{"id":"https://openalex.org/W4286603692","doi":"https://doi.org/10.1007/978-3-031-10525-8_6","title":"On the\u00a0Effects of\u00a0Properties of\u00a0the\u00a0Minibatch in\u00a0Reinforcement Learning","display_name":"On the\u00a0Effects of\u00a0Properties of\u00a0the\u00a0Minibatch in\u00a0Reinforcement Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4286603692","doi":"https://doi.org/10.1007/978-3-031-10525-8_6"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-10525-8_6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-10525-8_6","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information 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/A5032155769","display_name":"Eivind B\u00f8hn","orcid":"https://orcid.org/0000-0002-0676-3688"},"institutions":[{"id":"https://openalex.org/I173888879","display_name":"SINTEF","ror":"https://ror.org/01f677e56","country_code":"NO","type":"facility","lineage":["https://openalex.org/I173888879"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Eivind B\u00f8hn","raw_affiliation_strings":["Department of Mathematics and Cybernetics, SINTEF, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Cybernetics, SINTEF, Oslo, Norway","institution_ids":["https://openalex.org/I173888879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026424052","display_name":"Signe Moe","orcid":null},"institutions":[{"id":"https://openalex.org/I173888879","display_name":"SINTEF","ror":"https://ror.org/01f677e56","country_code":"NO","type":"facility","lineage":["https://openalex.org/I173888879"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Signe Moe","raw_affiliation_strings":["Department of Engineering Cybernetics, NTNU, Trondheim, Norway","Department of Mathematics and Cybernetics, SINTEF, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Cybernetics, NTNU, Trondheim, Norway","institution_ids":[]},{"raw_affiliation_string":"Department of Mathematics and Cybernetics, SINTEF, Oslo, Norway","institution_ids":["https://openalex.org/I173888879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012692888","display_name":"Tor Arne Johansen","orcid":"https://orcid.org/0000-0001-9440-5989"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tor Arne Johansen","raw_affiliation_strings":["Department of Engineering Cybernetics, NTNU, Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Cybernetics, NTNU, Trondheim, Norway","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032155769"],"corresponding_institution_ids":["https://openalex.org/I173888879"],"apc_list":null,"apc_paid":null,"fwci":0.3429,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58635178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9997000098228455,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7489052414894104},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.7355993390083313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6947928667068481},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6138217449188232},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.6066809892654419},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5741058588027954},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5121355056762695},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5061396956443787},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4661976397037506},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.4544033706188202},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4488636255264282},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.44596046209335327},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43887609243392944},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4205136001110077},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41873544454574585},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2300128936767578},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1758469045162201},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10055845975875854}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7489052414894104},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.7355993390083313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6947928667068481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6138217449188232},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.6066809892654419},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5741058588027954},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5121355056762695},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5061396956443787},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4661976397037506},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.4544033706188202},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4488636255264282},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.44596046209335327},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43887609243392944},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4205136001110077},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41873544454574585},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2300128936767578},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1758469045162201},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10055845975875854},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-10525-8_6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-10525-8_6","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information 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":8,"referenced_works":["https://openalex.org/W1673310716","https://openalex.org/W2009797711","https://openalex.org/W2173248099","https://openalex.org/W2761873684","https://openalex.org/W2963433607","https://openalex.org/W2972758308","https://openalex.org/W2997599645","https://openalex.org/W6603732165"],"related_works":["https://openalex.org/W2895097035","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W3020853991","https://openalex.org/W4362706668","https://openalex.org/W4231621013","https://openalex.org/W3171021120","https://openalex.org/W3008318776"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
