543","https://openalex.org/W2964291307","https://openalex.org/W3001507548","https://openalex.org/W3037207827","https://openalex.org/W3092065440","https://openalex.org/W3122152400","https://openalex.org/W3148685027","https://openalex.org/W4286365857","https://openalex.org/W4288416984","https://openalex.org/W4298876402","https://openalex.org/W4301337144","https://openalex.org/W4321392130","https://openalex.org/W4388475847","https://openalex.org/W4394666657","https://openalex.org/W6631190155","https://openalex.org/W6674812091","https://openalex.org/W6677262939","https://openalex.org/W6679960057","https://openalex.org/W6683195989","https://openalex.org/W6683300800","https://openalex.org/W6684921986","https://openalex.org/W6695011786","https://openalex.org/W6696972564","https://openalex.org/W6720563850","https://openalex.org/W6738414333","https://openalex.org/W6739585900","https://openalex.org/W6742461812","https://openalex.org/W6744838376","https://openalex.org/W6747473740","https://openalex.org/W6752027418","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4390193239","https://openalex.org/W4213266652","https://openalex.org/W2899872056","https://openalex.org/W3164368351","https://openalex.org/W2998735842","https://openalex.org/W4386265809","https://openalex.org/W3133706844","https://openalex.org/W2893467525","https://openalex.org/W2791575529","https://openalex.org/W3007191706"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"has":[3],"enabled":[4],"the":[5,14,55,58,65,75,79,89,109,137],"control":[6,106],"of":[7,16,19,78,95,108],"increasingly":[8],"complex":[9],"and":[10,38,45,57,121,129],"high-dimensional":[11],"problems.":[12],"However,":[13],"need":[15],"vast":[17],"amounts":[18],"data":[20],"before":[21],"reasonable":[22],"performance":[23],"is":[24,61],"attained":[25],"prevents":[26],"its":[27],"widespread":[28],"application.":[29],"We":[30,87],"employ":[31],"binary":[32],"corrective":[33,59],"feedback":[34,60],"as":[35,68],"a":[36,73],"general":[37],"intuitive":[39],"manner":[40],"to":[41,123],"incorporate":[42],"human":[43,128],"intuition":[44],"domain":[46],"knowledge":[47],"in":[48,54,64,98,116],"model-free":[49],"machine":[50],"learning.":[51],"The":[52],"uncertainty":[53],"policy":[56],"combined":[62],"directly":[63],"action":[66],"space":[67],"probabilistic":[69],"conditional":[70],"exploration.":[71],"As":[72],"result,":[74],"greatest":[76],"part":[77],"otherwise":[80],"ignorant":[81],"learning":[82],"process":[83],"can":[84],"be":[85],"avoided.":[86],"demonstrate":[88],"proposed":[90],"method,":[91],"Predictive":[92],"Probabilistic":[93],"Merging":[94],"Policies":[96],"(PPMP),":[97],"combination":[99],"with":[100],"DDPG.":[101],"In":[102],"experiments":[103],"on":[104],"continuous":[105],"problems":[107],"OpenAI":[110],"Gym,":[111],"we":[112,133],"achieve":[113],"drastic":[114],"improvements":[115],"sample":[117],"efficiency,":[118],"final":[119],"performance,":[120],"robustness":[122],"erroneous":[124],"feedback,":[125],"both":[126],"for":[127],"synthetic":[130],"feedback.":[131],"Additionally,":[132],"show":[134],"solutions":[135],"beyond":[136],"demonstrated":[138],"knowledge.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}