{"id":"https://openalex.org/W4312723588","doi":"https://doi.org/10.1007/978-3-031-20868-3_11","title":"Optimizing Exploration-Exploitation Trade-off in\u00a0Continuous Action Spaces via\u00a0Q-ensemble","display_name":"Optimizing Exploration-Exploitation Trade-off in\u00a0Continuous Action Spaces via\u00a0Q-ensemble","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312723588","doi":"https://doi.org/10.1007/978-3-031-20868-3_11"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-20868-3_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-20868-3_11","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/A5100408966","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0003-0124-9433"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University of Technology, Maanshan, 243032, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University of Technology, Maanshan, 243032, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101991566","display_name":"Haihong Zhang","orcid":"https://orcid.org/0000-0003-3199-0126"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haihong Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University of Technology, Maanshan, 243032, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University of Technology, Maanshan, 243032, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001511884","display_name":"Xueyu Wei","orcid":"https://orcid.org/0000-0003-1505-3087"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueyu Wei","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University of Technology, Maanshan, 243032, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University of Technology, Maanshan, 243032, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401500","display_name":"Tao Tao","orcid":"https://orcid.org/0000-0002-5630-2070"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Tao","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University of Technology, Maanshan, 243032, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University of Technology, Maanshan, 243032, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100372201","display_name":"Xue Li","orcid":"https://orcid.org/0000-0002-4515-6792"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Li","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University of Technology, Maanshan, 243032, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University of Technology, Maanshan, 243032, China","institution_ids":["https://openalex.org/I92178344"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I92178344"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"148","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9909999966621399,"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":0.9909999966621399,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9520000219345093,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9445000290870667,"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/computer-science","display_name":"Computer science","score":0.823547899723053},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.6801697015762329},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5216187238693237},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5167383551597595},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.502877414226532},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.47899100184440613},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4354243874549866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4276278018951416},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42560920119285583},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4225200116634369},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4196045398712158}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.823547899723053},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.6801697015762329},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5216187238693237},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5167383551597595},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.502877414226532},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.47899100184440613},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4354243874549866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4276278018951416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42560920119285583},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4225200116634369},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4196045398712158},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-20868-3_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-20868-3_11","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/W1977655452","https://openalex.org/W2158782408","https://openalex.org/W3162309646","https://openalex.org/W6600450872","https://openalex.org/W6620244557","https://openalex.org/W6814003322","https://openalex.org/W6815744420"],"related_works":["https://openalex.org/W2794896638","https://openalex.org/W1807784185","https://openalex.org/W4390905871","https://openalex.org/W3202800081","https://openalex.org/W1909207154","https://openalex.org/W3124390867","https://openalex.org/W3101614107","https://openalex.org/W3204228978","https://openalex.org/W1514365828","https://openalex.org/W3036530763"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
