{"id":"https://openalex.org/W4389302466","doi":"https://doi.org/10.1109/cog57401.2023.10333174","title":"Two-Memory Reinforcement Learning","display_name":"Two-Memory Reinforcement Learning","publication_year":2023,"publication_date":"2023-08-21","ids":{"openalex":"https://openalex.org/W4389302466","doi":"https://doi.org/10.1109/cog57401.2023.10333174"},"language":"en","primary_location":{"id":"doi:10.1109/cog57401.2023.10333174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog57401.2023.10333174","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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9793999791145325,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10581","display_name":"Neural dynamics and brain function","score":0.9603000283241272,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.887252926826477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6766747832298279},{"id":"https://openalex.org/keywords/episodic-memory","display_name":"Episodic memory","score":0.6751041412353516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5651084184646606},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5084092020988464},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43869855999946594},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.4339243173599243},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.42505836486816406},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38033968210220337},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.21023234724998474},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12105745077133179},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.08262050151824951}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.887252926826477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6766747832298279},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.6751041412353516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5651084184646606},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5084092020988464},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43869855999946594},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.4339243173599243},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.42505836486816406},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38033968210220337},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.21023234724998474},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12105745077133179},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.08262050151824951},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cog57401.2023.10333174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog57401.2023.10333174","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_4273658","is_oa":false,"landing_page_url":"https://hdl.handle.net/1887/4273658","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":"2023 IEEE Conference on Games (CoG)","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2056915253","https://openalex.org/W2083473390","https://openalex.org/W2150468603","https://openalex.org/W2201581102","https://openalex.org/W2436711315","https://openalex.org/W2766447205","https://openalex.org/W2785998395","https://openalex.org/W2948937890","https://openalex.org/W2964082094","https://openalex.org/W2970393539","https://openalex.org/W3134294674","https://openalex.org/W3189480080","https://openalex.org/W4210870706","https://openalex.org/W4213377513","https://openalex.org/W4214717370","https://openalex.org/W4298857966","https://openalex.org/W4300799055","https://openalex.org/W4302010773","https://openalex.org/W4308022997","https://openalex.org/W4389315147","https://openalex.org/W6637967152","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6718359804","https://openalex.org/W6734330393","https://openalex.org/W6740801417","https://openalex.org/W6747682777","https://openalex.org/W6763056091","https://openalex.org/W6767047803","https://openalex.org/W6791277150","https://openalex.org/W6846607747","https://openalex.org/W6846620579"],"related_works":["https://openalex.org/W4289718052","https://openalex.org/W2164121020","https://openalex.org/W2145559838","https://openalex.org/W2905319430","https://openalex.org/W3116498279","https://openalex.org/W4287549553","https://openalex.org/W4310285384","https://openalex.org/W3183027292","https://openalex.org/W4248896073","https://openalex.org/W2768698792"],"abstract_inverted_index":{"While":[0],"deep":[1],"reinforcement":[2,61,95,104,132,158,189],"learning":[3,39,46,62,79,96,105,133,190],"has":[4],"shown":[5],"important":[6],"empirical":[7],"success,":[8],"it":[9],"tends":[10],"to":[11,16,106,135,180],"learn":[12],"relatively":[13],"slow":[14,17,23],"due":[15],"propagation":[18],"of":[19,25,84,109,118,130],"rewards":[20],"information":[21],"and":[22,47,60,68,80,103,123,126,150,156],"update":[24],"parametric":[26],"neural":[27],"networks.":[28],"Non-parametric":[29],"episodic":[30,50,101,120,154,183],"memory,":[31],"on":[32],"the":[33,116,119,124,127,131,143,169],"other":[34,187],"hand,":[35],"provides":[36,172],"a":[37,91,163,173],"faster":[38],"alternative":[40],"that":[41,99,142,176],"does":[42],"not":[43],"require":[44],"representation":[45],"uses":[48],"maximum":[49],"return":[51],"as":[52,160,162],"state-action":[53],"values":[54],"for":[55],"action":[56],"selection.":[57],"Episodic":[58],"memory":[59,75,102,121,155,184],"both":[63,108,152],"have":[64],"their":[65,110],"own":[66],"strengths":[67],"weaknesses.":[69],"Notably,":[70],"humans":[71],"can":[72,177],"leverage":[73],"multiple":[74],"systems":[76],"concurrently":[77],"during":[78],"benefit":[81],"from":[82],"all":[83],"them.":[85],"In":[86],"this":[87],"work,":[88],"we":[89],"propose":[90],"method":[92],"called":[93],"Two-Memory":[94],"agent":[97,114,145,185],"(2M)":[98],"combines":[100],"distill":[107],"strengths.":[111],"The":[112],"2M":[113,144],"exploits":[115],"speed":[117],"part":[122,134],"optimality":[125],"generalization":[128],"capacity":[129],"complement":[136],"each":[137],"other.":[138],"Our":[139],"experiments":[140],"demonstrate":[141],"is":[146],"more":[147],"data":[148],"efficient":[149],"outperforms":[151],"pure":[153,157],"learning,":[159],"well":[161],"state-of-the-art":[164],"memory-augmented":[165],"RL":[166],"agent.":[167],"Moreover,":[168],"proposed":[170],"approach":[171],"general":[174],"framework":[175],"be":[178],"used":[179],"combine":[181],"any":[182],"with":[186],"off-policy":[188],"algorithms.":[191],"<sup":[192],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[193],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}