{"id":"https://openalex.org/W2807908072","doi":"https://doi.org/10.24963/ijcai.2018/444","title":"Self-Adaptive Double Bootstrapped DDPG","display_name":"Self-Adaptive Double Bootstrapped DDPG","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2807908072","doi":"https://doi.org/10.24963/ijcai.2018/444","mag":"2807908072"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/444","doi":"https://doi.org/10.24963/ijcai.2018/444","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/444","pdf_url":"https://www.ijcai.org/proceedings/2018/0444.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2018/0444.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102591905","display_name":"Zhuobin Zheng","orcid":"https://orcid.org/0009-0002-9674-5244","observed_orcids":["https://orcid.org/0009-0002-9674-5244"]},"institutions":[{"id":"https://openalex.org/I4405263052","display_name":"Tsinghua Shenzhen International Graduate School","ror":"https://ror.org/01vceef04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405263052","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuobin Zheng","raw_affiliation_strings":["Department of Computer Science and Technologies, Tsinghua University","Graduate School at Shenzhen, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technologies, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Graduate School at Shenzhen, Tsinghua University","institution_ids":["https://openalex.org/I4405263052","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101456902","display_name":"Chun Yuan","orcid":"https://orcid.org/0000-0002-3590-6676","observed_orcids":["https://orcid.org/0000-0002-3590-6676"]},"institutions":[{"id":"https://openalex.org/I4405263052","display_name":"Tsinghua Shenzhen International Graduate School","ror":"https://ror.org/01vceef04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405263052","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Yuan","raw_affiliation_strings":["Graduate School at Shenzhen, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School at Shenzhen, Tsinghua University","institution_ids":["https://openalex.org/I4405263052","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054238848","display_name":"Zhihui Lin","orcid":"https://orcid.org/0000-0003-0949-0635","observed_orcids":["https://orcid.org/0000-0003-0949-0635"]},"institutions":[{"id":"https://openalex.org/I4405263052","display_name":"Tsinghua Shenzhen International Graduate School","ror":"https://ror.org/01vceef04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405263052","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihui Lin","raw_affiliation_strings":["Department of Computer Science and Technologies, Tsinghua University","Graduate School at Shenzhen, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technologies, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Graduate School at Shenzhen, Tsinghua University","institution_ids":["https://openalex.org/I4405263052","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021760829","display_name":"Yangyang Cheng","orcid":"https://orcid.org/0000-0003-4991-6610","observed_orcids":["https://orcid.org/0000-0003-4991-6610"]},"institutions":[{"id":"https://openalex.org/I4405263052","display_name":"Tsinghua Shenzhen International Graduate School","ror":"https://ror.org/01vceef04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405263052","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangyang Cheng","raw_affiliation_strings":["Department of Computer Science and Technologies, Tsinghua University","Graduate School at Shenzhen, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technologies, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Graduate School at Shenzhen, Tsinghua University","institution_ids":["https://openalex.org/I4405263052","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049760745","display_name":"Hanghao Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405263052","display_name":"Tsinghua Shenzhen International Graduate School","ror":"https://ror.org/01vceef04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405263052","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanghao Wu","raw_affiliation_strings":["Department of Computer Science and Technologies, Tsinghua University","Graduate School at Shenzhen, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technologies, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Graduate School at Shenzhen, Tsinghua University","institution_ids":["https://openalex.org/I4405263052","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3216,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.86122637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3198","last_page":"3204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"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"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.0,"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/ddpg","display_name":"deep deterministic policy gradient","score":0.906000018119812},{"id":"https://openalex.org/keywords/exploration-efficiency","display_name":"exploration efficiency","score":0.8949999809265137},{"id":"https://openalex.org/keywords/training-stability","display_name":"training stability","score":0.7850000262260437},{"id":"https://openalex.org/keywords/continuous-control","display_name":"continuous control","score":0.8610000014305115},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.6200000047683716},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"ensemble learning","score":0.38600000739097595}],"concepts":[{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.8297443389892578},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6300820708274841},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6240876913070679},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4596073627471924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43518924713134766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26883792877197266},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2512917220592499},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10120841860771179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2018/444","doi":"https://doi.org/10.24963/ijcai.2018/444","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/444","pdf_url":"https://www.ijcai.org/proceedings/2018/0444.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/444","doi":"https://doi.org/10.24963/ijcai.2018/444","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/444","pdf_url":"https://www.ijcai.org/proceedings/2018/0444.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7188823739","display_name":null,"funder_award_id":"U1433112","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2807908072.pdf","grobid_xml":"https://content.openalex.org/works/W2807908072.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2260756217","https://openalex.org/W2280163991","https://openalex.org/W2551887912","https://openalex.org/W2554984891","https://openalex.org/W2614839826","https://openalex.org/W2623491082","https://openalex.org/W2739678353","https://openalex.org/W2747402019","https://openalex.org/W2754517384","https://openalex.org/W2766447205","https://openalex.org/W2767313115","https://openalex.org/W2774354230","https://openalex.org/W2964121744","https://openalex.org/W2964161785","https://openalex.org/W4214717370","https://openalex.org/W4302570325","https://openalex.org/W4310299640","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W2985758613","https://openalex.org/W3002765113","https://openalex.org/W6981511874","https://openalex.org/W4309467173","https://openalex.org/W2775482448","https://openalex.org/W2910509260","https://openalex.org/W4414580056","https://openalex.org/W4409662704","https://openalex.org/W4226083239","https://openalex.org/W3156364506"],"abstract_inverted_index":{"Deep":[0],"Deterministic":[1],"Policy":[2],"Gradient":[3],"(DDPG)":[4],"algorithm":[5,48],"has":[6],"been":[7],"successful":[8],"for":[9],"state-of-the-art":[10],"performance":[11,124],"in":[12,90,146],"high-dimensional":[13],"continuous":[14],"control":[15],"tasks.":[16],"However,":[17],"due":[18],"to":[19,29,52,86,112,148],"the":[20,25,58,88,104,115,122],"complexity":[21],"and":[22,34,70,120,126,143],"randomness":[23],"of":[24,60,81,96,117],"environment,":[26],"DDPG":[27,45,51,150],"tends":[28],"suffer":[30],"from":[31],"inefficient":[32],"exploration":[33,61],"unstable":[35],"training.":[36,101],"In":[37],"this":[38],"work,":[39],"we":[40],"propose":[41],"Self-Adaptive":[42],"Double":[43],"Bootstrapped":[44],"(SOUP),":[46],"an":[47],"that":[49,130],"extends":[50],"bootstrapped":[53,83,118],"actor-critic":[54],"architecture.":[55],"SOUP":[56,131],"improves":[57],"efficiency":[59],"by":[62,93,135],"multiple":[63,71,94],"actor":[64],"heads":[65,73,95,119],"capturing":[66],"more":[67,75],"potential":[68],"actions":[69],"critic":[72],"evaluating":[74],"reasonable":[76],"Q-values":[77],"collaboratively.":[78],"The":[79],"crux":[80],"double":[82],"architecture":[84],"is":[85,110],"tackle":[87],"fluctuations":[89],"performance,":[91],"caused":[92],"spotty":[97],"capacity":[98],"varying":[99],"throughout":[100],"To":[102],"alleviate":[103],"instability,":[105],"a":[106],"self-adaptive":[107],"confidence":[108],"mechanism":[109],"introduced":[111],"dynamically":[113],"adjust":[114],"weights":[116],"enhance":[121],"ensemble":[123],"effectively":[125],"efficiently.":[127],"We":[128],"demonstrate":[129],"achieves":[132],"faster":[133],"learning":[134],"at":[136],"least":[137],"45%":[138],"while":[139],"improving":[140],"cumulative":[141],"reward":[142],"stability":[144],"substantially":[145],"comparison":[147],"vanilla":[149],"on":[151],"OpenAI":[152],"Gym's":[153],"MuJoCo":[154],"environments.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2018-06-21T00:00:00"}