{"id":"https://openalex.org/W2795650232","doi":"https://doi.org/10.5220/0007308000730082","title":"BOOK: Storing Algorithm-Invariant Episodes for Deep Reinforcement Learning","display_name":"BOOK: Storing Algorithm-Invariant Episodes for Deep Reinforcement Learning","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2795650232","doi":"https://doi.org/10.5220/0007308000730082","mag":"2795650232"},"language":"en","primary_location":{"id":"doi:10.5220/0007308000730082","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0007308000730082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods","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/A5112998078","display_name":"Simyung Chang","orcid":"https://orcid.org/0000-0001-7750-191X"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Simyung Chang","raw_affiliation_strings":["Seoul National University, Seoul, Korea, Samsung Electronics, Suwon and Korea, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea, Samsung Electronics, Suwon and Korea, --- Select a Country ---","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073731761","display_name":"Youngjoon Yoo","orcid":"https://orcid.org/0000-0001-8084-5422"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"YoungJoon Yoo","raw_affiliation_strings":["Clova AI Research, NAVER Corp, Seongnam and Korea, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Clova AI Research, NAVER Corp, Seongnam and Korea, --- Select a Country ---","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062575074","display_name":"Jaeseok Choi","orcid":"https://orcid.org/0000-0002-9636-3484"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeseok Choi","raw_affiliation_strings":["Seoul National University, Seoul and Korea, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul and Korea, --- Select a Country ---","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084897975","display_name":"Nojun Kwak","orcid":"https://orcid.org/0000-0002-1792-0327"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nojun Kwak","raw_affiliation_strings":["Seoul National University, Seoul and Korea, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul and Korea, --- Select a Country ---","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112998078"],"corresponding_institution_ids":["https://openalex.org/I139264467","https://openalex.org/I2250650973"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0042937,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"82"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9865000247955322,"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":0.9865000247955322,"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":0.9811999797821045,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9297000169754028,"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":0.8089554309844971},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7728081941604614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6250389814376831},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5826930403709412},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5151166319847107},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.48317304253578186},{"id":"https://openalex.org/keywords/container","display_name":"Container (type theory)","score":0.4559749364852905},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4236201047897339},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4195462465286255},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07894596457481384}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8089554309844971},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7728081941604614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6250389814376831},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5826930403709412},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5151166319847107},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48317304253578186},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.4559749364852905},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4236201047897339},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4195462465286255},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07894596457481384},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0007308000730082","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0007308000730082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},{"id":"pmh:oai:s-space.snu.ac.kr:10371/206300","is_oa":false,"landing_page_url":"https://hdl.handle.net/10371/206300","pdf_url":null,"source":{"id":"https://openalex.org/S4306401345","display_name":"Seoul National University Open Repository (Seoul National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139264467","host_organization_name":"Seoul National University","host_organization_lineage":["https://openalex.org/I139264467"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2665305151"],"abstract_inverted_index":{"We":[0,156],"introduce":[1],"a":[2,16,24,33,93,117,132,153,177],"novel":[3],"method":[4,163],"to":[5,19,75,80,127,166],"train":[6],"agents":[7,91,130,188],"of":[8,22,32,121,179],"reinforcement":[9],"learning":[10,56,72,85,175],"(RL)":[11],"by":[12,39,96,174],"sharing":[13],"knowledge":[14,195],"in":[15,29,92,131,152],"way":[17],"similar":[18],"the":[20,30,36,45,58,64,67,77,99,107,141,171,193],"concept":[21],"using":[23],"book.":[25],"The":[26],"recorded":[27],"information":[28,88],"form":[31],"book":[34,84],"is":[35],"main":[37],"means":[38],"which":[40,124,183],"humans":[41],"learn":[42,191],"knowledge.":[43],"Nevertheless,":[44],"conventional":[46,172],"deep":[47,186],"RL":[48,129,187],"methods":[49,173],"have":[50],"mainly":[51],"focused":[52],"either":[53],"on":[54,70],"experiential":[55],"where":[57],"agent":[59],"learns":[60,164],"through":[61,192],"interactions":[62],"with":[63],"environment":[65],"from":[66,196],"start":[68],"or":[69],"imitation":[71],"that":[73,185],"tries":[74],"mimic":[76],"teacher.":[78],"Contrary":[79],"these,":[81],"our":[82],"proposed":[83],"shares":[86],"key":[87],"among":[89],"different":[90],"book-like":[94],"manner":[95],"delving":[97],"into":[98,116],"following":[100],"two":[101],"characteristic":[102],"features:":[103],"(1)":[104],"By":[105,136],"defining":[106,137],"linguistic":[108],"function,":[109],"input":[110],"states":[111],"can":[112,147,189],"be":[113,148],"clustered":[114],"semantically":[115],"relatively":[118],"small":[119,154],"number":[120],"core":[122,145,180],"clusters,":[123],"are":[125],"forwarded":[126],"other":[128,197],"prescribed":[133],"manner.":[134],"(2)":[135],"state":[138],"priorities":[139],"and":[140,150],"contents":[142],"for":[143],"recording,":[144],"experiences":[146],"selected":[149],"stored":[151],"container.":[155],"call":[157],"this":[158],"container":[159],"as":[160],"'BOOK'.":[161],"Our":[162],"hundreds":[165],"thousand":[167],"times":[168],"faster":[169],"than":[170],"only":[176],"handful":[178],"cluster":[181],"information,":[182],"shows":[184],"effectively":[190],"shared":[194],"agents.":[198]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}