{"id":"https://openalex.org/W7135099399","doi":"https://doi.org/10.1109/clei67442.2025.11420674","title":"Help me to Clean: Studying Multi-trainers on Interactive Reinforcement Learning in Domestic Scenarios","display_name":"Help me to Clean: Studying Multi-trainers on Interactive Reinforcement Learning in Domestic Scenarios","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W7135099399","doi":"https://doi.org/10.1109/clei67442.2025.11420674"},"language":null,"primary_location":{"id":"doi:10.1109/clei67442.2025.11420674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clei67442.2025.11420674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 LI Latin American Computer Conference (CLEI)","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/A5047544916","display_name":"Cristian Mill\u00e1n-Arias","orcid":"https://orcid.org/0000-0002-5286-3751"},"institutions":[{"id":"https://openalex.org/I71437568","display_name":"Universidade de Pernambuco","ror":"https://ror.org/00gtcbp88","country_code":"BR","type":"education","lineage":["https://openalex.org/I71437568"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Cristian Mill\u00e1n-Arias","raw_affiliation_strings":["Universidade de Pernambuco,Escola Politécnica de Pernambuco,Recife,PE,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade de Pernambuco,Escola Politécnica de Pernambuco,Recife,PE,Brazil","institution_ids":["https://openalex.org/I71437568"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128810655","display_name":"Ernesto Gutierrez","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156023","display_name":"Universidad Central de Chile","ror":"https://ror.org/0577avk88","country_code":"CL","type":"education","lineage":["https://openalex.org/I4210156023"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Ernesto Gutierrez","raw_affiliation_strings":["Universidad Central de Chile,Escuela de Ingeniería,Santiago,Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Central de Chile,Escuela de Ingeniería,Santiago,Chile","institution_ids":["https://openalex.org/I4210156023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128822991","display_name":"Francisco Cruz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156023","display_name":"Universidad Central de Chile","ror":"https://ror.org/0577avk88","country_code":"CL","type":"education","lineage":["https://openalex.org/I4210156023"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Francisco Cruz","raw_affiliation_strings":["Universidad Central de Chile,Escuela de Ingeniería,Santiago,Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Central de Chile,Escuela de Ingeniería,Santiago,Chile","institution_ids":["https://openalex.org/I4210156023"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82856982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6668000221252441,"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":0.6668000221252441,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1290999948978424,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.04729999974370003,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8235999941825867},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6323000192642212},{"id":"https://openalex.org/keywords/trainer","display_name":"Trainer","score":0.52920001745224},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4474000036716461},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.44690001010894775},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4404999911785126},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3646000027656555}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8235999941825867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7114999890327454},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6323000192642212},{"id":"https://openalex.org/C2780463512","wikidata":"https://www.wikidata.org/wiki/Q15122700","display_name":"Trainer","level":2,"score":0.52920001745224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5011000037193298},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44679999351501465},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4404999911785126},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4092000126838684},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3646000027656555},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.326200008392334},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.30309998989105225},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2897999882698059},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.28929999470710754},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/clei67442.2025.11420674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clei67442.2025.11420674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 LI Latin American Computer Conference (CLEI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4095160663127899,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1531725372","https://openalex.org/W1655830068","https://openalex.org/W2107726111","https://openalex.org/W2792217087","https://openalex.org/W3087055389","https://openalex.org/W3143003892","https://openalex.org/W3186035148","https://openalex.org/W4308934227","https://openalex.org/W4313546693"],"related_works":[],"abstract_inverted_index":{"In":[0,102],"the":[1,19,50,53,68,97,134,144,149,229],"last":[2],"decade,":[3],"robots":[4],"have":[5,92],"increasingly":[6],"participated":[7],"in":[8,14,112],"human-centered":[9],"environments,":[10,23],"particularly":[11],"performing":[12],"tasks":[13],"domestic":[15,115,190],"settings.":[16],"Due":[17],"to":[18,32,48,95,146,203,212],"complexity":[20],"of":[21,99,110,138,151],"these":[22],"reinforcement":[24,39],"learning":[25,40,69],"(RL)":[26],"has":[27],"become":[28],"a":[29,107,113,118,122,160,178,185],"key":[30],"approach":[31,158],"train":[33],"agents":[34],"autonomously.":[35],"A":[36],"variation,":[37],"interactive":[38],"(IRL),":[41],"incorporates":[42],"feedback":[43,168,196,225],"from":[44,126],"an":[45],"external":[46],"trainer":[47],"guide":[49],"agent":[51,145],"toward":[52],"optimal":[54],"policy.":[55],"However,":[56],"trainers":[57,220],"are":[58],"often":[59],"non-experts":[60],"and":[61,82,136,201,215,221],"may":[62],"provide":[63],"incorrect":[64,224],"feedback,":[65],"potentially":[66],"hindering":[67],"process.":[70],"To":[71,172],"address":[72],"this,":[73],"recent":[74],"approaches":[75],"like":[76],"Multi-Trainer":[77,163],"Interactive":[78],"Reinforcement":[79],"Learning":[80],"(MTIRL)":[81],"ensemble":[83],"strategies":[84],"such":[85],"as":[86],"Bayesian":[87],"Weighted":[88],"Voting":[89],"Ensemble":[90],"(BWVE)":[91],"been":[93],"proposed":[94],"mitigate":[96],"impact":[98],"erroneous":[100],"guidance.":[101],"this":[103,141,157],"work,":[104],"we":[105,176],"present":[106],"novel":[108],"application":[109],"MTIRL":[111],"simulated":[114],"environment,":[116,181],"where":[117,166],"robot":[119],"must":[120],"learn":[121],"household":[123],"navigation":[124,191],"task":[125],"multiple":[127],"non-expert":[128],"trainers.":[129],"Our":[130],"main":[131],"contribution":[132],"is":[133,169],"implementation":[135],"evaluation":[137],"BWVE":[139,210],"within":[140],"context,":[142],"allowing":[143],"dynamically":[147],"assess":[148],"reliability":[150],"each":[152],"trainer\u2019s":[153],"feedback.":[154],"We":[155],"compare":[156],"with":[159,184],"Full":[161],"Feedback":[162],"(FFMT)":[164],"baseline,":[165],"all":[167],"processed":[170],"equally.":[171],"support":[173],"our":[174],"experiments,":[175],"developed":[177],"custom":[179],"simulation":[180],"Domestic":[182],"Scenario":[183],"Cognitive":[186],"Agent,":[187],"tailored":[188],"for":[189],"task.":[192],"Evaluation":[193],"metrics":[194],"include":[195],"frequency,":[197],"steps":[198],"per":[199],"episode,":[200],"time":[202],"complete":[204],"100":[205],"episodes.":[206],"Results":[207],"demonstrate":[208],"that":[209],"leads":[211],"more":[213,226],"efficient":[214],"robust":[216],"learning,":[217],"requiring":[218],"fewer":[219],"tolerating":[222],"occasional":[223],"effectively":[227],"than":[228],"baseline.":[230]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-13T00:00:00"}