{"id":"https://openalex.org/W4311508998","doi":"https://doi.org/10.1007/s00521-022-07949-0","title":"Quantifying the effect of feedback frequency in interactive reinforcement learning for robotic tasks","display_name":"Quantifying the effect of feedback frequency in interactive reinforcement learning for robotic tasks","publication_year":2022,"publication_date":"2022-12-05","ids":{"openalex":"https://openalex.org/W4311508998","doi":"https://doi.org/10.1007/s00521-022-07949-0"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-022-07949-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-022-07949-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-022-07949-0.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-022-07949-0.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067081068","display_name":"Daniel Harnack","orcid":"https://orcid.org/0000-0001-6255-0321"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Daniel Harnack","raw_affiliation_strings":["Robotics Innovation Center, Deutsches Forschungszentrum f\u00fcr K\u00fcnstliche Intelligenz (DFKI) GmbH, Robert-Hooke-Stra\u00dfe 1, 28359, Bremen, Bremen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Innovation Center, Deutsches Forschungszentrum f\u00fcr K\u00fcnstliche Intelligenz (DFKI) GmbH, Robert-Hooke-Stra\u00dfe 1, 28359, Bremen, Bremen, Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644692","display_name":"Julie Pivin-Bachler","orcid":"https://orcid.org/0009-0005-9624-5057"},"institutions":[{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Julie Pivin-Bachler","raw_affiliation_strings":["Robotics and Interactive Systems \u2013 UPSSITECH, University Paul Sabatier, 118 Route de Narbonne, 31062, Toulouse, Occitanie, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and Interactive Systems \u2013 UPSSITECH, University Paul Sabatier, 118 Route de Narbonne, 31062, Toulouse, Occitanie, France","institution_ids":["https://openalex.org/I134560555"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040711005","display_name":"Nicol\u00e1s Navarro-Guerrero","orcid":"https://orcid.org/0000-0003-1164-5579"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nicol\u00e1s Navarro-Guerrero","raw_affiliation_strings":["Robotics Innovation Center, Deutsches Forschungszentrum f\u00fcr K\u00fcnstliche Intelligenz (DFKI) GmbH, Robert-Hooke-Stra\u00dfe 1, 28359, Bremen, Bremen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1164-5579","affiliations":[{"raw_affiliation_string":"Robotics Innovation Center, Deutsches Forschungszentrum f\u00fcr K\u00fcnstliche Intelligenz (DFKI) GmbH, Robert-Hooke-Stra\u00dfe 1, 28359, Bremen, Bremen, Germany","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067081068"],"corresponding_institution_ids":["https://openalex.org/I33256026"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.5549,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72945305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"35","issue":"23","first_page":"16931","last_page":"16943"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9934999942779541,"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8093623518943787},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7401648163795471},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6311565637588501},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.5480461716651917},{"id":"https://openalex.org/keywords/inverse-kinematics","display_name":"Inverse kinematics","score":0.488887220621109},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4627283811569214},{"id":"https://openalex.org/keywords/feedback-control","display_name":"Feedback control","score":0.4485180377960205},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4431934952735901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43018263578414917},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4271208643913269},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.41431230306625366},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3883611261844635},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.23824873566627502},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13466376066207886}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8093623518943787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401648163795471},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6311565637588501},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.5480461716651917},{"id":"https://openalex.org/C17816587","wikidata":"https://www.wikidata.org/wiki/Q1501872","display_name":"Inverse kinematics","level":3,"score":0.488887220621109},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4627283811569214},{"id":"https://openalex.org/C3018651601","wikidata":"https://www.wikidata.org/wiki/Q183635","display_name":"Feedback control","level":2,"score":0.4485180377960205},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4431934952735901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43018263578414917},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4271208643913269},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.41431230306625366},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3883611261844635},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.23824873566627502},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13466376066207886},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00521-022-07949-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-022-07949-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-022-07949-0.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00521-022-07949-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-022-07949-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-022-07949-0.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4311508998.pdf","grobid_xml":"https://content.openalex.org/works/W4311508998.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W745775011","https://openalex.org/W1969685488","https://openalex.org/W2087177988","https://openalex.org/W2101539915","https://openalex.org/W2121110499","https://openalex.org/W2129659607","https://openalex.org/W2157174816","https://openalex.org/W2189149359","https://openalex.org/W2308085711","https://openalex.org/W2559960928","https://openalex.org/W2602871544","https://openalex.org/W2765300328","https://openalex.org/W2766447205","https://openalex.org/W2795786572","https://openalex.org/W2795951333","https://openalex.org/W2916746008","https://openalex.org/W3039116038","https://openalex.org/W3096621767","https://openalex.org/W3126966255","https://openalex.org/W4246078117"],"related_works":["https://openalex.org/W2789522126","https://openalex.org/W2066693961","https://openalex.org/W2084494155","https://openalex.org/W2119963650","https://openalex.org/W2972304526","https://openalex.org/W2380210784","https://openalex.org/W2770397302","https://openalex.org/W998473388","https://openalex.org/W2375415610","https://openalex.org/W4235013387"],"abstract_inverted_index":{"Abstract":[0],"Reinforcement":[1],"learning":[2,111],"(RL)":[3],"has":[4,30],"become":[5],"widely":[6],"adopted":[7],"in":[8,97,153],"robot":[9],"control.":[10],"Despite":[11],"many":[12],"successes,":[13],"one":[14],"major":[15],"persisting":[16],"problem":[17],"can":[18],"be":[19,147],"very":[20],"low":[21],"data":[22],"efficiency.":[23],"One":[24],"solution":[25],"is":[26,42,66,73,81],"interactive":[27],"feedback,":[28],"which":[29,48,70,77],"been":[31],"shown":[32],"to":[33],"speed":[34],"up":[35],"RL":[36],"considerably.":[37],"As":[38],"a":[39],"result,":[40],"there":[41,65],"an":[43],"abundance":[44],"of":[45,94,116],"different":[46,117,128],"strategies,":[47],"are,":[49],"however,":[50],"primarily":[51],"tested":[52],"on":[53],"discrete":[54],"grid-world":[55],"and":[56,90,103],"small":[57],"scale":[58],"optimal":[59,74],"control":[60],"scenarios.":[61],"In":[62],"the":[63,79,92,150,154],"literature,":[64],"no":[67,136],"consensus":[68],"about":[69],"feedback":[71,80,95,139,144],"frequency":[72,96,140,145],"or":[75],"at":[76,127],"time":[78],"most":[82],"beneficial.":[83],"To":[84],"resolve":[85],"these":[86],"discrepancies":[87],"we":[88],"isolate":[89],"quantify":[91],"effect":[93],"robotic":[98,113],"tasks":[99],"with":[100],"continuous":[101],"state":[102],"action":[104],"spaces.":[105],"The":[106],"experiments":[107],"encompass":[108],"inverse":[109],"kinematics":[110],"for":[112],"manipulator":[114],"arms":[115],"complexity.":[118],"We":[119],"show":[120],"that":[121,135,143],"seemingly":[122],"contradictory":[123],"reported":[124],"phenomena":[125],"occur":[126],"complexity":[129],"levels.":[130],"Furthermore,":[131],"our":[132],"results":[133],"suggest":[134],"single":[137],"ideal":[138],"exists.":[141],"Rather":[142],"should":[146],"changed":[148],"as":[149],"agent\u2019s":[151],"proficiency":[152],"task":[155],"increases.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}
