{"id":"https://openalex.org/W2964615009","doi":"https://doi.org/10.24963/ijcai.2019/505","title":"Sharing Experience in Multitask Reinforcement Learning","display_name":"Sharing Experience in Multitask Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2964615009","doi":"https://doi.org/10.24963/ijcai.2019/505","mag":"2964615009"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/505","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/505","pdf_url":"https://www.ijcai.org/proceedings/2019/0505.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/2019/0505.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053574580","display_name":"Tung-Long Vuong","orcid":null},"institutions":[{"id":"https://openalex.org/I177233841","display_name":"Vietnam National University, Hanoi","ror":"https://ror.org/02jmfj006","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Tung-Long Vuong","raw_affiliation_strings":["HMI Lab, UET, Vietnam National University, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"HMI Lab, UET, Vietnam National University, Hanoi, Vietnam","institution_ids":["https://openalex.org/I177233841"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046379131","display_name":"Do Van Nguyen","orcid":"https://orcid.org/0000-0002-9992-2974"},"institutions":[{"id":"https://openalex.org/I177233841","display_name":"Vietnam National University, Hanoi","ror":"https://ror.org/02jmfj006","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Do-Van Nguyen","raw_affiliation_strings":["HMI Lab, UET, Vietnam National University, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"HMI Lab, UET, Vietnam National University, Hanoi, Vietnam","institution_ids":["https://openalex.org/I177233841"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076195477","display_name":"Tai-Long Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I177233841","display_name":"Vietnam National University, Hanoi","ror":"https://ror.org/02jmfj006","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Tai-Long Nguyen","raw_affiliation_strings":["HMI Lab, UET, Vietnam National University, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"HMI Lab, UET, Vietnam National University, Hanoi, Vietnam","institution_ids":["https://openalex.org/I177233841"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085899126","display_name":"Cong-Minh Bui","orcid":null},"institutions":[{"id":"https://openalex.org/I177233841","display_name":"Vietnam National University, Hanoi","ror":"https://ror.org/02jmfj006","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Cong-Minh Bui","raw_affiliation_strings":["HMI Lab, UET, Vietnam National University, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"HMI Lab, UET, Vietnam National University, Hanoi, Vietnam","institution_ids":["https://openalex.org/I177233841"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005900412","display_name":"Hai-Dang Kieu","orcid":"https://orcid.org/0000-0001-6743-088X"},"institutions":[{"id":"https://openalex.org/I177233841","display_name":"Vietnam National University, Hanoi","ror":"https://ror.org/02jmfj006","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hai-Dang Kieu","raw_affiliation_strings":["HMI Lab, UET, Vietnam National University, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"HMI Lab, UET, Vietnam National University, Hanoi, Vietnam","institution_ids":["https://openalex.org/I177233841"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053935756","display_name":"Viet Cuong Ta","orcid":"https://orcid.org/0000-0001-8058-5915"},"institutions":[{"id":"https://openalex.org/I177233841","display_name":"Vietnam National University, Hanoi","ror":"https://ror.org/02jmfj006","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Viet-Cuong Ta","raw_affiliation_strings":["HMI Lab, UET, Vietnam National University, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"HMI Lab, UET, Vietnam National University, Hanoi, Vietnam","institution_ids":["https://openalex.org/I177233841"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109234378","display_name":"Quoc-Long Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I177233841","display_name":"Vietnam National University, Hanoi","ror":"https://ror.org/02jmfj006","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Quoc-Long Tran","raw_affiliation_strings":["HMI Lab, UET, Vietnam National University, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"HMI Lab, UET, Vietnam National University, Hanoi, Vietnam","institution_ids":["https://openalex.org/I177233841"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111595103","display_name":"Thanh-Ha Le","orcid":null},"institutions":[{"id":"https://openalex.org/I177233841","display_name":"Vietnam National University, Hanoi","ror":"https://ror.org/02jmfj006","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thanh-Ha Le","raw_affiliation_strings":["HMI Lab, UET, Vietnam National University, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"HMI Lab, UET, Vietnam National University, Hanoi, Vietnam","institution_ids":["https://openalex.org/I177233841"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5053574580"],"corresponding_institution_ids":["https://openalex.org/I177233841"],"apc_list":null,"apc_paid":null,"fwci":1.5896,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.87803364,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3642","last_page":"3648"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9937000274658203,"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"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.989300012588501,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8188432455062866},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7825390100479126},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7480195760726929},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.5556047558784485},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5530555248260498},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.49336329102516174},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.48755425214767456},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.48449060320854187},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4457705616950989},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.44216811656951904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3747493624687195},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3198595345020294},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09162572026252747},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08426746726036072}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8188432455062866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825390100479126},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7480195760726929},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5556047558784485},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5530555248260498},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.49336329102516174},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.48755425214767456},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.48449060320854187},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4457705616950989},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.44216811656951904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3747493624687195},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3198595345020294},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09162572026252747},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08426746726036072},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/505","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/505","pdf_url":"https://www.ijcai.org/proceedings/2019/0505.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.2019/505","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/505","pdf_url":"https://www.ijcai.org/proceedings/2019/0505.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":[],"awards":[{"id":"https://openalex.org/G3591598716","display_name":null,"funder_award_id":"FA2386","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320318019","display_name":"Asian Office of Aerospace Research and Development","ror":null},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964615009.pdf","grobid_xml":"https://content.openalex.org/works/W2964615009.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1575592356","https://openalex.org/W1771410628","https://openalex.org/W1981437899","https://openalex.org/W1995688924","https://openalex.org/W2106261932","https://openalex.org/W2143612262","https://openalex.org/W2145339207","https://openalex.org/W2163605009","https://openalex.org/W2169743339","https://openalex.org/W2173248099","https://openalex.org/W2174786457","https://openalex.org/W2175259684","https://openalex.org/W2294805292","https://openalex.org/W2553882142","https://openalex.org/W2735995851","https://openalex.org/W2736601468","https://openalex.org/W2739678353","https://openalex.org/W2785342287","https://openalex.org/W2949600457","https://openalex.org/W2963019567","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964200634","https://openalex.org/W2964262254","https://openalex.org/W4297669644","https://openalex.org/W4298174377","https://openalex.org/W4319988532"],"related_works":["https://openalex.org/W2948333011","https://openalex.org/W4386619269","https://openalex.org/W1942758450","https://openalex.org/W2994972936","https://openalex.org/W2922338626","https://openalex.org/W4303645333","https://openalex.org/W4312745891","https://openalex.org/W2108010283","https://openalex.org/W4221067497","https://openalex.org/W4285239401"],"abstract_inverted_index":{"In":[0,47,63],"multitask":[1],"reinforcement":[2],"learning,":[3],"tasks":[4,17,39,84],"often":[5],"have":[6],"sub-tasks":[7],"that":[8,79,110],"share":[9],"the":[10,15,21,28,36,41,73,104,114,117],"same":[11],"solution,":[12],"even":[13],"though":[14],"overall":[16],"are":[18,95],"different.":[19],"If":[20],"shared-portions":[22],"could":[23,31,44],"be":[24,32,45,81],"effectively":[25],"identified,":[26],"then":[27],"learning":[29,105,120],"process":[30],"improved":[33],"since":[34],"all":[35],"samples":[37],"between":[38,91],"in":[40],"shared":[42,82],"space":[43],"used.":[46],"this":[48],"paper,":[49],"we":[50],"propose":[51],"a":[52,65],"Sharing":[53],"Experience":[54],"Framework":[55],"(SEF)":[56],"for":[57],"simultaneously":[58],"training":[59],"of":[60,119],"multiple":[61],"tasks.":[62,92],"SEF,":[64],"confidence":[66],"sharing":[67,100],"agent":[68],"uses":[69],"task-specific":[70],"rewards":[71],"from":[72],"environment":[74],"to":[75,97,125],"identify":[76],"similar":[77],"parts":[78,88],"should":[80],"across":[83],"and":[85,116,122],"defines":[86],"those":[87],"as":[89],"shared-regions":[90,94],"The":[93,107],"expected":[96],"guide":[98],"task-policies":[99,127],"their":[101],"experience":[102],"during":[103],"process.":[106],"experiments":[108],"highlight":[109],"our":[111],"framework":[112],"improves":[113],"performance":[115],"stability":[118],"task-policies,":[121],"is":[123],"possible":[124],"help":[126],"avoid":[128],"local":[129],"optimums.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
