{"id":"https://openalex.org/W3034815680","doi":"https://doi.org/10.24963/ijcai.2020/428","title":"Efficient Deep Reinforcement Learning via Adaptive Policy Transfer","display_name":"Efficient Deep Reinforcement Learning via Adaptive Policy Transfer","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3034815680","doi":"https://doi.org/10.24963/ijcai.2020/428","mag":"3034815680"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/428","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/428","pdf_url":"https://www.ijcai.org/proceedings/2020/0428.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0428.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101619771","display_name":"Tianpei Yang","orcid":"https://orcid.org/0000-0002-5497-7146"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]},{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN","SE"],"is_corresponding":true,"raw_author_name":"Tianpei Yang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University","Noah's Ark Lab, Huawei","College of Intelligence and Computing, Tianjin University; Noah's Ark Lab, Huawei"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University; Noah's Ark Lab, Huawei","institution_ids":["https://openalex.org/I4210159102","https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047509839","display_name":"Jianye Hao","orcid":"https://orcid.org/0000-0002-0422-8235"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["CN","SE"],"is_corresponding":false,"raw_author_name":"Jianye Hao","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University","Noah's Ark Lab, Huawei","Tianjin Key Lab of Machine Learning"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Tianjin Key Lab of Machine Learning","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005604730","display_name":"Zhaopeng Meng","orcid":"https://orcid.org/0000-0001-6019-5952"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaopeng Meng","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035138959","display_name":"Zongzhang Zhang","orcid":"https://orcid.org/0000-0002-9238-4747"},"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":"Zongzhang Zhang","raw_affiliation_strings":["Nanjing University","(Nanjing University)"],"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"(Nanjing University)","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104264364","display_name":"Yujing Hu","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":"Yujing Hu","raw_affiliation_strings":["Fuxi AI Lab in Netease"],"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab in Netease","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065987766","display_name":"Yingfeng Chen","orcid":"https://orcid.org/0000-0002-7995-2113"},"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":["Fuxi AI Lab in Netease"],"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab in Netease","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":["Fuxi AI Lab in Netease"],"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab in Netease","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082417441","display_name":"Weixun Wang","orcid":"https://orcid.org/0000-0002-2727-8948"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixun Wang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036527488","display_name":"Wulong Liu","orcid":"https://orcid.org/0000-0003-2901-1523"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Wulong Liu","raw_affiliation_strings":["Noah's Ark Lab, Huawei"],"affiliations":[{"raw_affiliation_string":"Noah's Ark Lab, Huawei","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641626","display_name":"Zhaodong Wang","orcid":"https://orcid.org/0000-0003-3112-077X"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaodong Wang","raw_affiliation_strings":["Washington State University","washington state university"],"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]},{"raw_affiliation_string":"washington state university","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084343474","display_name":"Jiajie Peng","orcid":"https://orcid.org/0000-0002-3857-7927"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajie Peng","raw_affiliation_strings":["Tianjin University"],"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5101619771"],"corresponding_institution_ids":["https://openalex.org/I162868743","https://openalex.org/I4210159102"],"apc_list":null,"apc_paid":null,"fwci":2.7184,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.92127359,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3094","last_page":"3100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9273999929428101,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.899911642074585},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8436156511306763},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.7660945653915405},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6859146952629089},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.6853739023208618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5716631412506104},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.5421522259712219},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46665072441101074},{"id":"https://openalex.org/keywords/policy-transfer","display_name":"Policy transfer","score":0.4493105113506317},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4148636758327484},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.13705995678901672},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09780994057655334},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.056418538093566895}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.899911642074585},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8436156511306763},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7660945653915405},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6859146952629089},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.6853739023208618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5716631412506104},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.5421522259712219},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46665072441101074},{"id":"https://openalex.org/C2776731479","wikidata":"https://www.wikidata.org/wiki/Q15142682","display_name":"Policy transfer","level":2,"score":0.4493105113506317},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4148636758327484},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.13705995678901672},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09780994057655334},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.056418538093566895},{"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/C3116431","wikidata":"https://www.wikidata.org/wiki/Q31728","display_name":"Public administration","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/428","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/428","pdf_url":"https://www.ijcai.org/proceedings/2020/0428.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/428","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/428","pdf_url":"https://www.ijcai.org/proceedings/2020/0428.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1063510118","display_name":null,"funder_award_id":"6170236","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2702356746","display_name":null,"funder_award_id":"61702","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3091702697","display_name":null,"funder_award_id":"61876119","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3319537635","display_name":null,"funder_award_id":"2018143","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5854786607","display_name":null,"funder_award_id":"Tianjin","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8921145797","display_name":null,"funder_award_id":"U1836214","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8955107213","display_name":null,"funder_award_id":"Major","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034815680.pdf","grobid_xml":"https://content.openalex.org/works/W3034815680.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2031727428","https://openalex.org/W2109910161","https://openalex.org/W2113953866","https://openalex.org/W2133458291","https://openalex.org/W2145339207","https://openalex.org/W2153874061","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2260756217","https://openalex.org/W2464736835","https://openalex.org/W2605369401","https://openalex.org/W2619137770","https://openalex.org/W2730602911","https://openalex.org/W2736601468","https://openalex.org/W2760355785","https://openalex.org/W2781585732","https://openalex.org/W2807238303","https://openalex.org/W2963864421","https://openalex.org/W2963946410","https://openalex.org/W2964043796","https://openalex.org/W2964227312","https://openalex.org/W4214717370","https://openalex.org/W4298845604","https://openalex.org/W4394662461","https://openalex.org/W6679518283","https://openalex.org/W6803771590","https://openalex.org/W6831247279"],"related_works":["https://openalex.org/W3095475970","https://openalex.org/W3017796982","https://openalex.org/W2027342354","https://openalex.org/W2906330542","https://openalex.org/W4390665401","https://openalex.org/W2142370952","https://openalex.org/W4393003728","https://openalex.org/W2035231162","https://openalex.org/W2998101326","https://openalex.org/W2299614762"],"abstract_inverted_index":{"Transfer":[0,75],"learning":[1,112,140],"has":[2],"shown":[3],"great":[4],"potential":[5],"to":[6,39,45,94,102],"accelerate":[7],"Reinforcement":[8],"Learning":[9],"(RL)":[10],"by":[11,28,51,78,105],"leveraging":[12],"prior":[13],"knowledge":[14,27,54],"from":[15,55],"past":[16],"learned":[17],"policies":[18,38,58],"of":[19,81,139],"relevant":[20],"tasks.":[21],"Existing":[22],"approaches":[23],"either":[24],"transfer":[25,108,135],"previous":[26],"explicitly":[29,60],"computing":[30],"similarities":[31,63],"between":[32],"tasks":[33],"or":[34],"select":[35],"appropriate":[36,56],"source":[37,57,89],"provide":[40],"guided":[41],"explorations.":[42],"However,":[43],"how":[44],"directly":[46],"optimize":[47],"the":[48,62,92,97],"target":[49,98],"policy":[50,90,99,134],"alternatively":[52],"utilizing":[53],"without":[59],"measuring":[61],"is":[64,91],"currently":[65],"missing.":[66],"In":[67],"this":[68,82],"paper,":[69],"we":[70],"propose":[71],"a":[72],"novel":[73],"Policy":[74],"Framework":[76],"(PTF)":[77],"taking":[79],"advantage":[80],"idea.":[83],"PTF":[84,114],"learns":[85],"when":[86,101],"and":[87,100,123,131,142,148],"which":[88],"best":[93],"reuse":[95],"for":[96],"terminate":[103],"it":[104,127],"modeling":[106],"multi-policy":[107],"as":[109],"an":[110],"option":[111],"problem.":[113],"can":[115],"be":[116],"easily":[117],"combined":[118],"with":[119],"existing":[120],"DRL":[121],"methods":[122,136],"experimental":[124],"results":[125],"show":[126],"significantly":[128],"accelerates":[129],"RL":[130],"surpasses":[132],"state-of-the-art":[133],"in":[137,145],"terms":[138],"efficiency":[141],"final":[143],"performance":[144],"both":[146],"discrete":[147],"continuous":[149],"action":[150],"spaces.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}