{"id":"https://openalex.org/W4206024271","doi":"https://doi.org/10.1109/tetci.2022.3140380","title":"Structural Parameter Space Exploration for Reinforcement Learning via a Matrix Variate Distribution","display_name":"Structural Parameter Space Exploration for Reinforcement Learning via a Matrix Variate Distribution","publication_year":2022,"publication_date":"2022-01-13","ids":{"openalex":"https://openalex.org/W4206024271","doi":"https://doi.org/10.1109/tetci.2022.3140380"},"language":"en","primary_location":{"id":"doi:10.1109/tetci.2022.3140380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2022.3140380","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","raw_type":"journal-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/A5038630321","display_name":"Shaochen Wang","orcid":"https://orcid.org/0000-0002-6985-240X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaochen Wang","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-6985-240X","affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614868","display_name":"Rui Yang","orcid":"https://orcid.org/0000-0003-4552-584X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Yang","raw_affiliation_strings":["CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365157","display_name":"Bin Li","orcid":"https://orcid.org/0000-0002-2332-3959"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-2332-3959","affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018344952","display_name":"Zhen Kan","orcid":"https://orcid.org/0000-0003-2069-9544"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Kan","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2069-9544","affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":1.6691,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85651349,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"7","issue":"4","first_page":"1025","last_page":"1035"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9936000108718872,"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/T10260","display_name":"Software Engineering Research","score":0.9484000205993652,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/random-variate","display_name":"Random variate","score":0.7418431639671326},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6474826335906982},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6418753862380981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.620036244392395},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5881292819976807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5687276124954224},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5653163194656372},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5148269534111023},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4998912811279297},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4448188841342926},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4231947064399719},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3509471118450165},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22736459970474243},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.12268978357315063},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10586333274841309},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10494014620780945}],"concepts":[{"id":"https://openalex.org/C141547133","wikidata":"https://www.wikidata.org/wiki/Q7291996","display_name":"Random variate","level":3,"score":0.7418431639671326},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6474826335906982},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6418753862380981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.620036244392395},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5881292819976807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5687276124954224},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5653163194656372},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5148269534111023},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4998912811279297},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4448188841342926},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4231947064399719},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3509471118450165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22736459970474243},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.12268978357315063},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10586333274841309},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10494014620780945},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetci.2022.3140380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2022.3140380","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G1051832680","display_name":null,"funder_award_id":"62173314","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2262853887","display_name":null,"funder_award_id":"61836011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4198966207","display_name":null,"funder_award_id":"U19B2044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6104967667","display_name":null,"funder_award_id":"U2013601","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1501823362","https://openalex.org/W1522301498","https://openalex.org/W2123327324","https://openalex.org/W2137104525","https://openalex.org/W2145339207","https://openalex.org/W2194775991","https://openalex.org/W2404342324","https://openalex.org/W2417786368","https://openalex.org/W2596367596","https://openalex.org/W2600383743","https://openalex.org/W2623491082","https://openalex.org/W2724169821","https://openalex.org/W2731982447","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2766447205","https://openalex.org/W2804380964","https://openalex.org/W2951266961","https://openalex.org/W2952300048","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964067469","https://openalex.org/W2964116903","https://openalex.org/W2990747716","https://openalex.org/W3148198191","https://openalex.org/W4293154685","https://openalex.org/W4297791094","https://openalex.org/W4298857966","https://openalex.org/W4391602018","https://openalex.org/W6630117878","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6640963894","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6697490744","https://openalex.org/W6713347985","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6734097942","https://openalex.org/W6735443497","https://openalex.org/W6735641298","https://openalex.org/W6739193204","https://openalex.org/W6740083460","https://openalex.org/W6740092555","https://openalex.org/W6747478502","https://openalex.org/W6751540476","https://openalex.org/W6756303580","https://openalex.org/W6764214684","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2997512100","https://openalex.org/W3074294383","https://openalex.org/W2331043530","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W4290792893","https://openalex.org/W2393933887","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W4319083788"],"abstract_inverted_index":{"The":[0],"trade-off":[1],"between":[2,123],"exploration":[3,38,127,150,155],"and":[4,26,70,95,128,160,165],"exploitation":[5],"is":[6,166],"essential":[7],"for":[8,22,73],"reinforcement":[9],"learning,":[10],"where":[11],"an":[12,40],"agent":[13],"needs":[14],"to":[15,20,28,88,111,168],"be":[16],"aware":[17],"of":[18,45,63,80,115,138],"when":[19,27],"explore":[21],"high":[23],"reward":[24],"policies":[25],"exploit":[29],"the":[30,46,52,61,64,77,81,102,113,116,124,135,169],"optimal":[31],"policy":[32],"known":[33],"so":[34],"far.":[35],"Parameter":[36],"space":[37,140],"provides":[39],"elegant":[41],"solution.":[42],"As":[43],"one":[44],"principal":[47],"methods,":[48],"injecting":[49],"noise":[50,72,98,110,126,149],"into":[51,67,92],"model":[53],"parameters":[54,62],"greatly":[55],"improves":[56],"exploration.":[57,141],"However,":[58],"directly":[59],"stretching":[60],"neural":[65,130],"network":[66],"a":[68,121],"vector":[69,75],"generating":[71],"this":[74,84],"ignore":[76],"structural":[78,103],"information":[79,91],"model.":[82],"In":[83],"paper,":[85],"we":[86,119],"aim":[87],"incorporate":[89],"spatial":[90],"weight":[93,104],"matrices":[94],"propose":[96],"matrix-variate":[97],"exploration,":[99],"which":[100,132],"exploits":[101],"uncertainty":[105],"brought":[106],"by":[107],"matrix":[108,125,147],"variate":[109,148],"enhance":[112],"stochasticity":[114],"agent.":[117],"Indeed,":[118],"construct":[120],"bridge":[122],"probabilistic":[129],"networks,":[131],"theoretically":[133],"explains":[134],"improved":[136],"performance":[137],"parameter":[139],"Extensive":[142],"experiments":[143],"have":[144],"shown":[145],"that":[146],"outperforms":[151],"fully":[152],"factorized":[153],"noisy":[154],"on":[156],"most":[157],"Atari":[158],"tasks":[159,164],"Super":[161],"Mario":[162],"Bros":[163],"competitive":[167],"state-of-the-art":[170],"methods.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}