{"id":"https://openalex.org/W4389315147","doi":"https://doi.org/10.1109/cog57401.2023.10333131","title":"Continuous Episodic Control","display_name":"Continuous Episodic Control","publication_year":2023,"publication_date":"2023-08-21","ids":{"openalex":"https://openalex.org/W4389315147","doi":"https://doi.org/10.1109/cog57401.2023.10333131"},"language":"en","primary_location":{"id":"doi:10.1109/cog57401.2023.10333131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog57401.2023.10333131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},"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/A5100362753","display_name":"Yang Zhao","orcid":"https://orcid.org/0009-0008-5440-7128"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Zhao Yang","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science Leiden University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science Leiden University","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003595753","display_name":"Thomas M. Moerland","orcid":null},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Thomas. M. Moerland","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science Leiden University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science Leiden University","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062774048","display_name":"Mike Preu\u00df","orcid":"https://orcid.org/0000-0003-4681-1346"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mike Preuss","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science Leiden University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science Leiden University","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085542421","display_name":"Aske Plaat","orcid":"https://orcid.org/0000-0001-7202-3322"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Aske Plaat","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science Leiden University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science Leiden University","institution_ids":["https://openalex.org/I121797337"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I121797337"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9789000153541565,"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/T11457","display_name":"Adipose Tissue and Metabolism","score":0.9491000175476074,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8076198101043701},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.743090808391571},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6217201352119446},{"id":"https://openalex.org/keywords/episodic-memory","display_name":"Episodic memory","score":0.5688191056251526},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5665242671966553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.557083249092102},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.528563380241394},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5211177468299866},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4395093619823456},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41644734144210815},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22360897064208984},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11029598116874695},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0873073935508728},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.07832261919975281}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8076198101043701},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743090808391571},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6217201352119446},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.5688191056251526},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5665242671966553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.557083249092102},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.528563380241394},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5211177468299866},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4395093619823456},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41644734144210815},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22360897064208984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11029598116874695},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0873073935508728},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.07832261919975281},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cog57401.2023.10333131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog57401.2023.10333131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarlypublications.universiteitleiden.nl:item_4273657","is_oa":false,"landing_page_url":"https://hdl.handle.net/1887/4273657","pdf_url":null,"source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2023 IEEE Conference on Games, CoG 2023","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1766797326","https://openalex.org/W1959608418","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2436711315","https://openalex.org/W2766447205","https://openalex.org/W2913668833","https://openalex.org/W2964082094","https://openalex.org/W2973229164","https://openalex.org/W2982316857","https://openalex.org/W3011120880","https://openalex.org/W3018036994","https://openalex.org/W3041214984","https://openalex.org/W3129322645","https://openalex.org/W3189480080","https://openalex.org/W4210870706","https://openalex.org/W4214717370","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6640963894","https://openalex.org/W6684921986","https://openalex.org/W6718359804","https://openalex.org/W6734330393","https://openalex.org/W6735003056","https://openalex.org/W6747473740","https://openalex.org/W6775686901","https://openalex.org/W6791277150","https://openalex.org/W6803314920"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2912415823"],"abstract_inverted_index":{"Non-parametric":[0],"episodic":[1,50,83],"memory":[2,84],"can":[3,129],"be":[4,30,130],"used":[5],"to":[6,18,29,37,67],"quickly":[7],"latch":[8],"onto":[9],"high-rewarded":[10],"experience":[11],"in":[12,24,55,90,136],"reinforcement":[13,21],"learning":[14,22,135],"tasks.":[15,139],"In":[16,126],"contrast":[17],"parametric":[19],"deep":[20],"approaches":[23],"which":[25],"reward":[26],"signals":[27],"need":[28,36],"back-propagated":[31],"slowly,":[32],"these":[33],"methods":[34],"only":[35,64],"discover":[38],"the":[39,47],"solution":[40],"once,":[41],"and":[42,58,115],"may":[43],"then":[44],"repeatedly":[45],"solve":[46],"task.":[48],"However,":[49],"control":[51,102,138],"solutions":[52],"are":[53],"stored":[54],"discrete":[56,68],"tables,":[57],"this":[59,73],"approach":[60,133],"has":[61],"so":[62],"far":[63],"been":[65],"applied":[66],"action":[69,95],"space":[70],"problems.":[71],"Therefore,":[72],"paper":[74],"introduces":[75],"Continuous":[76],"Episodic":[77],"Control":[78],"(CEC),":[79],"a":[80,93,131],"novel":[81],"non-parametric":[82],"algorithm":[85],"for":[86,134],"sequential":[87],"decision":[88],"making":[89],"problems":[91],"with":[92],"continuous":[94,101,137],"space.":[96],"Results":[97],"on":[98],"several":[99],"sparse-reward":[100],"environments":[103],"show":[104],"that":[105],"our":[106],"proposed":[107],"method":[108],"learns":[109],"faster":[110],"than":[111],"state-of-the-art":[112],"model-free":[113],"RL":[114,117],"memory-augmented":[116],"algorithms,":[118],"while":[119],"maintaining":[120],"good":[121],"long-run":[122],"performance":[123],"as":[124],"well.":[125],"short,":[127],"CEC":[128],"fast":[132],"<sup":[140],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[141],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[142]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}