{"id":"https://openalex.org/W3096621767","doi":"https://doi.org/10.1145/3406499.3418769","title":"A Robust Approach for Continuous Interactive Reinforcement Learning","display_name":"A Robust Approach for Continuous Interactive Reinforcement Learning","publication_year":2020,"publication_date":"2020-11-02","ids":{"openalex":"https://openalex.org/W3096621767","doi":"https://doi.org/10.1145/3406499.3418769","mag":"3096621767"},"language":"en","primary_location":{"id":"doi:10.1145/3406499.3418769","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3406499.3418769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Human-Agent Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/A_Robust_Approach_for_Continuous_Interactive_Reinforcement_Learning/20682442","any_repository_has_fulltext":true},"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":true,"raw_author_name":"Cristian Mill\u00e1n-Arias","raw_affiliation_strings":["Universidade de Pernambuco, Recife, Pernambuco, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade de Pernambuco, Recife, Pernambuco, Brazil","institution_ids":["https://openalex.org/I71437568"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059739611","display_name":"Bruno Fernandes","orcid":"https://orcid.org/0000-0002-6001-3925"},"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":"Bruno Fernandes","raw_affiliation_strings":["Universidade de Pernambuco, Recife, Pernambuco, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade de Pernambuco, Recife, Pernambuco, Brazil","institution_ids":["https://openalex.org/I71437568"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044098673","display_name":"Francisco Cruz","orcid":"https://orcid.org/0000-0002-1131-3382"},"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"]},{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU","CL"],"is_corresponding":false,"raw_author_name":"Francisco Cruz","raw_affiliation_strings":["Deakin University &amp; Universidad Central de Chile, Geelong, Australia"],"affiliations":[{"raw_affiliation_string":"Deakin University &amp; Universidad Central de Chile, Geelong, Australia","institution_ids":["https://openalex.org/I149704539","https://openalex.org/I4210156023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032749222","display_name":"Richard Dazeley","orcid":"https://orcid.org/0000-0002-6199-9685"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Richard Dazeley","raw_affiliation_strings":["Deakin University, Greelong, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Deakin University, Greelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102941027","display_name":"S\u00e9rgio Fernandes","orcid":"https://orcid.org/0000-0002-5922-4119"},"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":"Sergio Fernandes","raw_affiliation_strings":["Universidade de Pernambuco, Recife, Pernambuco, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade de Pernambuco, Recife, Pernambuco, Brazil","institution_ids":["https://openalex.org/I71437568"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047544916"],"corresponding_institution_ids":["https://openalex.org/I71437568"],"apc_list":null,"apc_paid":null,"fwci":1.0824,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83136144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"278","last_page":"280"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9980000257492065,"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":0.9595999717712402,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9083564281463623},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7622260451316833},{"id":"https://openalex.org/keywords/trainer","display_name":"Trainer","score":0.7094372510910034},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6956381797790527},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5095301270484924},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4989662170410156},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.44249227643013},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.43945205211639404},{"id":"https://openalex.org/keywords/interactive-learning","display_name":"Interactive Learning","score":0.43445098400115967},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4334101974964142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43046343326568604},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.14039042592048645},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1040445864200592}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9083564281463623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7622260451316833},{"id":"https://openalex.org/C2780463512","wikidata":"https://www.wikidata.org/wiki/Q15122700","display_name":"Trainer","level":2,"score":0.7094372510910034},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6956381797790527},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5095301270484924},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4989662170410156},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44249227643013},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.43945205211639404},{"id":"https://openalex.org/C2776716048","wikidata":"https://www.wikidata.org/wiki/Q6045290","display_name":"Interactive Learning","level":2,"score":0.43445098400115967},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4334101974964142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43046343326568604},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.14039042592048645},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1040445864200592},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3406499.3418769","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3406499.3418769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Human-Agent Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:dro.deakin.edu.au:DU:30146056","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401102","display_name":"Own your potential (DEAKIN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149704539","host_organization_name":"Deakin University","host_organization_lineage":["https://openalex.org/I149704539"],"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"},{"id":"pmh:oai:figshare.com:article/20682442","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/A_Robust_Approach_for_Continuous_Interactive_Reinforcement_Learning/20682442","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/20682442","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/A_Robust_Approach_for_Continuous_Interactive_Reinforcement_Learning/20682442","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W2091565802","https://openalex.org/W2098441518","https://openalex.org/W2105078254","https://openalex.org/W2129659607","https://openalex.org/W2153120627","https://openalex.org/W2156869222","https://openalex.org/W2312609093","https://openalex.org/W2559960928","https://openalex.org/W2795786572","https://openalex.org/W2883750587","https://openalex.org/W2901974609","https://openalex.org/W2957624498"],"related_works":["https://openalex.org/W1985059659","https://openalex.org/W2090273011","https://openalex.org/W4200580761","https://openalex.org/W2289004814","https://openalex.org/W2088374858","https://openalex.org/W2786916331","https://openalex.org/W3128800637","https://openalex.org/W3041314865","https://openalex.org/W1765911225","https://openalex.org/W3096621767"],"abstract_inverted_index":{"Interactive":[0],"reinforcement":[1,43,73],"learning":[2,44,74],"is":[3,20,45],"an":[4,8,12,51,68,93],"approach":[5,48,69,91],"in":[6,22,60,76,102],"which":[7],"external":[9],"trainer":[10,19],"helps":[11],"agent":[13,52,94],"to":[14,53,95],"learn":[15,54],"through":[16],"advice.":[17],"A":[18],"useful":[21],"large":[23],"or":[24],"continuous":[25,81,105],"scenarios;":[26],"however,":[27],"when":[28],"the":[29,32,40,61,89,97],"characteristics":[30],"of":[31,58],"environment":[33,79],"change":[34],"over":[35],"time,":[36],"it":[37],"can":[38],"affect":[39],"learning.":[41],"Robust":[42],"a":[46,55,77,103],"reliable":[47],"that":[49,70,88],"allows":[50,92],"task,":[56],"regardless":[57],"disturbances":[59],"environment.":[62],"In":[63],"this":[64],"work,":[65],"we":[66],"present":[67],"addresses":[71],"interactive":[72],"problems":[75],"dynamic":[78],"with":[80],"states":[82],"and":[83],"actions.":[84],"Our":[85],"results":[86],"show":[87],"proposed":[90],"complete":[96],"cart-pole":[98],"balancing":[99],"task":[100],"satisfactorily":[101],"dynamic,":[104],"action-state":[106],"domain.":[107]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
