{"id":"https://openalex.org/W20840515","doi":"https://doi.org/10.1007/978-3-642-39802-5_17","title":"Learning Epistemic Actions in Model-Free Memory-Free Reinforcement Learning: Experiments with a Neuro-robotic Model","display_name":"Learning Epistemic Actions in Model-Free Memory-Free Reinforcement Learning: Experiments with a Neuro-robotic Model","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W20840515","doi":"https://doi.org/10.1007/978-3-642-39802-5_17","mag":"20840515"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-39802-5_17","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-39802-5_17","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10281/301913","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068529617","display_name":"Dimitri Ognibene","orcid":"https://orcid.org/0000-0002-9454-680X"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dimitri Ognibene","raw_affiliation_strings":["Personal Robotics Laboratory, Imperial College London, UK","Personal Robotics Laboratory, Imperial College London, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Personal Robotics Laboratory, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Personal Robotics Laboratory, Imperial College London, UK#TAB#","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011154546","display_name":"Nicola Catenacci Volpi","orcid":"https://orcid.org/0000-0002-0114-3041"},"institutions":[{"id":"https://openalex.org/I127077003","display_name":"IMT School for Advanced Studies Lucca","ror":"https://ror.org/035gh3a49","country_code":"IT","type":"education","lineage":["https://openalex.org/I127077003"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Catenacci Volpi","raw_affiliation_strings":["IMT Institute for Advanced Studies, Lucca, Italy","IMT \u2014 Institute for Advanced Studies Lucca, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMT Institute for Advanced Studies, Lucca, Italy","institution_ids":["https://openalex.org/I127077003"]},{"raw_affiliation_string":"IMT \u2014 Institute for Advanced Studies Lucca, Italy","institution_ids":["https://openalex.org/I127077003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053290697","display_name":"Giovanni Pezzulo","orcid":"https://orcid.org/0000-0001-6813-8282"},"institutions":[{"id":"https://openalex.org/I4210124522","display_name":"Institute for Computational Linguistics \u201cA. Zampolli\u201d","ror":"https://ror.org/028g3pe33","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210124522","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210166865","display_name":"Institute of Cognitive Sciences and Technologies","ror":"https://ror.org/05w9g2j85","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210155236","https://openalex.org/I4210166865"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Pezzulo","raw_affiliation_strings":["Istituto di Linguistica Computazionale \u201cAntonio Zampolli\u201d, CNR, Italy","Istituto di Scienze e Tecnologie della Cognizione, CNR, Italy","Istituto di Scienze e Tecnologie della Cognizione, CNR, Italy and Istituto di Linguistica Computazionale Antonio Zampolli, CNR, Italy#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto di Linguistica Computazionale \u201cAntonio Zampolli\u201d, CNR, Italy","institution_ids":["https://openalex.org/I4210124522"]},{"raw_affiliation_string":"Istituto di Scienze e Tecnologie della Cognizione, CNR, Italy","institution_ids":["https://openalex.org/I4210166865"]},{"raw_affiliation_string":"Istituto di Scienze e Tecnologie della Cognizione, CNR, Italy and Istituto di Linguistica Computazionale Antonio Zampolli, CNR, Italy#TAB#","institution_ids":["https://openalex.org/I4210166865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113643103","display_name":"Gianluca Baldassare","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166865","display_name":"Institute of Cognitive Sciences and Technologies","ror":"https://ror.org/05w9g2j85","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210155236","https://openalex.org/I4210166865"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gianluca Baldassare","raw_affiliation_strings":["Istituto di Scienze e Tecnologie della Cognizione, CNR, Italy","Istituto di Scienze e Tecnologie della Cognizione, CNR, Italy#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto di Scienze e Tecnologie della Cognizione, CNR, Italy","institution_ids":["https://openalex.org/I4210166865"]},{"raw_affiliation_string":"Istituto di Scienze e Tecnologie della Cognizione, CNR, Italy#TAB#","institution_ids":["https://openalex.org/I4210166865"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"191","last_page":"203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9459999799728394,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.9398000240325928,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.698797345161438},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6751081347465515},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.630333662033081},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5796753168106079},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5149403214454651},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.5141213536262512},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.47724032402038574},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4554433822631836},{"id":"https://openalex.org/keywords/cognitive-architecture","display_name":"Cognitive architecture","score":0.4497312903404236},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4480679929256439},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4470583200454712},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.4053478240966797},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.20513445138931274},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09969183802604675},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09736689925193787}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.698797345161438},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6751081347465515},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.630333662033081},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5796753168106079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5149403214454651},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.5141213536262512},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.47724032402038574},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4554433822631836},{"id":"https://openalex.org/C20854674","wikidata":"https://www.wikidata.org/wiki/Q4386060","display_name":"Cognitive architecture","level":3,"score":0.4497312903404236},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4480679929256439},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4470583200454712},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4053478240966797},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.20513445138931274},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09969183802604675},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09736689925193787},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-642-39802-5_17","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-39802-5_17","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:boa.unimib.it:10281/301913","is_oa":true,"landing_page_url":"http://hdl.handle.net/10281/301913","pdf_url":"http://hdl.handle.net/10281/301913","source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:boa.unimib.it:10281/301913","is_oa":true,"landing_page_url":"http://hdl.handle.net/10281/301913","pdf_url":"http://hdl.handle.net/10281/301913","source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338370","display_name":"FP7 Information and Communication Technologies","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W20840515.pdf","grobid_xml":"https://content.openalex.org/works/W20840515.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W94274217","https://openalex.org/W123964375","https://openalex.org/W180325379","https://openalex.org/W355724390","https://openalex.org/W1491843047","https://openalex.org/W1515851193","https://openalex.org/W1556499654","https://openalex.org/W1557073320","https://openalex.org/W1777239053","https://openalex.org/W1864286575","https://openalex.org/W1982948368","https://openalex.org/W1989616852","https://openalex.org/W2022029210","https://openalex.org/W2043608504","https://openalex.org/W2048984163","https://openalex.org/W2049095866","https://openalex.org/W2052117683","https://openalex.org/W2059156134","https://openalex.org/W2079813462","https://openalex.org/W2096351669","https://openalex.org/W2101692583","https://openalex.org/W2106237563","https://openalex.org/W2115356364","https://openalex.org/W2121375212","https://openalex.org/W2121863487","https://openalex.org/W2123429050","https://openalex.org/W2128349062","https://openalex.org/W2128922568","https://openalex.org/W2140219596","https://openalex.org/W2144691386","https://openalex.org/W2152364132","https://openalex.org/W2168986765","https://openalex.org/W2171578695","https://openalex.org/W2239029832","https://openalex.org/W2296434941","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2967463586","https://openalex.org/W2765830098","https://openalex.org/W1971989957","https://openalex.org/W3157641275","https://openalex.org/W2517338020","https://openalex.org/W4312300846","https://openalex.org/W2615757685","https://openalex.org/W2098782634","https://openalex.org/W3000546688"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
