{"id":"https://openalex.org/W2791869553","doi":"https://doi.org/10.1109/tsmc.2018.2800040","title":"Guided Policy Search for Sequential Multitask Learning","display_name":"Guided Policy Search for Sequential Multitask Learning","publication_year":2018,"publication_date":"2018-02-19","ids":{"openalex":"https://openalex.org/W2791869553","doi":"https://doi.org/10.1109/tsmc.2018.2800040","mag":"2791869553"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2018.2800040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2018.2800040","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://napier-surface.worktribe.com/1450377/1/Guided%20Policy%20Search%20for%20Sequential%20Multitask%20Learning","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056039500","display_name":"Fangzhou Xiong","orcid":"https://orcid.org/0000-0002-2592-4096"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fangzhou Xiong","raw_affiliation_strings":["School of Computer and Control, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Control, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101979437","display_name":"Biao Sun","orcid":"https://orcid.org/0000-0001-6677-8673"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Sun","raw_affiliation_strings":["School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007963696","display_name":"Xu Yang","orcid":"https://orcid.org/0000-0003-0553-4581"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Yang","raw_affiliation_strings":["School of Computer and Control, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Control, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026688050","display_name":"Hong Qiao","orcid":"https://orcid.org/0000-0001-6384-3687"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Qiao","raw_affiliation_strings":["Cloud Computing Center, Chinese Academy of Sciences, Dongguan, China"],"affiliations":[{"raw_affiliation_string":"Cloud Computing Center, Chinese Academy of Sciences, Dongguan, China","institution_ids":["https://openalex.org/I4210144487","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026022035","display_name":"Kaizhu Huang","orcid":"https://orcid.org/0000-0002-3034-9639"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaizhu Huang","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Xi\u2019an Jiaotong-Liverpool University, Suzhou, China","Department of Electrical and Electronic Engineering, Xi'an Jiaotong-Liverpool University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Xi\u2019an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Xi'an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062211930","display_name":"Amir Hussain","orcid":"https://orcid.org/0000-0002-8080-082X"},"institutions":[{"id":"https://openalex.org/I12093191","display_name":"University of Stirling","ror":"https://ror.org/045wgfr59","country_code":"GB","type":"education","lineage":["https://openalex.org/I12093191"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Amir Hussain","raw_affiliation_strings":["Division of Computing Science and Maths, School of Natural Sciences, University of Stirling, Stirling, U.K"],"affiliations":[{"raw_affiliation_string":"Division of Computing Science and Maths, School of Natural Sciences, University of Stirling, Stirling, U.K","institution_ids":["https://openalex.org/I12093191"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100434504","display_name":"Zhiyong Liu","orcid":"https://orcid.org/0000-0003-2148-1846"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Liu","raw_affiliation_strings":["Cloud Computing Center, Chinese Academy of Sciences, Dongguan, China"],"affiliations":[{"raw_affiliation_string":"Cloud Computing Center, Chinese Academy of Sciences, Dongguan, China","institution_ids":["https://openalex.org/I4210144487","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5056039500"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":5.4155,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.96459668,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"49","issue":"1","first_page":"216","last_page":"226"},"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":0.9929999709129333,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/computer-science","display_name":"Computer science","score":0.6734658479690552},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6561493873596191},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.608278214931488},{"id":"https://openalex.org/keywords/global-positioning-system","display_name":"Global Positioning System","score":0.6066766381263733},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5980059504508972},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4761612117290497},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4268152117729187},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.41987723112106323},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.4171847701072693},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4165528118610382},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.274898886680603},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14129933714866638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6734658479690552},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6561493873596191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.608278214931488},{"id":"https://openalex.org/C60229501","wikidata":"https://www.wikidata.org/wiki/Q18822","display_name":"Global Positioning System","level":2,"score":0.6066766381263733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5980059504508972},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4761612117290497},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4268152117729187},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.41987723112106323},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.4171847701072693},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4165528118610382},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.274898886680603},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14129933714866638},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tsmc.2018.2800040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2018.2800040","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"},{"id":"pmh:oai:dspace.stir.ac.uk:1893/27076","is_oa":false,"landing_page_url":"http://hdl.handle.net/1893/27076","pdf_url":null,"source":{"id":"https://openalex.org/S4306400268","display_name":"Stirling Online Research Repository (University of Stirling)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I12093191","host_organization_name":"University of Stirling","host_organization_lineage":["https://openalex.org/I12093191"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:napier-surface.worktribe.com:1450377","is_oa":true,"landing_page_url":"https://napier-surface.worktribe.com/1450377/1/Guided%20Policy%20Search%20for%20Sequential%20Multitask%20Learning","pdf_url":null,"source":{"id":"https://openalex.org/S4306400544","display_name":"Research Output (Edinburgh Napier University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I251738","host_organization_name":"Edinburgh Napier University","host_organization_lineage":["https://openalex.org/I251738"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:repository@napier.ac.uk:1450377","is_oa":true,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/1450377","pdf_url":null,"source":{"id":"https://openalex.org/S4306402591","display_name":"Edinburgh Napier Research Repository (Edinburgh Napier University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I251738","host_organization_name":"Edinburgh Napier University","host_organization_lineage":["https://openalex.org/I251738"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:napier-surface.worktribe.com:1450377","is_oa":true,"landing_page_url":"https://napier-surface.worktribe.com/1450377/1/Guided%20Policy%20Search%20for%20Sequential%20Multitask%20Learning","pdf_url":null,"source":{"id":"https://openalex.org/S4306400544","display_name":"Research Output (Edinburgh Napier University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I251738","host_organization_name":"Edinburgh Napier University","host_organization_lineage":["https://openalex.org/I251738"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1597499265","display_name":null,"funder_award_id":"61702516","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1748546653","display_name":null,"funder_award_id":"2015BAK35B00","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G3214453966","display_name":null,"funder_award_id":"61627808","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4097937278","display_name":"Towards visually-driven speech enhancement for cognitively-inspired multi-modal hearing-aid devices (AV-COGHEAR)","funder_award_id":"EP/M026981/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4178453836","display_name":null,"funder_award_id":"61503383","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4769349813","display_name":null,"funder_award_id":"EP/M026981/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5341411597","display_name":null,"funder_award_id":"2016B090910001","funder_id":"https://openalex.org/F4320324202","funder_display_name":"Guangdong Science and Technology Department"},{"id":"https://openalex.org/G5652064144","display_name":null,"funder_award_id":"61210009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5743527310","display_name":null,"funder_award_id":"U1613213","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5992429082","display_name":null,"funder_award_id":"61473236","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6130823433","display_name":null,"funder_award_id":"91648205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6840412308","display_name":null,"funder_award_id":"61375005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G687224823","display_name":null,"funder_award_id":"EP/I009310/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7677743178","display_name":null,"funder_award_id":"2015BAK35B01","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"},{"id":"https://openalex.org/F4320324202","display_name":"Guangdong Science and Technology Department","ror":"https://ror.org/00tjzgn92"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1512387364","https://openalex.org/W1519626139","https://openalex.org/W1771410628","https://openalex.org/W1844261860","https://openalex.org/W1977655452","https://openalex.org/W1982262386","https://openalex.org/W2012587148","https://openalex.org/W2031727428","https://openalex.org/W2051620263","https://openalex.org/W2098284983","https://openalex.org/W2100235553","https://openalex.org/W2101493843","https://openalex.org/W2104733512","https://openalex.org/W2106008664","https://openalex.org/W2113913482","https://openalex.org/W2116453957","https://openalex.org/W2121103318","https://openalex.org/W2121863487","https://openalex.org/W2126204609","https://openalex.org/W2155007355","https://openalex.org/W2158782408","https://openalex.org/W2182506181","https://openalex.org/W2408432900","https://openalex.org/W2473930607","https://openalex.org/W2493077727","https://openalex.org/W2528760429","https://openalex.org/W2529601334","https://openalex.org/W2560414840","https://openalex.org/W2560647685","https://openalex.org/W2613321912","https://openalex.org/W2761941767","https://openalex.org/W2963630259","https://openalex.org/W2963864421","https://openalex.org/W2964161785","https://openalex.org/W2964309400","https://openalex.org/W3011120880","https://openalex.org/W3021931813","https://openalex.org/W4205513846","https://openalex.org/W4214717370","https://openalex.org/W4253978526","https://openalex.org/W6630579473","https://openalex.org/W6631089601","https://openalex.org/W6638018090","https://openalex.org/W6639024717","https://openalex.org/W6674909112","https://openalex.org/W6675999342","https://openalex.org/W6676004469","https://openalex.org/W6678367057","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6685839705","https://openalex.org/W6714150371","https://openalex.org/W6720711607","https://openalex.org/W6745125137","https://openalex.org/W6765478815","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W4289718052","https://openalex.org/W2164121020","https://openalex.org/W2145559838","https://openalex.org/W2905319430","https://openalex.org/W3116498279","https://openalex.org/W4287549553","https://openalex.org/W4310285384","https://openalex.org/W3183027292","https://openalex.org/W4248896073","https://openalex.org/W2974871044"],"abstract_inverted_index":{"Policy":[0],"search":[1,37],"in":[2,15,60,69,155],"reinforcement":[3],"learning":[4,72,94,158],"(RL)":[5],"is":[6,39,75,99,119,135,151,203],"a":[7,123,206],"practical":[8],"approach":[9,118],"to":[10,77,137,153,178,191],"interact":[11],"directly":[12],"with":[13,21],"environments":[14],"parameter":[16],"spaces,":[17],"that":[18],"often":[19],"deal":[20],"dilemmas":[22],"of":[23,41,45,92],"local":[24,56],"optima":[25],"and":[26,128,160,169,194,213],"real-time":[27,103,211],"sample":[28],"collection.":[29],"A":[30],"promising":[31],"algorithm,":[32,146],"known":[33],"as":[34,205],"guided":[35],"policy":[36,163],"(GPS),":[38],"capable":[40],"handling":[42,183],"the":[43,64,90,93,116,174,192,200,210],"challenge":[44],"training":[46,80,84,106,186],"samples":[47,85,107],"using":[48],"trajectory-centric":[49],"methods.":[50],"It":[51],"can":[52,110],"also":[53],"provide":[54],"asymptotic":[55],"convergence":[57],"guarantees.":[58],"However,":[59],"its":[61,78],"current":[62],"form,":[63],"GPS":[65,117,196],"algorithm":[66,202],"cannot":[67],"operate":[68,154],"sequential":[70,148,156],"multitask":[71,149,157],"scenarios.":[73],"This":[74],"due":[76],"batch-style":[79],"requirement,":[81],"where":[82,105],"all":[83],"are":[86],"collectively":[87],"provided":[88],"at":[89],"start":[91],"process.":[95],"The":[96,144],"algorithm\u2019s":[97],"adaptation":[98],"thus":[100],"hindered":[101],"for":[102,182,209],"applications,":[104],"or":[108],"tasks":[109],"arrive":[111],"randomly.":[112],"In":[113,198],"this":[114],"paper,":[115],"reformulated,":[120],"by":[121],"adapting":[122],"recently":[124],"proposed,":[125],"lifelong-learning":[126],"method,":[127],"elastic":[129],"weight":[130],"consolidation.":[131],"Specifically,":[132],"Fisher":[133],"information":[134],"incorporated":[136],"impart":[138],"knowledge":[139],"from":[140],"previously":[141],"learned":[142],"tasks.":[143],"proposed":[145,201],"termed":[147],"learning-GPS,":[150],"able":[152],"settings":[159],"ensuring":[161],"continuous":[162],"learning,":[164],"without":[165],"catastrophic":[166],"forgetting.":[167],"Pendulum":[168],"robotic":[170],"manipulation":[171],"experiments":[172],"demonstrate":[173],"new":[175,207],"algorithms":[176],"efficacy":[177],"learn":[179],"control":[180],"policies":[181],"sequentially":[184],"arriving":[185],"samples,":[187],"delivering":[188],"comparable":[189],"performance":[190],"traditional,":[193],"batch-based":[195],"algorithm.":[197],"conclusion,":[199],"posited":[204],"benchmark":[208],"RL":[212],"robotics":[214],"research":[215],"community.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
