{"id":"https://openalex.org/W2965870268","doi":"https://doi.org/10.24963/ijcai.2019/589","title":"Experience Replay Optimization","display_name":"Experience Replay Optimization","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965870268","doi":"https://doi.org/10.24963/ijcai.2019/589","mag":"2965870268"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/589","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/589","pdf_url":"https://www.ijcai.org/proceedings/2019/0589.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0589.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058071176","display_name":"Daochen Zha","orcid":"https://orcid.org/0000-0002-6677-7504"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daochen Zha","raw_affiliation_strings":["Department of Computer Science and Engineering, Texas A&M University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Texas A&M University","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089183436","display_name":"Kwei-Herng Lai","orcid":"https://orcid.org/0000-0001-8933-7117"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kwei-Herng Lai","raw_affiliation_strings":["Department of Computer Science and Engineering, Texas A&M University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Texas A&M University","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071607114","display_name":"Kaixiong Zhou","orcid":"https://orcid.org/0000-0001-5226-8736"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaixiong Zhou","raw_affiliation_strings":["Department of Computer Science and Engineering, Texas A&M University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Texas A&M University","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068477431","display_name":"Xia Hu","orcid":"https://orcid.org/0000-0003-2234-3226"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xia Hu","raw_affiliation_strings":["Department of Computer Science and Engineering, Texas A&M University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Texas A&M University","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5058071176"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":7.0808,"has_fulltext":false,"cited_by_count":84,"citation_normalized_percentile":{"value":0.97554696,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4243","last_page":"4249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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/T13219","display_name":"Mind wandering and attention","score":0.9902999997138977,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8677657842636108},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.837801456451416},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5277488827705383},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.5239684581756592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3416043817996979},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3391014337539673},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.06893062591552734},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0629139244556427},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.05992355942726135}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8677657842636108},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.837801456451416},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5277488827705383},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.5239684581756592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3416043817996979},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3391014337539673},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.06893062591552734},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0629139244556427},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.05992355942726135},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/589","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/589","pdf_url":"https://www.ijcai.org/proceedings/2019/0589.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/589","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/589","pdf_url":"https://www.ijcai.org/proceedings/2019/0589.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2220043244","display_name":null,"funder_award_id":"IIS-1718840","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2364183095","display_name":null,"funder_award_id":"#IIS-1750074","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5913764691","display_name":null,"funder_award_id":"IIS-1750074","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6604742037","display_name":"CAREER: Human-Centric Big Network Embedding","funder_award_id":"1750074","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7013756359","display_name":null,"funder_award_id":"#IIS-1718840","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8766092123","display_name":"III: Small: Collaborative Research: A General Feature Learning Framework for Dynamic Attributed Networks","funder_award_id":"1718840","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965870268.pdf","grobid_xml":"https://content.openalex.org/works/W2965870268.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1172323223","https://openalex.org/W1595483645","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2604618034","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2772721022","https://openalex.org/W2792305967","https://openalex.org/W2803767077","https://openalex.org/W2892359699","https://openalex.org/W2952504784","https://openalex.org/W2963079702","https://openalex.org/W2963095800","https://openalex.org/W2963582482","https://openalex.org/W2963864421","https://openalex.org/W2964096423","https://openalex.org/W4214717370","https://openalex.org/W4254755460","https://openalex.org/W4289753142","https://openalex.org/W4298857966","https://openalex.org/W4300799055","https://openalex.org/W4302570325","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Experience":[0],"replay":[1,15,26,34,47,60,81,95,113,144],"enables":[2],"reinforcement":[3,152],"learning":[4,45,55,145,153],"agents":[5],"to":[6,49,101,117,146],"memorize":[7],"and":[8,64,66,93],"reuse":[9],"past":[10,27],"experiences,":[11],"just":[12],"as":[13],"humans":[14],"memories":[16],"for":[17],"the":[18,51,59,67,90,94,103,108,112,119,122,135,148],"situation":[19],"at":[20],"hand.":[21],"Contemporary":[22],"off-policy":[23,151],"algorithms":[24],"either":[25],"experiences":[28],"uniformly":[29],"or":[30],"utilize":[31],"a":[32,46,78],"rule-based":[33],"strategy,":[35],"which":[36,85],"may":[37],"be":[38],"sub-optimal.":[39],"In":[40],"this":[41],"work,":[42],"we":[43,76],"consider":[44],"policy":[48,114],"optimize":[50],"cumulative":[52,68,104],"reward.":[53],"Replay":[54],"is":[56,62,70,99,115],"challenging":[57],"because":[58],"memory":[61],"noisy":[63],"large,":[65],"reward":[69,105],"unstable.":[71],"To":[72],"address":[73],"these":[74],"issues,":[75],"propose":[77],"novel":[79],"experience":[80,143],"optimization":[82],"(ERO)":[83],"framework":[84],"alternately":[86],"updates":[87],"two":[88],"policies:":[89],"agent":[91,98,120],"policy,":[92],"policy.":[96],"The":[97,126],"updated":[100,116],"maximize":[102],"based":[106],"on":[107,129],"replayed":[109],"data,":[110],"while":[111],"provide":[118],"with":[121],"most":[123],"useful":[124],"experiences.":[125],"conducted":[127],"experiments":[128],"various":[130],"continuous":[131],"control":[132],"tasks":[133],"demonstrate":[134],"effectiveness":[136],"of":[137,150],"ERO,":[138],"empirically":[139],"showing":[140],"promise":[141],"in":[142],"improve":[147],"performance":[149],"algorithms.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}