{"id":"https://openalex.org/W2602717673","doi":"https://doi.org/10.1109/la-cci.2016.7885734","title":"Teaching agents with corrective human feedback for challenging problems","display_name":"Teaching agents with corrective human feedback for challenging problems","publication_year":2016,"publication_date":"2016-11-01","ids":{"openalex":"https://openalex.org/W2602717673","doi":"https://doi.org/10.1109/la-cci.2016.7885734","mag":"2602717673"},"language":"en","primary_location":{"id":"doi:10.1109/la-cci.2016.7885734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/la-cci.2016.7885734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Latin American Conference on Computational Intelligence (LA-CCI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"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":[],"countries":[],"is_corresponding":true,"raw_author_name":"Carlos Celemin","raw_affiliation_strings":["Dept. Elect. Eng., Advanced Mining Technology Center, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"Dept. Elect. Eng., Advanced Mining Technology Center, Santiago, Chile","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048448415","display_name":"Javier Ruiz\u2010del\u2010Solar","orcid":"https://orcid.org/0000-0003-2965-633X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Ruiz-del-Solar","raw_affiliation_strings":["Dept. Elect. Eng., Advanced Mining Technology Center, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"Dept. Elect. Eng., Advanced Mining Technology Center, Santiago, Chile","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028010633"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.12392147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9908999800682068,"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"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9886000156402588,"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/computer-science","display_name":"Computer science","score":0.6852793097496033},{"id":"https://openalex.org/keywords/corrective-feedback","display_name":"Corrective feedback","score":0.6585330963134766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5635440349578857},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5592613816261292},{"id":"https://openalex.org/keywords/advice","display_name":"Advice (programming)","score":0.5438476204872131},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5362192392349243},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4783153831958771},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4391572177410126},{"id":"https://openalex.org/keywords/action-learning","display_name":"Action learning","score":0.4362945854663849},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.43550384044647217},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43384021520614624},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4010365903377533},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13861599564552307},{"id":"https://openalex.org/keywords/cooperative-learning","display_name":"Cooperative learning","score":0.13210800290107727},{"id":"https://openalex.org/keywords/teaching-method","display_name":"Teaching method","score":0.10903531312942505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6852793097496033},{"id":"https://openalex.org/C2779305910","wikidata":"https://www.wikidata.org/wiki/Q5172809","display_name":"Corrective feedback","level":2,"score":0.6585330963134766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5635440349578857},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5592613816261292},{"id":"https://openalex.org/C2779955035","wikidata":"https://www.wikidata.org/wiki/Q4686785","display_name":"Advice (programming)","level":2,"score":0.5438476204872131},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5362192392349243},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4783153831958771},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4391572177410126},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.4362945854663849},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.43550384044647217},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43384021520614624},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4010365903377533},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13861599564552307},{"id":"https://openalex.org/C51672120","wikidata":"https://www.wikidata.org/wiki/Q303446","display_name":"Cooperative learning","level":3,"score":0.13210800290107727},{"id":"https://openalex.org/C88610354","wikidata":"https://www.wikidata.org/wiki/Q1813494","display_name":"Teaching method","level":2,"score":0.10903531312942505},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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:10.1109/la-cci.2016.7885734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/la-cci.2016.7885734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Latin American Conference on Computational Intelligence (LA-CCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1499408472","https://openalex.org/W1520340982","https://openalex.org/W1626155273","https://openalex.org/W1977655452","https://openalex.org/W1979308911","https://openalex.org/W2079325629","https://openalex.org/W2150818585","https://openalex.org/W2156869222","https://openalex.org/W2401683402","https://openalex.org/W2406235655","https://openalex.org/W4214717370","https://openalex.org/W6636829564","https://openalex.org/W6713621959"],"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":{"COACH":[0,35,58,117,133],"(COrrective":[1],"Advice":[2],"Communicated":[3],"by":[4],"Humans)":[5],"is":[6,60,118,134],"an":[7],"interactive":[8],"learning":[9,66,79,125],"framework":[10,59],"that":[11,132],"allows":[12],"non-expert":[13],"humans":[14],"to":[15,80,136,141],"shape":[16],"a":[17,23,82,101,105],"policy":[18,52,108],"through":[19],"corrective":[20],"advice,":[21],"using":[22,104],"binary":[24],"signal":[25],"in":[26,40,73],"the":[27,31,51,57,74,91,94,114,121,150],"action":[28,75,146],"domain":[29,76],"of":[30,42,68,116,123,152,155],"agent.":[32],"The":[33],"original":[34],"formulation":[36],"has":[37],"been":[38],"tested":[39,61],"problems":[41,67,113],"one-dimensional":[43],"actions":[44],"spaces":[45],"with":[46,62,86,120,143],"RBF":[47],"linear":[48],"models":[49],"for":[50,90,99],"approximation.":[53,109],"In":[54,110],"this":[55],"paper":[56],"two":[63,112],"more":[64,69],"complex":[65],"than":[70],"one":[71,122],"dimension":[72],"such":[77],"as":[78],"drive":[81],"bicycle,":[83],"and":[84],"ball-dribbling":[85],"humanoid":[87],"robots.":[88],"Moreover,":[89],"second":[92],"problem,":[93],"COACH's":[95],"principles":[96],"are":[97],"extended":[98],"training":[100],"decision-making":[102],"system":[103],"fuzzy":[106],"based":[107,148],"these":[111],"performance":[115],"compared":[119],"other":[124],"methods,":[126],"obtaining":[127],"better":[128],"results.":[129],"Results":[130],"show":[131],"able":[135],"transfer":[137],"successfully":[138],"human":[139],"knowledge":[140],"agents":[142],"multi-dimensional":[144],"continuous":[145],"domains":[147],"on":[149],"use":[151],"different":[153],"kind":[154],"models.":[156]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}