{"id":"https://openalex.org/W2964082094","doi":"https://doi.org/10.24963/ijcai.2018/337","title":"Episodic Memory Deep Q-Networks","display_name":"Episodic Memory Deep Q-Networks","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2964082094","doi":"https://doi.org/10.24963/ijcai.2018/337","mag":"2964082094"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/337","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/337","pdf_url":"https://www.ijcai.org/proceedings/2018/0337.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0337.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070351115","display_name":"Zichuan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Zichuan Lin","raw_affiliation_strings":["Microsoft Research","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103082783","display_name":"Tianqi Zhao","orcid":"https://orcid.org/0000-0002-1625-4502"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tianqi Zhao","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101678397","display_name":"Guangwen Yang","orcid":"https://orcid.org/0000-0002-8673-8254"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangwen Yang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101985940","display_name":"Lintao Zhang","orcid":"https://orcid.org/0009-0005-7527-8183"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lintao Zhang","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3928,"has_fulltext":true,"cited_by_count":67,"citation_normalized_percentile":{"value":0.95580472,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2433","last_page":"2439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9921000003814697,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9916999936103821,"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":0.8427917957305908},{"id":"https://openalex.org/keywords/episodic-memory","display_name":"Episodic memory","score":0.8331730365753174},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8267784118652344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6034051775932312},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5605533719062805},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47219833731651306},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4395657479763031},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.07745766639709473},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06137403845787048},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.05868101119995117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8427917957305908},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.8331730365753174},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8267784118652344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6034051775932312},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5605533719062805},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47219833731651306},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4395657479763031},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.07745766639709473},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06137403845787048},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.05868101119995117}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2018/337","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/337","pdf_url":"https://www.ijcai.org/proceedings/2018/0337.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/337","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/337","pdf_url":"https://www.ijcai.org/proceedings/2018/0337.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964082094.pdf","grobid_xml":"https://content.openalex.org/works/W2964082094.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W51508254","https://openalex.org/W1538131130","https://openalex.org/W1906772730","https://openalex.org/W1980035368","https://openalex.org/W2100983013","https://openalex.org/W2112707476","https://openalex.org/W2113913482","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2165558283","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2260756217","https://openalex.org/W2290354866","https://openalex.org/W2346736747","https://openalex.org/W2436711315","https://openalex.org/W2553109721","https://openalex.org/W2583528914","https://openalex.org/W2746553466","https://openalex.org/W2950471160","https://openalex.org/W2951799221","https://openalex.org/W2952509347","https://openalex.org/W2962766894","https://openalex.org/W2964006217","https://openalex.org/W2964043796","https://openalex.org/W2979473749","https://openalex.org/W3103780890","https://openalex.org/W4254755460","https://openalex.org/W4297732320","https://openalex.org/W6602057636","https://openalex.org/W6677145610","https://openalex.org/W6684266549","https://openalex.org/W6864014924"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W4315865067","https://openalex.org/W2979433843","https://openalex.org/W3208304128"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"algorithms":[3,25],"have":[4],"made":[5],"huge":[6],"progress":[7],"in":[8],"recent":[9],"years":[10],"by":[11],"leveraging":[12],"the":[13,21,39,116],"power":[14],"of":[15,36,115,118],"deep":[16,23],"neural":[17],"networks":[18],"(DNN).":[19],"Despite":[20],"success,":[22],"RL":[24,49,74,137],"are":[26],"known":[27],"to":[28,41,54,57,86,99,107,120],"be":[29],"sample":[30,101],"inefficient,":[31],"often":[32],"requiring":[33],"many":[34,122],"rounds":[35],"interactions":[37,117],"with":[38],"environments":[40],"obtain":[42],"satisfactory":[43],"performances.":[44],"Recently,":[45],"episodic":[46,84,134],"memory":[47,85,135],"based":[48,136],"has":[50],"attracted":[51],"attention":[52],"due":[53],"its":[55],"ability":[56],"latch":[58],"on":[59,125],"good":[60,109],"actions":[61],"quickly.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"present":[67],"a":[68],"simple":[69],"yet":[70],"effective":[71],"biologically":[72],"inspired":[73],"algorithm":[75],"called":[76],"Episodic":[77],"Memory":[78],"Deep":[79],"Q-Networks":[80],"(EMDQN),":[81],"which":[82],"leverages":[83],"supervise":[87],"an":[88],"agent":[89],"during":[90],"training.":[91],"Experiments":[92],"show":[93],"that":[94],"our":[95],"proposed":[96],"method":[97],"leads":[98],"better":[100],"efficiency":[102],"and":[103,132],"is":[104],"more":[105],"likely":[106],"find":[108],"policy.":[110],"It":[111],"only":[112],"requires":[113],"1/5":[114],"DQN":[119,131],"achieve":[121],"state-of-the-art":[123],"performances":[124],"Atari":[126],"games,":[127],"significantly":[128],"outperforming":[129],"regular":[130],"other":[133],"algorithms.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}