{"id":"https://openalex.org/W4401209889","doi":"https://doi.org/10.1007/978-981-97-5581-3_32","title":"Efficient Reinforcement Learning via Decoupling Exploration and Utilization","display_name":"Efficient Reinforcement Learning via Decoupling Exploration and Utilization","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401209889","doi":"https://doi.org/10.1007/978-981-97-5581-3_32"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-97-5581-3_32","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-97-5581-3_32","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/A5102251703","display_name":"Jingpu Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingpu Yang","raw_affiliation_strings":["Northeastern University, Shenyang, 110819, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, 110819, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101664824","display_name":"Helin Wang","orcid":"https://orcid.org/0000-0001-6088-0378"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helin Wang","raw_affiliation_strings":["Northeastern University, Shenyang, 110819, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, 110819, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102541694","display_name":"Qirui Zhao","orcid":"https://orcid.org/0009-0004-0623-9204"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qirui Zhao","raw_affiliation_strings":["Northeastern University, Shenyang, 110819, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, 110819, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114201382","display_name":"Zhecheng Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhecheng Shi","raw_affiliation_strings":["Northeastern University, Shenyang, 110819, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, 110819, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108833307","display_name":"Zirui Song","orcid":null},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zirui Song","raw_affiliation_strings":["University of Technology Sydney, Sydney, 2007, Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, 2007, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081000664","display_name":"Fang Miao","orcid":"https://orcid.org/0000-0002-5117-5869"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]},{"id":"https://openalex.org/I4210100070","display_name":"Guangzhou Mechanical Engineering Research Institute (China)","ror":"https://ror.org/0114hcc46","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210100070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao Fang","raw_affiliation_strings":["Northeastern University, Shenyang, 110819, China","Olimei Company, Guangzhou, 510420, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, 110819, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Olimei Company, Guangzhou, 510420, China","institution_ids":["https://openalex.org/I4210100070"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102251703"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26941022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"396","last_page":"406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9904000163078308,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8664500713348389},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8554104566574097},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.8311586976051331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4593117833137512},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.1540476381778717}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8664500713348389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8554104566574097},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.8311586976051331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4593117833137512},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.1540476381778717},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-97-5581-3_32","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-97-5581-3_32","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":22,"referenced_works":["https://openalex.org/W2073787051","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2257979135","https://openalex.org/W2260756217","https://openalex.org/W2766447205","https://openalex.org/W2799899844","https://openalex.org/W2877093712","https://openalex.org/W3087403610","https://openalex.org/W3126321819","https://openalex.org/W3214325366","https://openalex.org/W4283789768","https://openalex.org/W4283801758","https://openalex.org/W4307772200","https://openalex.org/W4376112099","https://openalex.org/W4382866712","https://openalex.org/W4390446540","https://openalex.org/W6600018615","https://openalex.org/W6702088316","https://openalex.org/W6729404389","https://openalex.org/W6775522024","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4313561376","https://openalex.org/W3103825105","https://openalex.org/W3027880158","https://openalex.org/W1617565119","https://openalex.org/W160381218","https://openalex.org/W2512958550","https://openalex.org/W2390279801","https://openalex.org/W2004102934"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}