{"id":"https://openalex.org/W4312941177","doi":"https://doi.org/10.1109/ijcnn55064.2022.9891902","title":"Deep Reinforcement Learning with Parametric Episodic Memory","display_name":"Deep Reinforcement Learning with Parametric Episodic Memory","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312941177","doi":"https://doi.org/10.1109/ijcnn55064.2022.9891902"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9891902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9891902","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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/A5006937743","display_name":"Kangkang Chen","orcid":"https://orcid.org/0000-0002-2250-0941"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kangkang Chen","raw_affiliation_strings":["Institute of AI and Robotics, Fudan University, Academy for Engineering and Technology,Shanghai,China,200433"],"affiliations":[{"raw_affiliation_string":"Institute of AI and Robotics, Fudan University, Academy for Engineering and Technology,Shanghai,China,200433","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103267605","display_name":"Zhongxue Gan","orcid":"https://orcid.org/0000-0003-2709-6148"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongxue Gan","raw_affiliation_strings":["Institute of AI and Robotics, Fudan University, Academy for Engineering and Technology,Shanghai,China,200433"],"affiliations":[{"raw_affiliation_string":"Institute of AI and Robotics, Fudan University, Academy for Engineering and Technology,Shanghai,China,200433","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003378348","display_name":"Siyang Leng","orcid":"https://orcid.org/0000-0002-2285-4758"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyang Leng","raw_affiliation_strings":["Institute of AI and Robotics, Fudan University, Academy for Engineering and Technology,Shanghai,China,200433"],"affiliations":[{"raw_affiliation_string":"Institute of AI and Robotics, Fudan University, Academy for Engineering and Technology,Shanghai,China,200433","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111073539","display_name":"Chun Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Guan","raw_affiliation_strings":["Institute of AI and Robotics, Fudan University, Academy for Engineering and Technology,Shanghai,China,200433"],"affiliations":[{"raw_affiliation_string":"Institute of AI and Robotics, Fudan University, Academy for Engineering and Technology,Shanghai,China,200433","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006937743"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.1039,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.33225598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9936000108718872,"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":0.9706000089645386,"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":0.7883391380310059},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7704155445098877},{"id":"https://openalex.org/keywords/episodic-memory","display_name":"Episodic memory","score":0.7566289901733398},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6316060423851013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5386014580726624},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.4833321273326874},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.44846946001052856},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4282759130001068},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3513195514678955},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1001339852809906},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.07286468148231506},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07133910059928894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7883391380310059},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7704155445098877},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.7566289901733398},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6316060423851013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5386014580726624},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4833321273326874},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.44846946001052856},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4282759130001068},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3513195514678955},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1001339852809906},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.07286468148231506},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07133910059928894},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/ijcnn55064.2022.9891902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9891902","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2929787900","display_name":null,"funder_award_id":"12101133","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3603046598","display_name":null,"funder_award_id":"2021 SHZDZX0 103","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1714211023","https://openalex.org/W1771410628","https://openalex.org/W2099647287","https://openalex.org/W2100983013","https://openalex.org/W2158782408","https://openalex.org/W2165031188","https://openalex.org/W2257979135","https://openalex.org/W2436711315","https://openalex.org/W2574227367","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2787938642","https://openalex.org/W2803683443","https://openalex.org/W2804380964","https://openalex.org/W2902907165","https://openalex.org/W2949475445","https://openalex.org/W2963276097","https://openalex.org/W2963864421","https://openalex.org/W2964067469","https://openalex.org/W2964082094","https://openalex.org/W2996624412","https://openalex.org/W3134294674","https://openalex.org/W3189480080","https://openalex.org/W4297732320","https://openalex.org/W4302570325","https://openalex.org/W6637441126","https://openalex.org/W6638018090","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6717230150","https://openalex.org/W6718359804","https://openalex.org/W6730641667","https://openalex.org/W6732164336","https://openalex.org/W6734330393","https://openalex.org/W6741002519","https://openalex.org/W6748839928","https://openalex.org/W6751540476","https://openalex.org/W6751893390","https://openalex.org/W6756303580","https://openalex.org/W6772744401","https://openalex.org/W6791277150"],"related_works":["https://openalex.org/W1562959674","https://openalex.org/W2923653485","https://openalex.org/W2957776456","https://openalex.org/W4361026739","https://openalex.org/W2952472710","https://openalex.org/W4255994452","https://openalex.org/W4372194388","https://openalex.org/W4319083788","https://openalex.org/W3022038857","https://openalex.org/W1629725936"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"methods":[3,121],"are":[4],"widely":[5],"acknowledged":[6],"to":[7,24,48],"be":[8],"sample":[9,86],"inefficient,":[10],"while":[11],"incorporating":[12],"episodic":[13,31,58,124],"memory":[14,78],"significantly":[15],"improves":[16],"it":[17],"through":[18],"rapidly":[19],"latching":[20],"onto":[21],"successful":[22],"experiences":[23],"guide":[25],"the":[26,39,50,63,76,99,118],"action":[27],"of":[28,101],"agents.":[29],"Previous":[30],"methods,":[32],"utilizing":[33],"discrete":[34,77],"memory,":[35,103],"cannot":[36],"well":[37],"accommodate":[38],"continuous":[40,114],"control":[41,115],"tasks":[42],"and":[43,82,88,122],"have":[44],"limited":[45],"generalization":[46,89],"ability":[47],"aggregate":[49],"experience":[51],"across":[52],"trajectories.":[53],"We":[54],"propose":[55],"an":[56,92],"improved":[57],"memory-based":[59,125],"RL":[60,126],"algorithm,":[61,109],"combining":[62],"one-step":[64],"method":[65],"in":[66,97],"off-policy":[67],"algorithm":[68],"with":[69],"Parametric":[70],"Episodic":[71],"Memory":[72],"(PEM),":[73],"which":[74],"leverages":[75],"by":[79],"neural":[80],"networks,":[81],"thereby":[83],"enhances":[84],"both":[85],"efficiency":[87],"ability.":[90],"Moreover,":[91],"adaptive":[93],"k-nearest-neighbors":[94],"is":[95],"used":[96],"determining":[98],"volume":[100],"retrieved":[102],"further":[104],"improving":[105],"its":[106],"efficiency.":[107],"Our":[108],"evaluated":[110],"on":[111],"various":[112],"MuJoCo":[113],"tasks,":[116],"outperforms":[117],"model-free":[119],"baseline":[120],"latest":[123],"algorithms.":[127]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}