{"id":"https://openalex.org/W4386931056","doi":"https://doi.org/10.1007/978-3-031-44198-1_16","title":"Efficient Reinforcement Learning Using State-Action Uncertainty with\u00a0Multiple Heads","display_name":"Efficient Reinforcement Learning Using State-Action Uncertainty with\u00a0Multiple Heads","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386931056","doi":"https://doi.org/10.1007/978-3-031-44198-1_16"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-44198-1_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-44198-1_16","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092916608","display_name":"Tomoharu Aizu","orcid":null},"institutions":[{"id":"https://openalex.org/I4840577","display_name":"Toyota Technological Institute","ror":"https://ror.org/001hv0k59","country_code":"JP","type":"education","lineage":["https://openalex.org/I4840577"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tomoharu Aizu","raw_affiliation_strings":["Toyota Technological Institute, Nagoya, Aichi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I4840577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072993100","display_name":"Takeru Oba","orcid":"https://orcid.org/0000-0002-8858-3647"},"institutions":[{"id":"https://openalex.org/I4840577","display_name":"Toyota Technological Institute","ror":"https://ror.org/001hv0k59","country_code":"JP","type":"education","lineage":["https://openalex.org/I4840577"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeru Oba","raw_affiliation_strings":["Toyota Technological Institute, Nagoya, Aichi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I4840577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053167635","display_name":"Norimichi Ukita","orcid":"https://orcid.org/0000-0002-0240-1065"},"institutions":[{"id":"https://openalex.org/I4840577","display_name":"Toyota Technological Institute","ror":"https://ror.org/001hv0k59","country_code":"JP","type":"education","lineage":["https://openalex.org/I4840577"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Norimichi Ukita","raw_affiliation_strings":["Toyota Technological Institute, Nagoya, Aichi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I4840577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5092916608"],"corresponding_institution_ids":["https://openalex.org/I4840577"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"184","last_page":"196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9801999926567078,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9793000221252441,"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":0.9073455333709717},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8222492337226868},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6695049405097961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6067121624946594},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6001091599464417},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5280196070671082},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4513765871524811},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4101922810077667},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08691301941871643},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06309264898300171}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9073455333709717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8222492337226868},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6695049405097961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6067121624946594},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6001091599464417},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5280196070671082},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4513765871524811},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4101922810077667},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08691301941871643},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06309264898300171},{"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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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:10.1007/978-3-031-44198-1_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-44198-1_16","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1988526405","https://openalex.org/W2167489871","https://openalex.org/W2561776174","https://openalex.org/W2996695841","https://openalex.org/W2996868001","https://openalex.org/W4214717370","https://openalex.org/W6775522024"],"related_works":["https://openalex.org/W4388870064","https://openalex.org/W4235186151","https://openalex.org/W2056057048","https://openalex.org/W2054685365","https://openalex.org/W2272354214","https://openalex.org/W2120383820","https://openalex.org/W2043010663","https://openalex.org/W2667588871","https://openalex.org/W4248308508","https://openalex.org/W2912415823"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
