{"id":"https://openalex.org/W3114470652","doi":"https://doi.org/10.1109/gcce50665.2020.9291872","title":"Rainbow with Episodic Memory in Deep Reinforcement Learning","display_name":"Rainbow with Episodic Memory in Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-10-13","ids":{"openalex":"https://openalex.org/W3114470652","doi":"https://doi.org/10.1109/gcce50665.2020.9291872","mag":"3114470652"},"language":"en","primary_location":{"id":"doi:10.1109/gcce50665.2020.9291872","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce50665.2020.9291872","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"},"type":"article","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/A5083622472","display_name":"Daiki Kuyoshi","orcid":null},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Daiki Kuyoshi","raw_affiliation_strings":["Kanazawa University, Kanazawa, Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa University, Kanazawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000097788","display_name":"Toi Tsuneda","orcid":"https://orcid.org/0000-0003-1913-9179"},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toi Tsuneda","raw_affiliation_strings":["Kanazawa University, Kanazawa, Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa University, Kanazawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102728648","display_name":"Satoshi Yamane","orcid":"https://orcid.org/0000-0001-7883-4054"},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Yamane","raw_affiliation_strings":["Kanazawa University, Kanazawa, Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa University, Kanazawa, Japan","institution_ids":["https://openalex.org/I10091056"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083622472"],"corresponding_institution_ids":["https://openalex.org/I10091056"],"apc_list":null,"apc_paid":null,"fwci":0.2651,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64886571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"70","issue":null,"first_page":"113","last_page":"116"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9976999759674072,"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":0.9627000093460083,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.863917350769043},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7739502191543579},{"id":"https://openalex.org/keywords/episodic-memory","display_name":"Episodic memory","score":0.7118649482727051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6327469944953918},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6003038883209229},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.5563266277313232},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.455466091632843},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4203948676586151},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1039949357509613},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.1003713607788086},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08383959531784058},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06982877850532532}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.863917350769043},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7739502191543579},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.7118649482727051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6327469944953918},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6003038883209229},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.5563266277313232},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.455466091632843},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4203948676586151},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1039949357509613},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.1003713607788086},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08383959531784058},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06982877850532532},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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":1,"locations":[{"id":"doi:10.1109/gcce50665.2020.9291872","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce50665.2020.9291872","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2100677568","https://openalex.org/W2112707476","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2724169821","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2890148520","https://openalex.org/W2951799221","https://openalex.org/W2963423916","https://openalex.org/W2963477884","https://openalex.org/W2964174623","https://openalex.org/W2994240296","https://openalex.org/W3041202696","https://openalex.org/W3157836284","https://openalex.org/W4289376774","https://openalex.org/W4298876402","https://openalex.org/W6677145610","https://openalex.org/W6683300800","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6740092555","https://openalex.org/W6744838376","https://openalex.org/W6754857033","https://openalex.org/W6771522568","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4243114048","https://openalex.org/W2529605301","https://openalex.org/W4237896776","https://openalex.org/W4231665652","https://openalex.org/W1837630526","https://openalex.org/W2000242494","https://openalex.org/W2335589441","https://openalex.org/W4296826658","https://openalex.org/W1979697693","https://openalex.org/W2164312800"],"abstract_inverted_index":{"Recently,":[0],"episodic":[1,39],"memory":[2,40],"based":[3],"deep":[4],"reinforcement":[5],"learning":[6,26],"using":[7],"nonparametric":[8],"value":[9],"estimation":[10],"such":[11],"as":[12],"EVA":[13,43],"has":[14],"attracted":[15],"attention":[16],"because":[17],"these":[18],"methods":[19],"can":[20],"improve":[21],"sample":[22,64],"efficiency":[23,65],"and":[24,66],"converge":[25],"faster.":[27],"In":[28],"this":[29,54],"paper,":[30],"we":[31],"propose":[32],"a":[33],"method":[34,55],"that":[35],"combines":[36],"Rainbow":[37],"with":[38],"by":[41],"extending":[42],"in":[44,60],"order":[45],"for":[46],"an":[47,57],"agent":[48,58],"to":[49],"perform":[50],"better.":[51],"We":[52],"show":[53],"improves":[56],"performance":[59],"terms":[61],"of":[62],"both":[63],"getting":[67],"high":[68],"scores":[69],"through":[70],"some":[71],"experiments":[72],"on":[73],"Atari":[74],"environment.":[75]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}