{"id":"https://openalex.org/W3035189581","doi":"https://doi.org/10.24963/ijcai.2020/436","title":"Exploring Parameter Space with Structured Noise for Meta-Reinforcement Learning","display_name":"Exploring Parameter Space with Structured Noise for Meta-Reinforcement Learning","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3035189581","doi":"https://doi.org/10.24963/ijcai.2020/436","mag":"3035189581"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/436","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/436","pdf_url":"https://www.ijcai.org/proceedings/2020/0436.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0436.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100625645","display_name":"Hui Xu","orcid":"https://orcid.org/0000-0003-2081-555X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Xu","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393899","display_name":"Chong Zhang","orcid":"https://orcid.org/0000-0002-2162-4344"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chong Zhang","raw_affiliation_strings":["Tencent Robotics X"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Robotics X","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100717645","display_name":"Jiaxing Wang","orcid":"https://orcid.org/0000-0003-0028-3162"},"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/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":"Jiaxing Wang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065413088","display_name":"Deqiang Ouyang","orcid":"https://orcid.org/0000-0003-2259-886X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deqiang Ouyang","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103176848","display_name":"Y. Zheng","orcid":"https://orcid.org/0000-0002-4617-3252"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zheng","raw_affiliation_strings":["Tencent Robotics X"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Robotics X","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072350518","display_name":"Jie Shao","orcid":"https://orcid.org/0000-0003-2615-1555"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4210131846","display_name":"Artificial Intelligence Research Institute","ror":"https://ror.org/03c0ach84","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210131846"]},{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["CN","ES","US"],"is_corresponding":false,"raw_author_name":"Jie Shao","raw_affiliation_strings":["Sichuan Arti\ufb01cial Intelligence Research Institute","University of Electronic Science and Technology of China","Sichuan Artificial Intelligence Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan Arti\ufb01cial Intelligence Research Institute","institution_ids":["https://openalex.org/I4210145386"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Sichuan Artificial Intelligence Research Institute","institution_ids":["https://openalex.org/I4210131846"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.575,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.6884484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3153","last_page":"3159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9947999715805054,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9930999875068665,"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":0.8848608732223511},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7581350207328796},{"id":"https://openalex.org/keywords/dither","display_name":"Dither","score":0.7473289966583252},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6955028772354126},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6899642944335938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.546066164970398},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.5177668333053589},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4731368124485016},{"id":"https://openalex.org/keywords/noise-shaping","display_name":"Noise shaping","score":0.14551085233688354},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12009620666503906},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11297264695167542}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8848608732223511},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7581350207328796},{"id":"https://openalex.org/C70451592","wikidata":"https://www.wikidata.org/wiki/Q376493","display_name":"Dither","level":3,"score":0.7473289966583252},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6955028772354126},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6899642944335938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.546066164970398},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.5177668333053589},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4731368124485016},{"id":"https://openalex.org/C9083635","wikidata":"https://www.wikidata.org/wiki/Q2133535","display_name":"Noise shaping","level":2,"score":0.14551085233688354},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12009620666503906},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11297264695167542},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/436","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/436","pdf_url":"https://www.ijcai.org/proceedings/2020/0436.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.2020/436","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/436","pdf_url":"https://www.ijcai.org/proceedings/2020/0436.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/G2445068122","display_name":null,"funder_award_id":"2018GZDZX0032","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4253300795","display_name":null,"funder_award_id":"61832001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4255492492","display_name":"\u793e\u4f1a\u5316\u5a92\u4f53\u4e2d\u7684\u79fb\u52a8\u8f68\u8ff9\u8bed\u4e49\u589e\u5f3a\u548c\u6316\u6398\u63a8\u8350\u7814\u7a76","funder_award_id":"61672133","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4387417602","display_name":null,"funder_award_id":"No. 61832001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7819190046","display_name":null,"funder_award_id":"2019YFG0535","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/W3035189581.pdf","grobid_xml":"https://content.openalex.org/works/W3035189581.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1550989509","https://openalex.org/W1771410628","https://openalex.org/W1959608418","https://openalex.org/W2091118421","https://openalex.org/W2121863487","https://openalex.org/W2123327324","https://openalex.org/W2137825550","https://openalex.org/W2140256637","https://openalex.org/W2145680191","https://openalex.org/W2158782408","https://openalex.org/W2161966552","https://openalex.org/W2280163991","https://openalex.org/W2417786368","https://openalex.org/W2489939061","https://openalex.org/W2592651140","https://openalex.org/W2604763608","https://openalex.org/W2614839826","https://openalex.org/W2623491082","https://openalex.org/W2724169821","https://openalex.org/W2734377693","https://openalex.org/W2742093937","https://openalex.org/W2788904251","https://openalex.org/W2805481182","https://openalex.org/W2949475445","https://openalex.org/W2963276097","https://openalex.org/W2963341924","https://openalex.org/W2963523627","https://openalex.org/W2963938771","https://openalex.org/W2964078140","https://openalex.org/W2964121937","https://openalex.org/W2964174623","https://openalex.org/W2966461828","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W4294646197","https://openalex.org/W4295676892","https://openalex.org/W4300514939"],"related_works":["https://openalex.org/W2389128124","https://openalex.org/W2364812720","https://openalex.org/W2138725603","https://openalex.org/W1984486060","https://openalex.org/W2050335563","https://openalex.org/W3001913892","https://openalex.org/W2273639645","https://openalex.org/W4294873804","https://openalex.org/W4383109125","https://openalex.org/W2891227010"],"abstract_inverted_index":{"Efficient":[0],"exploration":[1,66,109],"is":[2],"a":[3,17,38,76,135],"major":[4],"challenge":[5],"in":[6,82,110],"Reinforcement":[7],"Learning":[8],"(RL)":[9],"and":[10,90,126],"has":[11],"been":[12],"studied":[13],"extensively.":[14],"However,":[15],"for":[16,107],"new":[18,69,111],"task":[19,29],"existing":[20],"methods":[21],"explore":[22],"either":[23],"by":[24],"taking":[25],"actions":[26],"that":[27],"maximize":[28],"agnostic":[30],"objectives":[31],"(such":[32,42],"as":[33,43,99],"information":[34],"gain)":[35],"or":[36],"applying":[37],"simple":[39],"dithering":[40],"strategy":[41],"noise":[44],"injection),":[45],"which":[46,95],"might":[47],"not":[48],"be":[49,62],"effective":[50,108],"enough.":[51],"In":[52],"this":[53,72],"paper,":[54],"we":[55,74],"investigate":[56],"whether":[57],"previous":[58],"learning":[59],"experiences":[60],"can":[61],"leveraged":[63],"to":[64,102],"guide":[65],"of":[67,118,132,137],"current":[68],"task.":[70],"To":[71],"end,":[73],"propose":[75],"novel":[77],"Exploration":[78],"with":[79],"Structured":[80],"Noise":[81],"Parameter":[83],"Space":[84],"(ESNPS)":[85],"approach.":[86],"ESNPS":[87,133],"utilizes":[88],"meta-learning":[89],"directly":[91],"uses":[92],"meta-policy":[93],"parameters,":[94],"contain":[96],"prior":[97],"knowledge,":[98],"structured":[100],"noises":[101],"perturb":[103],"the":[104,130],"base":[105],"model":[106],"tasks.":[112],"Experimental":[113],"results":[114],"on":[115],"four":[116],"groups":[117],"tasks:":[119],"cheetah":[120,122],"velocity,":[121],"direction,":[123],"ant":[124,127],"velocity":[125],"direction":[128],"demonstrate":[129],"superiority":[131],"against":[134],"number":[136],"competitive":[138],"baselines.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}