{"id":"https://openalex.org/W1945304475","doi":"https://doi.org/10.1007/11676935_5","title":"Reinforcement Distribution in Continuous State Action Space Fuzzy Q\u2013Learning: A Novel Approach","display_name":"Reinforcement Distribution in Continuous State Action Space Fuzzy Q\u2013Learning: A Novel Approach","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W1945304475","doi":"https://doi.org/10.1007/11676935_5","mag":"1945304475"},"language":"en","primary_location":{"id":"doi:10.1007/11676935_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/11676935_5","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":"book-chapter","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/A5060263666","display_name":"Andrea Bonarini","orcid":"https://orcid.org/0000-0002-4880-4521"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Andrea Bonarini","raw_affiliation_strings":["Politecnico di Milano Electronic and Information Department, Piazza Leonardo da Vinci, 32, 20133, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano Electronic and Information Department, Piazza Leonardo da Vinci, 32, 20133, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082314614","display_name":"Francesco Montrone","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Montrone","raw_affiliation_strings":["Politecnico di Milano Electronic and Information Department, Piazza Leonardo da Vinci, 32, 20133, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano Electronic and Information Department, Piazza Leonardo da Vinci, 32, 20133, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017130830","display_name":"Marcello Restelli","orcid":"https://orcid.org/0000-0002-6322-1076"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marcello Restelli","raw_affiliation_strings":["Politecnico di Milano Electronic and Information Department, Piazza Leonardo da Vinci, 32, 20133, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano Electronic and Information Department, Piazza Leonardo da Vinci, 32, 20133, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060263666"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.3022,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5954513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"40","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9937000274658203,"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":0.9937000274658203,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.988099992275238,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8012350797653198},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6075829267501831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5999194383621216},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5635076761245728},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.5309039354324341},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4903128445148468},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4842393100261688},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4605085253715515},{"id":"https://openalex.org/keywords/fuzzy-inference","display_name":"Fuzzy inference","score":0.4565730392932892},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44363903999328613},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.41367006301879883},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.41010114550590515},{"id":"https://openalex.org/keywords/fuzzy-control-system","display_name":"Fuzzy control system","score":0.3629167377948761},{"id":"https://openalex.org/keywords/adaptive-neuro-fuzzy-inference-system","display_name":"Adaptive neuro fuzzy inference system","score":0.33659636974334717},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32668668031692505},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25568363070487976},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17892378568649292},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.04609322547912598}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8012350797653198},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6075829267501831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5999194383621216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5635076761245728},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.5309039354324341},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4903128445148468},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4842393100261688},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4605085253715515},{"id":"https://openalex.org/C2986395286","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy inference","level":5,"score":0.4565730392932892},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44363903999328613},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.41367006301879883},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.41010114550590515},{"id":"https://openalex.org/C195975749","wikidata":"https://www.wikidata.org/wiki/Q1475705","display_name":"Fuzzy control system","level":3,"score":0.3629167377948761},{"id":"https://openalex.org/C186108316","wikidata":"https://www.wikidata.org/wiki/Q352530","display_name":"Adaptive neuro fuzzy inference system","level":4,"score":0.33659636974334717},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32668668031692505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25568363070487976},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17892378568649292},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.04609322547912598},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/11676935_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/11676935_5","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1515851193","https://openalex.org/W1551593752","https://openalex.org/W1557517019","https://openalex.org/W1932277696","https://openalex.org/W1980056622","https://openalex.org/W2121863487","https://openalex.org/W2162906935","https://openalex.org/W2312609093","https://openalex.org/W4214717370","https://openalex.org/W4236304806"],"related_works":["https://openalex.org/W2114654021","https://openalex.org/W2263529430","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W3009457412","https://openalex.org/W2364727641"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}