{"id":"https://openalex.org/W2401683402","doi":"https://doi.org/10.1007/978-3-319-29339-4_2","title":"Interactive Learning of Continuous Actions from Corrective Advice Communicated by Humans","display_name":"Interactive Learning of Continuous Actions from Corrective Advice Communicated by Humans","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2401683402","doi":"https://doi.org/10.1007/978-3-319-29339-4_2","mag":"2401683402"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-29339-4_2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-29339-4_2","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-319-29339-4_2.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-319-29339-4_2.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028010633","display_name":"Carlos Celemin","orcid":"https://orcid.org/0000-0001-8880-0966"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":true,"raw_author_name":"Carlos Celemin","raw_affiliation_strings":["Department of Electrical Engineering and Advanced Mining Technology Center, Universidad de Chile, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Advanced Mining Technology Center, Universidad de Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048448415","display_name":"Javier Ruiz\u2010del\u2010Solar","orcid":"https://orcid.org/0000-0003-2965-633X"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Javier Ruiz-del-Solar","raw_affiliation_strings":["Department of Electrical Engineering and Advanced Mining Technology Center, Universidad de Chile, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Advanced Mining Technology Center, Universidad de Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028010633"],"corresponding_institution_ids":["https://openalex.org/I69737025"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":2.0457,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88027905,"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":"16","last_page":"27"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8162798285484314},{"id":"https://openalex.org/keywords/corrective-feedback","display_name":"Corrective feedback","score":0.7739177942276001},{"id":"https://openalex.org/keywords/advice","display_name":"Advice (programming)","score":0.7598693370819092},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7481521368026733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5475268959999084},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5214576125144958},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.49365362524986267},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4876793622970581},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.47176721692085266},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.10103890299797058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8162798285484314},{"id":"https://openalex.org/C2779305910","wikidata":"https://www.wikidata.org/wiki/Q5172809","display_name":"Corrective feedback","level":2,"score":0.7739177942276001},{"id":"https://openalex.org/C2779955035","wikidata":"https://www.wikidata.org/wiki/Q4686785","display_name":"Advice (programming)","level":2,"score":0.7598693370819092},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7481521368026733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5475268959999084},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5214576125144958},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49365362524986267},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4876793622970581},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.47176721692085266},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.10103890299797058},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-319-29339-4_2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-29339-4_2","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-319-29339-4_2.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-319-29339-4_2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-29339-4_2","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-319-29339-4_2.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323458","display_name":"Universidad de Chile","ror":"https://ror.org/047gc3g35"},{"id":"https://openalex.org/F4320334812","display_name":"Comisi\u00f3n Nacional de Investigaci\u00f3n Cient\u00edfica y Tecnol\u00f3gica","ror":"https://ror.org/02ap3w078"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2401683402.pdf","grobid_xml":"https://content.openalex.org/works/W2401683402.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1536323281","https://openalex.org/W1626155273","https://openalex.org/W1966259872","https://openalex.org/W1979308911","https://openalex.org/W1986014385","https://openalex.org/W1999874108","https://openalex.org/W2062821321","https://openalex.org/W2098584016","https://openalex.org/W2104308387","https://openalex.org/W2108503630","https://openalex.org/W2110064869","https://openalex.org/W2120982521","https://openalex.org/W2121863487","https://openalex.org/W2126861176","https://openalex.org/W2128103053","https://openalex.org/W2129659607","https://openalex.org/W2150818585","https://openalex.org/W2156869222","https://openalex.org/W2162932021","https://openalex.org/W2406235655","https://openalex.org/W4214717370"],"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/W1984742304"],"abstract_inverted_index":{"An":[0],"interactive":[1],"learning":[2,96,107],"framework":[3],"that":[4,55,117],"allows":[5],"non-expert":[6],"humans":[7],"to":[8,121,126,135],"shape":[9],"a":[10,16,45,56,132],"policy":[11],"through":[12],"corrective":[13],"advice,":[14],"using":[15,91],"binary":[17],"signal":[18],"in":[19,93,109,142],"the":[20,24,30,41,50,72,105,110],"action":[21,58,144],"domain":[22],"of":[23,29,34,52,67,74],"robot/agent,":[25],"is":[26,44,69,119,138],"proposed.":[27],"One":[28],"most":[31],"innovative":[32],"features":[33],"COACH":[35,68,103,118],"(COrrective":[36],"Advice":[37],"Communicated":[38],"by":[39],"Humans),":[40],"proposed":[42],"framework,":[43],"mechanism":[46],"for":[47,140],"adaptively":[48],"adjusting":[49],"amount":[51],"human":[53,124],"feedback":[54],"given":[57],"receives,":[59],"taking":[60],"into":[61],"consideration":[62],"past":[63],"feedback.":[64],"The":[65],"performance":[66],"compared":[70],"with":[71,128],"one":[73],"TAMER":[75],"(Teaching":[76],"an":[77,87],"Agent":[78],"Manually":[79],"via":[80],"Evaluative":[81],"Reinforcement),":[82],"ACTAMER":[83],"(Actor-Critic":[84],"TAMER),":[85],"and":[86,100],"autonomous":[88],"agent":[89],"trained":[90],"SARSA(\u03bb)":[92],"two":[94],"reinforcement":[95],"problems:":[97],"ball":[98],"dribbling":[99],"Cart-Pole":[101],"balancing.":[102],"outperforms":[104],"other":[106],"frameworks":[108],"reported":[111],"experiments.":[112],"In":[113],"addition,":[114],"results":[115],"show":[116],"able":[120],"transfer":[122],"successfully":[123],"knowledge":[125],"agents":[127],"continuous":[129],"actions,":[130],"being":[131],"complementary":[133],"approach":[134],"TAMER,":[136],"which":[137],"appropriate":[139],"teaching":[141],"discrete":[143],"domains.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-24T08:23:43.765630","created_date":"2025-10-10T00:00:00"}
