{"id":"https://openalex.org/W2900831917","doi":"https://doi.org/10.1109/tii.2018.2881266","title":"Multitask Policy Adversarial Learning for Human-Level Control With Large State Spaces","display_name":"Multitask Policy Adversarial Learning for Human-Level Control With Large State Spaces","publication_year":2018,"publication_date":"2018-11-14","ids":{"openalex":"https://openalex.org/W2900831917","doi":"https://doi.org/10.1109/tii.2018.2881266","mag":"2900831917"},"language":"en","primary_location":{"id":"doi:10.1109/tii.2018.2881266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2018.2881266","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","raw_type":"journal-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/A5079958538","display_name":"Jun Ping Wang","orcid":"https://orcid.org/0000-0003-4355-9827"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Ping Wang","raw_affiliation_strings":["Laboratory of Precision Sensing and Control Center, Institute of Automation, Chinese Academy of Science, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4355-9827","affiliations":[{"raw_affiliation_string":"Laboratory of Precision Sensing and Control Center, Institute of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061141330","display_name":"You Kang Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You Kang Shi","raw_affiliation_strings":["Communications Standards Research Institute, China Academy of Telecommunication Research, MIIT, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications Standards Research Institute, China Academy of Telecommunication Research, MIIT, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102315254","display_name":"Wen Sheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Sheng Zhang","raw_affiliation_strings":["Laboratory of Precision Sensing and Control Center, Institute of Automation, Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Precision Sensing and Control Center, Institute of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034694755","display_name":"Ian Thomas","orcid":"https://orcid.org/0000-0003-3887-6668"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ian Thomas","raw_affiliation_strings":["Fujitsu RunMyProcess, Asnieres-sur-Seine, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu RunMyProcess, Asnieres-sur-Seine, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029427275","display_name":"Shi Hui Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi Hui Duan","raw_affiliation_strings":["Communications Standards Research Institute, China Academy of Telecommunication Research, MIIT, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications Standards Research Institute, China Academy of Telecommunication Research, MIIT, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8448,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.80997475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"15","issue":"4","first_page":"2395","last_page":"2404"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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":0.9986000061035156,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9866999983787537,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10876","display_name":"Fault Detection and Control Systems","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/computer-science","display_name":"Computer science","score":0.717627763748169},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6987345218658447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.655643105506897},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5317524671554565},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.4981682300567627},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4813028872013092},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4745044410228729},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4406152367591858},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4405766725540161},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.42188745737075806},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.20895814895629883},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13501909375190735}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717627763748169},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6987345218658447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.655643105506897},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5317524671554565},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.4981682300567627},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4813028872013092},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4745044410228729},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4406152367591858},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4405766725540161},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.42188745737075806},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.20895814895629883},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13501909375190735},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"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/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tii.2018.2881266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2018.2881266","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/10"},{"display_name":"Peace, Justice and strong institutions","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4586133978","display_name":null,"funder_award_id":"61702517","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5828135306","display_name":null,"funder_award_id":"61602482","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6392050175","display_name":null,"funder_award_id":"61772524","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8092751400","display_name":"\u9762\u5411\u7535\u4fe1\u7528\u6237\u7fa4\u4f53\u4ea4\u4e92\u5927\u6570\u636e\u7684\u4e8b\u4ef6\u7ebf\u7d22\u5728\u7ebf\u6d8c\u73b0\u4e0e\u9884\u5224\u7814\u7a76","funder_award_id":"61772525","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1506538356","https://openalex.org/W1519626139","https://openalex.org/W1848094219","https://openalex.org/W1969074599","https://openalex.org/W2106008664","https://openalex.org/W2114235770","https://openalex.org/W2134197408","https://openalex.org/W2145339207","https://openalex.org/W2161981491","https://openalex.org/W2169743339","https://openalex.org/W2181252817","https://openalex.org/W2235081654","https://openalex.org/W2322277786","https://openalex.org/W2535680674","https://openalex.org/W2563877105","https://openalex.org/W2588013103","https://openalex.org/W2605077367","https://openalex.org/W2613428888","https://openalex.org/W2744355733","https://openalex.org/W2951523806","https://openalex.org/W2952505042","https://openalex.org/W2962897020","https://openalex.org/W3141797743","https://openalex.org/W4293534691","https://openalex.org/W4320013936","https://openalex.org/W6621378261","https://openalex.org/W6631089601","https://openalex.org/W6638853687","https://openalex.org/W6676004469","https://openalex.org/W6677184444","https://openalex.org/W6680171673","https://openalex.org/W6689515257","https://openalex.org/W6713960836","https://openalex.org/W6730027589","https://openalex.org/W6736061541","https://openalex.org/W6742058293","https://openalex.org/W6742534726"],"related_works":["https://openalex.org/W2995777218","https://openalex.org/W2953246223","https://openalex.org/W4293320219","https://openalex.org/W4283584549","https://openalex.org/W3110074278","https://openalex.org/W2618858825","https://openalex.org/W2554314924","https://openalex.org/W2998859928","https://openalex.org/W3151498616","https://openalex.org/W4381885966"],"abstract_inverted_index":{"The":[0,86],"sequential":[1,110,180],"decision-making":[2],"problem":[3],"with":[4,146],"large-scale":[5],"state":[6],"spaces":[7],"is":[8,89,159],"an":[9,118],"important":[10],"and":[11,105,149],"challenging":[12],"topic":[13],"for":[14,34,64,113],"multitask":[15,58,129,151],"reinforcement":[16],"learning":[17,61,65],"(MTRL).":[18],"Training":[19],"near-optimality":[20],"policies":[21],"across":[22,72],"tasks":[23,47],"suffers":[24],"from":[25,97,135,141,162,167,215],"prior":[26,43,137,160],"knowledge":[27,44],"deficiency":[28],"in":[29,121,189],"discrete-time":[30],"nonlinear":[31,67],"environment,":[32],"especially":[33],"continuous":[35],"task":[36,116],"variations,":[37],"requiring":[38],"scalability":[39],"approaches":[40],"to":[41,82,90,217],"transfer":[42],"among":[45],"new":[46,115],"when":[48],"considering":[49],"large":[50,98],"number":[51],"of":[52,78,109,198],"tasks.":[53],"This":[54],"paper":[55],"proposes":[56],"a":[57,66,92,128,136,142,150,190],"policy":[59,69,94,112,130,152,185,192],"adversarial":[60,119],"(MTPAL)":[62],"method":[63],"feedback":[68],"that":[70,207],"generalizes":[71],"multiple":[73],"tasks,":[74],"making":[75],"cognizance":[76],"ability":[77],"robot":[79],"much":[80],"closer":[81],"human-level":[83,163,173,184],"decision":[84,111,181],"making.":[85],"key":[87],"idea":[88],"construct":[91],"parametrized":[93],"model":[95],"directly":[96],"high-dimensional":[99],"observations":[100],"by":[101,117],"deep":[102,191],"function":[103],"approximators,":[104],"then":[106],"train":[107],"optimal":[108],"each":[114],"process,":[120],"which":[122],"simultaneously":[123,214],"two":[124],"models":[125],"are":[126,176],"trained:":[127],"generator":[131],"transforms":[132],"samples":[133,140],"drawn":[134],"distribution":[138,145,161],"into":[139,178],"complex":[143],"data":[144,204],"higher":[147],"dimensionality,":[148],"discriminator":[153],"decides":[154],"whether":[155],"the":[156,168,171,179],"given":[157],"sample":[158],"empirically":[164,174],"derived":[165,175],"or":[166],"generator.":[169],"All":[170],"related":[172],"integrated":[177],"policy,":[182],"transferring":[183],"at":[186],"every":[187],"layer":[188],"network.":[193],"Extensive":[194],"experimental":[195],"testing":[196],"result":[197],"four":[199],"different":[200],"WeiChai":[201],"Power":[202],"manufacturing":[203],"sets":[205],"shows":[206],"our":[208],"approach":[209],"can":[210],"surpass":[211],"human":[212],"performance":[213],"cart-pole":[216],"production":[218],"assembly":[219],"control.":[220]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}