{"id":"https://openalex.org/W3029901419","doi":"https://doi.org/10.1145/3387168.3387199","title":"Twin-Delayed DDPG","display_name":"Twin-Delayed DDPG","publication_year":2019,"publication_date":"2019-08-26","ids":{"openalex":"https://openalex.org/W3029901419","doi":"https://doi.org/10.1145/3387168.3387199","mag":"3029901419"},"language":"en","primary_location":{"id":"doi:10.1145/3387168.3387199","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3387168.3387199","pdf_url":null,"source":{"id":"https://openalex.org/S4306523820","display_name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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 3rd International Conference on Vision, Image and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5040416969","display_name":"Stephen Dankwa","orcid":"https://orcid.org/0000-0002-8329-5398"},"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":"Stephen Dankwa","raw_affiliation_strings":["Automation Engineering, University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Automation Engineering, University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062384828","display_name":"Wenfeng Zheng","orcid":"https://orcid.org/0000-0002-8486-1654"},"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":"Wenfeng Zheng","raw_affiliation_strings":["Automation Engineering, University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Automation Engineering, University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":155,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9902999997138977,"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":0.7412784099578857},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6950809955596924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6012652516365051},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5876036286354065},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4480772018432617},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42401576042175293},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2161874771118164},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12026897072792053}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7412784099578857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6950809955596924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6012652516365051},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5876036286354065},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4480772018432617},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42401576042175293},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2161874771118164},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12026897072792053},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3387168.3387199","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3387168.3387199","pdf_url":null,"source":{"id":"https://openalex.org/S4306523820","display_name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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 3rd International Conference on Vision, Image and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1757796397","https://openalex.org/W2492794003","https://openalex.org/W2612690371","https://openalex.org/W2749928749","https://openalex.org/W2787938642","https://openalex.org/W6600986572","https://openalex.org/W6638018090","https://openalex.org/W6684205842","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4206669594","https://openalex.org/W3037422413","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W3111983280","https://openalex.org/W3164468573","https://openalex.org/W3155882255","https://openalex.org/W2386387936"],"abstract_inverted_index":{"In":[0],"this":[1],"current":[2],"research,":[3],"Twin-Delayed":[4,34,168],"DDPG":[5,35,169],"(TD3)":[6,36,170],"algorithm":[7],"has":[8,215],"been":[9],"used":[10,97],"to":[11,29,75,151,172],"solve":[12],"the":[13,50,91,94,124,136,139,145,152,156,167,192,197,220,226],"most":[14],"challenging":[15,234],"virtual":[16],"Artificial":[17,54],"Intelligence":[18],"application":[19],"by":[20],"training":[21],"a":[22,32,44,98,131,233,237],"4-ant-legged":[23],"robot":[24],"as":[25,115,149],"an":[26,38,72,78,116,186,203],"Intelligent":[27,73],"Agent":[28],"run":[30],"across":[31],"field.":[33],"is":[37,171],"incredibly":[39],"smart":[40],"AI":[41],"model":[42,201],"of":[43,93,103,138,206,225],"Deep":[45,64,67,177,227],"Reinforcement":[46,68],"Learning":[47,69],"which":[48,182],"combines":[49],"state-of-the-art":[51],"methods":[52],"in":[53,176,185,232,236],"Intelligence.":[55],"These":[56,66],"includes":[57],"Policy":[58,229],"gradient,":[59],"Actor-Critics,":[60],"and":[61,105,126,147,223],"continuous":[62,238],"Double":[63],"Q-Learning.":[65],"approaches":[70],"trained":[71],"agent":[74],"interact":[76],"with":[77,80,110,179],"environment":[79,235],"automatic":[81],"feature":[82],"engineering,":[83],"that":[84],"is,":[85],"necessitating":[86],"minimal":[87],"domain":[88,188],"knowledge.":[89],"For":[90],"implementation":[92],"TD3,":[95],"we":[96,209],"two-layer":[99],"feedforward":[100],"neural":[101],"network":[102,157],"400":[104],"300":[106],"hidden":[107],"nodes":[108],"respectively,":[109],"Rectified":[111],"Linear":[112],"Units":[113],"(ReLU)":[114],"activation":[117],"function":[118],"between":[119],"each":[120],"layer":[121],"for":[122],"both":[123,144,219],"Actor":[125],"Critics.":[127],"We,":[128],"then":[129],"added":[130],"final":[132],"tanh":[133],"unit":[134],"after":[135],"output":[137],"Actor.":[140],"The":[141,164],"Critic":[142],"receives":[143],"state":[146],"action":[148],"input":[150],"first":[153],"layer.":[154],"Both":[155],"parameters":[158],"were":[159],"updated":[160],"using":[161],"Adam":[162],"optimizer.":[163],"idea":[165],"behind":[166],"reduce":[173],"overestimation":[174],"bias":[175],"Q-Learning":[178],"discrete":[180],"actions":[181],"are":[183],"ineffective":[184],"Actor-Critic":[187],"setting.":[189],"Based":[190],"on":[191,218],"Maximum":[193],"Average":[194],"Reward":[195],"over":[196],"evaluation":[198],"time-step,":[199],"our":[200],"achieved":[202],"approximate":[204],"maximum":[205],"2364.":[207],"Therefore,":[208],"can":[210],"truly":[211],"say":[212],"that,":[213],"TD3":[214],"obviously":[216],"improved":[217],"learning":[221],"speed":[222],"performance":[224],"Deterministic":[228],"Gradient":[230],"(DDPG)":[231],"control":[239],"domain.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":46},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2020-06-05T00:00:00"}