{"id":"https://openalex.org/W2890367452","doi":"https://doi.org/10.1515/pjbr-2018-0016","title":"Adaptive reinforcement learning with active state-specific exploration for engagement maximization during simulated child-robot interaction","display_name":"Adaptive reinforcement learning with active state-specific exploration for engagement maximization during simulated child-robot interaction","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2890367452","doi":"https://doi.org/10.1515/pjbr-2018-0016","mag":"2890367452"},"language":"en","primary_location":{"id":"doi:10.1515/pjbr-2018-0016","is_oa":true,"landing_page_url":"https://doi.org/10.1515/pjbr-2018-0016","pdf_url":"https://www.degruyter.com/document/doi/10.1515/pjbr-2018-0016/pdf","source":{"id":"https://openalex.org/S4210226531","display_name":"Paladyn Journal of Behavioral Robotics","issn_l":"2080-9778","issn":["2080-9778","2081-4836"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Paladyn, Journal of Behavioral Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.degruyter.com/document/doi/10.1515/pjbr-2018-0016/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077199166","display_name":"George Velentzas","orcid":"https://orcid.org/0000-0003-3358-7488"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"George Velentzas","raw_affiliation_strings":["School of Electrical and Computer Engineering, National Technical University of Athens, Athens , Greece","School of E.C.E - School of of Electrical and Computer Engineering [Athens] (National Technical University of Athens, School of Electrical and Computer Engineers, 9, Iroon Polytechniou str., Athens, Post Code 157 80 - Greece)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National Technical University of Athens, Athens , Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"School of E.C.E - School of of Electrical and Computer Engineering [Athens] (National Technical University of Athens, School of Electrical and Computer Engineers, 9, Iroon Polytechniou str., Athens, Post Code 157 80 - Greece)","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035447694","display_name":"Theodore Tsitsimis","orcid":null},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Theodore Tsitsimis","raw_affiliation_strings":["School of Electrical and Computer Engineering, National Technical University of Athens, Athens , Greece","School of E.C.E - School of of Electrical and Computer Engineering [Athens] (National Technical University of Athens, School of Electrical and Computer Engineers, 9, Iroon Polytechniou str., Athens, Post Code 157 80 - Greece)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National Technical University of Athens, Athens , Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"School of E.C.E - School of of Electrical and Computer Engineering [Athens] (National Technical University of Athens, School of Electrical and Computer Engineers, 9, Iroon Polytechniou str., Athens, Post Code 157 80 - Greece)","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074968710","display_name":"I\u00f1aki Ra\u00f1\u00f3","orcid":"https://orcid.org/0000-0002-0461-0258"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"I\u00f1aki Ra\u00f1\u00f3","raw_affiliation_strings":["Intelligent Systems Research Centre, Ulster University, Coleraine , UK","Faculty of Computing and Engineering [University of Ulster] (St James' House\r\n10 Rosebery Avenue\r\nHolborn\r\nLondon\r\nEC1R 4TF - United Kingdom)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems Research Centre, Ulster University, Coleraine , UK","institution_ids":["https://openalex.org/I138801177"]},{"raw_affiliation_string":"Faculty of Computing and Engineering [University of Ulster] (St James' House\r\n10 Rosebery Avenue\r\nHolborn\r\nLondon\r\nEC1R 4TF - United Kingdom)","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075518884","display_name":"Costas S. Tzafestas","orcid":"https://orcid.org/0000-0003-1545-9191"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Costas Tzafestas","raw_affiliation_strings":["School of Electrical and Computer Engineering, National Technical University of Athens, Athens , Greece","School of E.C.E - School of of Electrical and Computer Engineering [Athens] (National Technical University of Athens, School of Electrical and Computer Engineers, 9, Iroon Polytechniou str., Athens, Post Code 157 80 - Greece)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National Technical University of Athens, Athens , Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"School of E.C.E - School of of Electrical and Computer Engineering [Athens] (National Technical University of Athens, School of Electrical and Computer Engineers, 9, Iroon Polytechniou str., Athens, Post Code 157 80 - Greece)","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016381589","display_name":"Mehdi Khamassi","orcid":"https://orcid.org/0000-0002-2515-1046"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Mehdi Khamassi","raw_affiliation_strings":["Sorbonne Universit\u00e9,CNRS, Institute of Intelligent Systems and Robotics, Paris , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9,CNRS, Institute of Intelligent Systems and Robotics, Paris , France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210150358"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016381589"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210150358"],"apc_list":{"value":1000,"currency":"EUR","value_usd":1078},"apc_paid":{"value":1000,"currency":"EUR","value_usd":1078},"fwci":0.7389,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79860421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"9","issue":"1","first_page":"235","last_page":"253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9990000128746033,"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":0.7363768815994263},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7150619029998779},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6041122674942017},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5911616086959839},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5896194577217102},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5722020268440247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48832008242607117},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4201262593269348},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3886812627315521},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23701879382133484},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13566124439239502},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1103728711605072},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1062641441822052}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7363768815994263},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7150619029998779},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6041122674942017},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5911616086959839},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5896194577217102},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5722020268440247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48832008242607117},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4201262593269348},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3886812627315521},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23701879382133484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13566124439239502},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1103728711605072},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1062641441822052},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1515/pjbr-2018-0016","is_oa":true,"landing_page_url":"https://doi.org/10.1515/pjbr-2018-0016","pdf_url":"https://www.degruyter.com/document/doi/10.1515/pjbr-2018-0016/pdf","source":{"id":"https://openalex.org/S4210226531","display_name":"Paladyn Journal of Behavioral Robotics","issn_l":"2080-9778","issn":["2080-9778","2081-4836"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Paladyn, Journal of Behavioral Robotics","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-02324073v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02324073","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Paladyn: Journal of Behavioral Robotics, 2018, 9 (1), pp.235-253. ⟨10.1515/pjbr-2018-0016⟩","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:4bbd84ee70fe43179fdf670b2b0ab96b","is_oa":true,"landing_page_url":"https://doaj.org/article/4bbd84ee70fe43179fdf670b2b0ab96b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Paladyn, Vol 9, Iss 1, Pp 235-253 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1515/pjbr-2018-0016","is_oa":true,"landing_page_url":"https://doi.org/10.1515/pjbr-2018-0016","pdf_url":"https://www.degruyter.com/document/doi/10.1515/pjbr-2018-0016/pdf","source":{"id":"https://openalex.org/S4210226531","display_name":"Paladyn Journal of Behavioral Robotics","issn_l":"2080-9778","issn":["2080-9778","2081-4836"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320322","host_organization_name":"De Gruyter Open","host_organization_lineage":["https://openalex.org/P4310320322","https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter Open","De Gruyter"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Paladyn, Journal of Behavioral Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1156222357","display_name":null,"funder_award_id":"H2020-ICT-24-2015","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G1182127530","display_name":null,"funder_award_id":"687831","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G1189697078","display_name":null,"funder_award_id":"ANR\u201311\u2013LABX\u201365","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G2647246237","display_name":null,"funder_award_id":"ANR-11IDEX-0004-02","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G4344075577","display_name":null,"funder_award_id":"ANR-11-IDEX-0004-02","funder_id":"https://openalex.org/F4320322892","funder_display_name":"Centre National de la Recherche Scientifique"},{"id":"https://openalex.org/G4600281106","display_name":"Self Aware Robots","funder_award_id":"ANR-12-CORD-0030","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G4866930200","display_name":null,"funder_award_id":"ANR-11-IDEX","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5615659713","display_name":null,"funder_award_id":"IDEX-0004-02","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G6654833908","display_name":"Sorbonne Universit\u00e9s \u00e0 Paris pour l'Enseignement et la Recherche","funder_award_id":"ANR-11-IDEX-0004","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G6702880738","display_name":null,"funder_award_id":"ANR-12","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G7235831075","display_name":null,"funder_award_id":"ANR-11-LABX-65","funder_id":"https://openalex.org/F4320322892","funder_display_name":"Centre National de la Recherche Scientifique"}],"funders":[{"id":"https://openalex.org/F4320320006","display_name":"Royal Society","ror":"https://ror.org/03wnrjx87"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2890367452.pdf","grobid_xml":"https://content.openalex.org/works/W2890367452.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1836026262","https://openalex.org/W1977655452","https://openalex.org/W1996579288","https://openalex.org/W2004303440","https://openalex.org/W2012392077","https://openalex.org/W2061868368","https://openalex.org/W2070329666","https://openalex.org/W2085627234","https://openalex.org/W2087384102","https://openalex.org/W2094856020","https://openalex.org/W2096284813","https://openalex.org/W2099019320","https://openalex.org/W2101539915","https://openalex.org/W2124848740","https://openalex.org/W2139219009","https://openalex.org/W2153463593","https://openalex.org/W2159554014","https://openalex.org/W2161563886","https://openalex.org/W2256420211","https://openalex.org/W2330879847","https://openalex.org/W2482333547","https://openalex.org/W2587122513","https://openalex.org/W2612581922","https://openalex.org/W2789759008","https://openalex.org/W2793748321","https://openalex.org/W2824479732","https://openalex.org/W3036876381","https://openalex.org/W3143996792","https://openalex.org/W4240195433"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3213722473","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Abstract":[0],"Using":[1],"assistive":[2],"robots":[3,8],"for":[4,17,159],"educational":[5],"applications":[6],"requires":[7],"to":[9,12,75,114,125,136,164,187,219],"be":[10],"able":[11],"adapt":[13],"their":[14],"behavior":[15,56,203],"specifically":[16],"each":[18],"child":[19,76],"with":[20,37,67,189,238],"whom":[21],"they":[22],"interact.Among":[23],"relevant":[24],"signals,":[25],"non-verbal":[26,225],"cues":[27,226],"such":[28,85,142],"as":[29,79,81,86,100,143],"the":[30,35,41,46,50,104,112,119,134,150,154,160,169,173,184,196,209,228],"child\u2019s":[31,42],"gaze":[32],"can":[33,234],"provide":[34],"robot":[36,51,151,170,221],"important":[38],"information":[39],"about":[40],"current":[43,55],"engagement":[44,77],"in":[45,195,204],"task,":[47],"and":[48,71,163,192,227],"whether":[49],"should":[52,152,171],"continue":[53],"its":[54,73,92],"or":[57],"not.":[58],"Here":[59],"we":[60],"propose":[61],"a":[62,96,122,137,165,201,216],"reinforcement":[63],"learning":[64,222],"algorithm":[65,135,185],"extended":[66,145],"active":[68],"state-specific":[69],"exploration":[70],"show":[72,182],"applicability":[74],"maximization":[78],"well":[80],"more":[82],"classical":[83],"tasks":[84],"maze":[87,98],"navigation.":[88],"We":[89,181],"first":[90],"demonstrate":[91],"adaptive":[93],"nature":[94],"on":[95,224],"continuous":[97],"problem":[99],"an":[101,144],"enhancement":[102],"of":[103,121,139,147,157,177,179,208,231],"classic":[105],"grid":[106],"world.":[107],"There,":[108],"parameterized":[109],"actions":[110],"enable":[111,220],"agent":[113],"learn":[115],"single":[116],"moves":[117],"until":[118],"end":[120],"corridor,":[123],"similarly":[124],"\u201coptions\u201d":[126],"but":[127],"without":[128],"explicit":[129],"hierarchical":[130],"representations.We":[131],"then":[132],"apply":[133],"series":[138],"simulated":[140],"scenarios,":[141],"Tower":[146],"Hanoi":[148],"where":[149,168],"find":[153,172],"appropriate":[155,175],"speed":[156],"movement":[158],"interacting":[161],"child,":[162],"pointing":[166],"task":[167],"child-specific":[174],"level":[176],"expressivity":[178],"action.":[180],"that":[183,233],"enables":[186],"cope":[188],"both":[190],"global":[191],"local":[193],"non-stationarities":[194,232],"state":[197,210],"space":[198],"while":[199],"preserving":[200],"stable":[202],"other":[205],"stationary":[206],"portions":[207],"space.":[211],"Altogether,":[212],"these":[213],"results":[214],"suggest":[215],"promising":[217],"way":[218],"based":[223],"high":[229],"degree":[230],"occur":[235],"during":[236],"interaction":[237],"children.":[239]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}