{"id":"https://openalex.org/W3090903721","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207681","title":"Noisy Importance Sampling Actor-Critic: An Off-Policy Actor-Critic With Experience Replay","display_name":"Noisy Importance Sampling Actor-Critic: An Off-Policy Actor-Critic With Experience Replay","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3090903721","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207681","mag":"3090903721"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5024288134","display_name":"Norman Tasfi","orcid":null},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Norman Tasfi","raw_affiliation_strings":["Department of Electrical And Computer Engineering, Western University, London, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical And Computer Engineering, Western University, London, Canada","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083634004","display_name":"Miriam A. M. Capretz","orcid":"https://orcid.org/0000-0002-1380-971X"},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Miriam Capretz","raw_affiliation_strings":["Department of Electrical And Computer Engineering, Western University, London, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical And Computer Engineering, Western University, London, Canada","institution_ids":["https://openalex.org/I125749732"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024288134"],"corresponding_institution_ids":["https://openalex.org/I125749732"],"apc_list":null,"apc_paid":null,"fwci":0.2651,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63610352,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9700000286102295,"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":0.9426000118255615,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7988696694374084},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.749373197555542},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6147832274436951},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5492702126502991},{"id":"https://openalex.org/keywords/truncation","display_name":"Truncation (statistics)","score":0.5335944890975952},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4901009500026703},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4886382222175598},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47871923446655273},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.470337450504303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40776723623275757},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28229546546936035},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14841118454933167},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.14579400420188904}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7988696694374084},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.749373197555542},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6147832274436951},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5492702126502991},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.5335944890975952},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4901009500026703},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4886382222175598},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47871923446655273},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.470337450504303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40776723623275757},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28229546546936035},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14841118454933167},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.14579400420188904},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:ir.lib.uwo.ca:electricalpub-1194","is_oa":false,"landing_page_url":"https://ir.lib.uwo.ca/electricalpub/182","pdf_url":null,"source":{"id":"https://openalex.org/S4306400648","display_name":"Scholarship@Western (Western University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I125749732","host_organization_name":"Western University","host_organization_lineage":["https://openalex.org/I125749732"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical and Computer Engineering Publications","raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W10548402","https://openalex.org/W32403112","https://openalex.org/W1191599655","https://openalex.org/W1515851193","https://openalex.org/W1590243462","https://openalex.org/W1771410628","https://openalex.org/W2089434629","https://openalex.org/W2104733512","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2153874061","https://openalex.org/W2155027007","https://openalex.org/W2162262334","https://openalex.org/W2257979135","https://openalex.org/W2296701362","https://openalex.org/W2547875792","https://openalex.org/W2556958149","https://openalex.org/W2919115771","https://openalex.org/W2953334758","https://openalex.org/W2963095800","https://openalex.org/W2963674921","https://openalex.org/W2964043796","https://openalex.org/W3103780890","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W6627932998","https://openalex.org/W6635158312","https://openalex.org/W6638018090","https://openalex.org/W6675999342","https://openalex.org/W6682998330","https://openalex.org/W6683001934","https://openalex.org/W6683204974","https://openalex.org/W6684017535","https://openalex.org/W6692846177","https://openalex.org/W6697501834","https://openalex.org/W6715102896","https://openalex.org/W6729448088","https://openalex.org/W6730111887","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W1974935850","https://openalex.org/W2074350688","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2042589464","https://openalex.org/W2024136090","https://openalex.org/W2155206396"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"Noisy":[3],"Importance":[4],"Sampling":[5],"Actor-Critic":[6],"(NISAC),":[7],"a":[8,130],"set":[9],"of":[10,35,102,118,132],"empirically":[11],"validated":[12],"modifications":[13],"to":[14,70,85,114],"the":[15,72,77,98,103,133],"advantage":[16],"actor-critic":[17,74,81,91,127],"algorithm":[18,59],"(A2C),":[19],"allowing":[20],"off-policy":[21,80,126],"reinforcement":[22],"learning":[23],"and":[24,39,66,76,110,125],"increased":[25],"performance.":[26],"NISAC":[27,96,119],"uses":[28],"additive":[29,45],"action":[30],"space":[31],"noise,":[32],"aggressive":[33],"truncation":[34],"importance":[36,78],"sample":[37,67],"weights,":[38],"large":[40],"batchsizes.":[41],"We":[42],"see":[43],"that":[44],"noise":[46],"drastically":[47],"changes":[48],"how":[49],"off-sample":[50],"experience":[51,93],"is":[52,120],"weighted":[53,79],"for":[54],"policy":[55],"updates.":[56],"The":[57,116],"modified":[58],"achieves":[60],"an":[61],"increase":[62],"in":[63],"convergence":[64],"speed":[65],"efficiency":[68],"compared":[69],"both":[71],"on-policy":[73,124],"A2C":[75],"algorithm.":[82],"In":[83],"comparison":[84],"state-of-the-art":[86],"(SOTA)":[87],"methods,":[88],"such":[89],"as":[90],"with":[92],"replay":[94],"(ACER),":[95],"nears":[97],"performance":[99],"on":[100,129],"several":[101],"tested":[104],"environments":[105],"while":[106],"training":[107],"40%":[108],"faster":[109],"being":[111],"significantly":[112],"easier":[113],"implement.":[115],"effectiveness":[117],"demonstrated":[121],"against":[122],"existing":[123],"algorithms":[128],"subset":[131],"Atari":[134],"domain.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}