{"id":"https://openalex.org/W2939075711","doi":"https://doi.org/10.1109/icassp.2019.8682832","title":"Non-local Self-attention Structure for Function Approximation in Deep Reinforcement Learning","display_name":"Non-local Self-attention Structure for Function Approximation in Deep Reinforcement Learning","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939075711","doi":"https://doi.org/10.1109/icassp.2019.8682832","mag":"2939075711"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100700404","display_name":"Zhixiang Wang","orcid":"https://orcid.org/0000-0002-5016-587X"},"institutions":[{"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":"Zhixiang Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101600503","display_name":"Xi Xiao","orcid":"https://orcid.org/0000-0003-1521-9542"},"institutions":[{"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":"Xi Xiao","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085450781","display_name":"Guangwu Hu","orcid":"https://orcid.org/0000-0003-3947-9998"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangwu Hu","raw_affiliation_strings":["School of Computer Science, Shenzhen Institute of Information Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Shenzhen Institute of Information Technology, Shenzhen, China","institution_ids":["https://openalex.org/I158809036"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389418","display_name":"Yao Yao","orcid":"https://orcid.org/0000-0001-9887-4301"},"institutions":[{"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":"Yao Yao","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022127523","display_name":"Dianyan Zhang","orcid":null},"institutions":[{"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":"Dianyan Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041630666","display_name":"Zhendong Peng","orcid":null},"institutions":[{"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":"Zhendong Peng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404176","display_name":"Qing Li","orcid":"https://orcid.org/0000-0003-3370-471X"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["Southern University of Science and Technology, Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034104790","display_name":"Shu\u2010Tao Xia","orcid":"https://orcid.org/0000-0002-8639-982X"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shutao Xia","raw_affiliation_strings":["Southern University of Science and Technology, Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03140243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"3042","last_page":"3046"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.986299991607666,"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":0.9642999768257141,"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":0.9251563549041748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8009183406829834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6757737994194031},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5457543134689331},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.525883138179779},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5040968656539917},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4781276285648346},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47250068187713623},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4479573965072632},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4336181581020355},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4236447811126709},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4197629392147064},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08449754118919373}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9251563549041748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8009183406829834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6757737994194031},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5457543134689331},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.525883138179779},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5040968656539917},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4781276285648346},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47250068187713623},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4479573965072632},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4336181581020355},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4236447811126709},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4197629392147064},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08449754118919373},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2413794162","https://openalex.org/W2727840223","https://openalex.org/W2736601468","https://openalex.org/W2749928749","https://openalex.org/W2766447205","https://openalex.org/W2787579267","https://openalex.org/W2804078698","https://openalex.org/W2962754210","https://openalex.org/W2963091558","https://openalex.org/W2963313316","https://openalex.org/W2963403868","https://openalex.org/W2963864421","https://openalex.org/W2963871073","https://openalex.org/W2964043796","https://openalex.org/W4298857966","https://openalex.org/W4385245566","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6683204974","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6739901393","https://openalex.org/W6741002519","https://openalex.org/W6743802245","https://openalex.org/W6746034047","https://openalex.org/W6748655329","https://openalex.org/W6752378368","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W4384574988","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1528400370"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,41],"is":[2,107],"a":[3,87],"framework":[4],"to":[5,28,80,92],"make":[6,25,29,39],"sequential":[7,30],"decisions.":[8],"The":[9],"combination":[10],"with":[11,72],"deep":[12,114],"neural":[13,51],"networks":[14,24,52],"further":[15],"improves":[16],"the":[17,73,77,82],"ability":[18,91],"of":[19,47],"this":[20],"framework.":[21],"Convolutional":[22],"nerual":[23],"it":[26],"possible":[27],"decisions":[31],"based":[32],"on":[33,100],"raw":[34],"pixels":[35],"information":[36],"directly":[37],"and":[38,61,96],"reinforcement":[40,115],"achieve":[42],"satisfying":[43],"performances":[44],"in":[45,57,67,113],"series":[46],"tasks.":[48],"However,":[49],"convolutional":[50],"still":[53],"have":[54],"own":[55],"limitations":[56],"representing":[58],"geometric":[59],"patterns":[60],"long-term":[62],"dependencies":[63,95],"that":[64,104],"occur":[65],"consistently":[66],"state":[68],"inputs.":[69],"To":[70],"tackle":[71],"limitation,":[74],"we":[75],"propose":[76],"self-attention":[78,105],"architecture":[79],"augment":[81],"original":[83],"network.":[84],"It":[85],"provides":[86],"better":[88],"balance":[89],"between":[90],"model":[93],"long-range":[94],"computational":[97],"efficiency.":[98],"Experiments":[99],"Atari":[101],"games":[102],"illustrate":[103],"structure":[106],"significantly":[108],"effective":[109],"for":[110],"function":[111],"approximation":[112],"learning.":[116]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}