{"id":"https://openalex.org/W4402352007","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651193","title":"Remember the Past for Better Future: Memory-Augmented Offline RL","display_name":"Remember the Past for Better Future: Memory-Augmented Offline RL","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352007","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651193"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651193","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5100333727","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0002-5141-6992"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["University of Science and Technology of China,EEIS Department"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,EEIS Department","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025046910","display_name":"Yaodong Yang","orcid":"https://orcid.org/0000-0002-1707-0633"},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yaodong Yang","raw_affiliation_strings":["Peking University,Institute for AI"],"affiliations":[{"raw_affiliation_string":"Peking University,Institute for AI","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056177421","display_name":"Zhenbo Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137491","display_name":"National Science Center","ror":"https://ror.org/03ha2q922","country_code":"PL","type":"funder","lineage":["https://openalex.org/I4210137491"]},{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Zhenbo Lu","raw_affiliation_strings":["Institute of Artificial Intelligence,Hefei Comprehensive National Science Center"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence,Hefei Comprehensive National Science Center","institution_ids":["https://openalex.org/I4210137491","https://openalex.org/I4210105595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["University of Science and Technology of China,EEIS Department"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,EEIS Department","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["University of Science and Technology of China,EEIS Department"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,EEIS Department","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100333727"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66488266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"117","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":0.9990000128746033,"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":0.9990000128746033,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.974399983882904,"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":0.741226315498352}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741226315498352}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651193","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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":66,"referenced_works":["https://openalex.org/W2009292571","https://openalex.org/W2078047435","https://openalex.org/W2107726111","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2171273397","https://openalex.org/W2416094133","https://openalex.org/W2436711315","https://openalex.org/W2736601468","https://openalex.org/W2789500754","https://openalex.org/W2991355586","https://openalex.org/W2996037775","https://openalex.org/W2998702515","https://openalex.org/W3016525976","https://openalex.org/W3025606523","https://openalex.org/W3027879771","https://openalex.org/W3028766998","https://openalex.org/W3033324992","https://openalex.org/W3093096978","https://openalex.org/W3108984808","https://openalex.org/W3134294674","https://openalex.org/W3172360140","https://openalex.org/W3189480080","https://openalex.org/W3201700917","https://openalex.org/W4221158443","https://openalex.org/W4225110331","https://openalex.org/W4282813201","https://openalex.org/W4282938007","https://openalex.org/W4288319859","https://openalex.org/W4289376774","https://openalex.org/W4293112425","https://openalex.org/W4298857966","https://openalex.org/W4306295204","https://openalex.org/W4385245566","https://openalex.org/W4385488842","https://openalex.org/W6637967152","https://openalex.org/W6718359804","https://openalex.org/W6734330393","https://openalex.org/W6741002519","https://openalex.org/W6754857033","https://openalex.org/W6757469721","https://openalex.org/W6764053384","https://openalex.org/W6771270455","https://openalex.org/W6772005887","https://openalex.org/W6772744401","https://openalex.org/W6776601253","https://openalex.org/W6777091672","https://openalex.org/W6777615688","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6779857854","https://openalex.org/W6784531327","https://openalex.org/W6791277150","https://openalex.org/W6791413555","https://openalex.org/W6796589144","https://openalex.org/W6802659552","https://openalex.org/W6810030924","https://openalex.org/W6810265657","https://openalex.org/W6810277566","https://openalex.org/W6838356327","https://openalex.org/W6838845867","https://openalex.org/W6842830264","https://openalex.org/W6845414265","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"As":[0],"a":[1,61,69],"foundation":[2],"of":[3,40,49,97,112,127],"human":[4,14],"intelligence,":[5],"memory":[6,41,50,63],"has":[7],"been":[8],"found":[9],"to":[10,72,81,108,125],"be":[11],"critical":[12],"for":[13,94],"attention":[15],"and":[16,67],"decision":[17],"making.":[18],"However,":[19],"it":[20],"is":[21,65,79,122],"usually":[22],"underutilized":[23],"in":[24,42,86,135],"current":[25],"reinforcement":[26,57],"learning":[27,58],"literature,":[28],"primarily":[29],"serving":[30],"as":[31],"training":[32,111],"data.":[33],"Researchers":[34],"have":[35],"rarely":[36],"noticed":[37],"the":[38,47,55,95,110,136],"use":[39],"other":[43],"perspectives.":[44],"To":[45],"explore":[46],"potential":[48],"architectures,":[51],"we":[52],"focus":[53],"on":[54],"offline":[56,128],"setting,":[59],"where":[60],"fixed":[62],"buffer":[64],"provided,":[66],"propose":[68],"novel":[70],"framework":[71],"exploit":[73],"it.":[74],"Specifically,":[75],"an":[76],"attention-based":[77],"architecture":[78],"designed":[80],"adaptively":[82],"utilize":[83],"past":[84],"memories":[85],"learned":[87],"environment":[88,102],"dynamic":[89,103],"models,":[90],"providing":[91],"reliable":[92],"references":[93],"estimation":[96],"future":[98],"states.":[99],"Such":[100],"memory-augmented":[101],"models":[104],"are":[105],"then":[106],"applied":[107],"boost":[109],"RL":[113,130],"policies.":[114],"While":[115],"demonstrating":[116],"superior":[117],"empirical":[118],"performance,":[119],"our":[120],"method":[121],"highly":[123],"extendable":[124],"most":[126],"model-based":[129],"algorithms":[131],"without":[132],"any":[133],"change":[134],"pipelines":[137],"or":[138],"theoretical":[139],"conclusions.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}