{"id":"https://openalex.org/W2966033451","doi":"https://doi.org/10.24963/ijcai.2019/618","title":"Reinforcement Learning Experience Reuse with Policy Residual Representation","display_name":"Reinforcement Learning Experience Reuse with Policy Residual Representation","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2966033451","doi":"https://doi.org/10.24963/ijcai.2019/618","mag":"2966033451"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/618","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/618","pdf_url":"https://www.ijcai.org/proceedings/2019/0618.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0618.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055893718","display_name":"Wen-Ji Zhou","orcid":"https://orcid.org/0000-0002-5116-5679"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"WenJi Zhou","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342263","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-1732-9545"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103121632","display_name":"Yingfeng Chen","orcid":"https://orcid.org/0000-0002-9747-5947"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingfeng Chen","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006918020","display_name":"Kai Guan","orcid":"https://orcid.org/0000-0003-3582-3464"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Guan","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042252596","display_name":"Tangjie Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tangjie Lv","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022008180","display_name":"Changjie Fan","orcid":"https://orcid.org/0000-0001-5420-0516"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changjie Fan","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100621138","display_name":"Zhi\u2010Hua Zhou","orcid":"https://orcid.org/0000-0003-0746-1494"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi-Hua Zhou","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4447","last_page":"4453"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.989799976348877,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9671000242233276,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8528962135314941},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.8230106234550476},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7926359176635742},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6837189793586731},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5950702428817749},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5616569519042969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5321955680847168},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5262942910194397},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.49092036485671997},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.48334214091300964},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4815824031829834},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4781647324562073},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39727532863616943},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0852944552898407},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08389908075332642}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8528962135314941},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.8230106234550476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7926359176635742},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6837189793586731},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5950702428817749},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5616569519042969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5321955680847168},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5262942910194397},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.49092036485671997},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.48334214091300964},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4815824031829834},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4781647324562073},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39727532863616943},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0852944552898407},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08389908075332642},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/618","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/618","pdf_url":"https://www.ijcai.org/proceedings/2019/0618.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.2019/618","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/618","pdf_url":"https://www.ijcai.org/proceedings/2019/0618.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/G5469316478","display_name":null,"funder_award_id":"61876077","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G697213553","display_name":null,"funder_award_id":"61751306","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2966033451.pdf","grobid_xml":"https://content.openalex.org/works/W2966033451.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W110451278","https://openalex.org/W1771410628","https://openalex.org/W2007043381","https://openalex.org/W2145339207","https://openalex.org/W2151210636","https://openalex.org/W2155007355","https://openalex.org/W2158782408","https://openalex.org/W2257979135","https://openalex.org/W2412094331","https://openalex.org/W2440926996","https://openalex.org/W2604763608","https://openalex.org/W2736601468","https://openalex.org/W2788904251","https://openalex.org/W2789543555","https://openalex.org/W2808577099","https://openalex.org/W2808578944","https://openalex.org/W2963161674","https://openalex.org/W2963864421","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W2999756192","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746","https://openalex.org/W2975817033","https://openalex.org/W4382701072"],"abstract_inverted_index":{"Experience":[0],"reuse":[1,160],"is":[2,13,17,75],"key":[3],"to":[4,93,158],"sample-efficient":[5],"reinforcement":[6],"learning.":[7,126],"One":[8],"of":[9,30,71,80,96,121,136,161],"the":[10,15,22,28,35,58,97,100,104,125,130,154],"critical":[11],"issues":[12],"how":[14],"experience":[16,23,49,105,122,162],"represented":[18],"and":[19,34,67,143,163],"stored.":[20],"Previously,":[21],"can":[24,65,117],"be":[25],"stored":[26],"in":[27,89,106,146],"forms":[29],"features,":[31],"individual":[32],"models,":[33],"average":[36],"model,":[37],"each":[38,90],"lying":[39],"at":[40],"a":[41,78,83,87,94,107,113,134,147],"different":[42,119],"granularity.":[43],"However,":[44],"new":[45,114],"tasks":[46,81,145],"may":[47],"require":[48],"across":[50],"multiple":[51,69],"granularities.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"propose":[57],"policy":[59],"residual":[60],"representation":[61],"(PRR)":[62],"network,":[63],"which":[64],"extract":[66],"store":[68],"levels":[70,120],"experience.":[72],"PRR":[73,101,116,131,155],"network":[74,102,132,156],"trained":[76],"on":[77,112,133],"set":[79,135],"with":[82,129],"multi-level":[84],"architecture,":[85],"where":[86],"module":[88],"level":[91],"corresponds":[92],"subset":[95],"tasks.":[98],"Therefore,":[99],"represents":[103],"spectrum-like":[108],"way.":[109],"When":[110],"training":[111],"task,":[115],"provide":[118],"for":[123],"accelerating":[124],"We":[127],"experiment":[128],"grid":[137],"world":[138],"navigation":[139],"tasks,":[140,142],"locomotion":[141],"fighting":[144],"video":[148],"game.":[149],"The":[150],"results":[151],"show":[152],"that":[153],"leads":[157],"better":[159],"thus":[164],"outperforms":[165],"some":[166],"state-of-the-art":[167],"approaches.":[168]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}