{"id":"https://openalex.org/W4401908497","doi":"https://doi.org/10.1109/tnnls.2024.3446371","title":"Discretizing Continuous Action Space With Unimodal Probability Distributions for On-Policy Reinforcement Learning","display_name":"Discretizing Continuous Action Space With Unimodal Probability Distributions for On-Policy Reinforcement Learning","publication_year":2024,"publication_date":"2024-08-27","ids":{"openalex":"https://openalex.org/W4401908497","doi":"https://doi.org/10.1109/tnnls.2024.3446371","pmid":"https://pubmed.ncbi.nlm.nih.gov/39190528"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3446371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3446371","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5021451616","display_name":"Yuanyang Zhu","orcid":"https://orcid.org/0000-0001-7484-1804"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyang Zhu","raw_affiliation_strings":["Department of Control Science and Intelligence Engineering, School of Management and Engineering, and the Laboratory of Data Intelligence and Interdisciplinary Innovation, Nanjing University, Nanjing, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7484-1804","affiliations":[{"raw_affiliation_string":"Department of Control Science and Intelligence Engineering, School of Management and Engineering, and the Laboratory of Data Intelligence and Interdisciplinary Innovation, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376415","display_name":"Zhi Wang","orcid":"https://orcid.org/0000-0003-0304-3965"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Wang","raw_affiliation_strings":["Department of Control Science and Intelligence Engineering, School of Management and Engineering, and the Research Center for Novel Technology of Intelligent Equipment, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0304-3965","affiliations":[{"raw_affiliation_string":"Department of Control Science and Intelligence Engineering, School of Management and Engineering, and the Research Center for Novel Technology of Intelligent Equipment, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080193690","display_name":"Yuanheng Zhu","orcid":"https://orcid.org/0000-0001-5384-423X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanheng Zhu","raw_affiliation_strings":["Department of Control Science and Intelligence Engineering, School of Management and Engineering, and the Laboratory of Data Intelligence and Interdisciplinary Innovation, Nanjing University, Nanjing, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5384-423X","affiliations":[{"raw_affiliation_string":"Department of Control Science and Intelligence Engineering, School of Management and Engineering, and the Laboratory of Data Intelligence and Interdisciplinary Innovation, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697167","display_name":"Chunlin Chen","orcid":"https://orcid.org/0000-0003-3929-4707"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlin Chen","raw_affiliation_strings":["Department of Control Science and Intelligence Engineering, School of Management and Engineering, and the Research Center for Novel Technology of Intelligent Equipment, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-3929-4707","affiliations":[{"raw_affiliation_string":"Department of Control Science and Intelligence Engineering, School of Management and Engineering, and the Research Center for Novel Technology of Intelligent Equipment, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8218-9633","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.10147847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"6","first_page":"11285","last_page":"11297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8930000066757202,"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":0.8930000066757202,"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/discretization","display_name":"Discretization","score":0.7461951971054077},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.7358896732330322},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7147480249404907},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.632444441318512},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5904713869094849},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.46560221910476685},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42244136333465576},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.39753568172454834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2957514524459839},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.22259056568145752},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.19279658794403076},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1783788800239563},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12089845538139343},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.10747236013412476}],"concepts":[{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.7461951971054077},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7358896732330322},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7147480249404907},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.632444441318512},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5904713869094849},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.46560221910476685},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42244136333465576},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39753568172454834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2957514524459839},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22259056568145752},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.19279658794403076},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1783788800239563},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12089845538139343},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.10747236013412476},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3446371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3446371","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:39190528","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39190528","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4399999976158142,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G7996831764","display_name":null,"funder_award_id":"62073160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8129508401","display_name":null,"funder_award_id":"62376122","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8564052084","display_name":null,"funder_award_id":"2021132","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W68008431","https://openalex.org/W2119717200","https://openalex.org/W2131490903","https://openalex.org/W2155802349","https://openalex.org/W2229058806","https://openalex.org/W2440214111","https://openalex.org/W2769883686","https://openalex.org/W2894298649","https://openalex.org/W2907537824","https://openalex.org/W2911087563","https://openalex.org/W2990747716","https://openalex.org/W2993534970","https://openalex.org/W2997902164","https://openalex.org/W3046093665","https://openalex.org/W3192708540","https://openalex.org/W4319165238","https://openalex.org/W4321195885","https://openalex.org/W4377971366","https://openalex.org/W4386025780","https://openalex.org/W4386702747","https://openalex.org/W6610566761","https://openalex.org/W6627932998","https://openalex.org/W6631190155","https://openalex.org/W6638018090","https://openalex.org/W6639949747","https://openalex.org/W6676023451","https://openalex.org/W6679257226","https://openalex.org/W6680821758","https://openalex.org/W6681451320","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6685951826","https://openalex.org/W6696324988","https://openalex.org/W6704571135","https://openalex.org/W6732309060","https://openalex.org/W6734517396","https://openalex.org/W6738317315","https://openalex.org/W6738596827","https://openalex.org/W6741002519","https://openalex.org/W6741471465","https://openalex.org/W6743802245","https://openalex.org/W6747473740","https://openalex.org/W6747993910","https://openalex.org/W6748523217","https://openalex.org/W6748839928","https://openalex.org/W6752152363","https://openalex.org/W6756287877","https://openalex.org/W6768017362","https://openalex.org/W6780113477","https://openalex.org/W6780559895","https://openalex.org/W6785759594","https://openalex.org/W6800229816","https://openalex.org/W6802631393","https://openalex.org/W6803004859","https://openalex.org/W6804064126","https://openalex.org/W6846157468","https://openalex.org/W6858746968","https://openalex.org/W6910476156"],"related_works":["https://openalex.org/W2006251942","https://openalex.org/W2364741597","https://openalex.org/W2920061524","https://openalex.org/W1492103595","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1864774435","https://openalex.org/W946352265","https://openalex.org/W3020787026","https://openalex.org/W2334479858"],"abstract_inverted_index":{"For":[0],"on-policy":[1,121],"reinforcement":[2],"learning":[3,165],"(RL),":[4],"discretizing":[5],"action":[6,91],"space":[7,92],"for":[8,49,120],"continuous":[9,90],"control":[10,126],"can":[11,40,82,156],"easily":[12],"express":[13],"multiple":[14],"modes":[15],"and":[16,44,117,161],"is":[17],"straightforward":[18,61],"to":[19,72,102],"optimize.":[20],"However,":[21],"without":[22],"considering":[23],"the":[24,28,32,35,50,69,85,88,105,109,141,144],"inherent":[25],"ordering":[26],"between":[27],"discrete":[29,38,70,106,154],"atomic":[30],"actions,":[31],"explosion":[33],"in":[34,87,124,129],"number":[36],"of":[37,143],"actions":[39],"possess":[41],"undesired":[42],"properties":[43],"induce":[45],"a":[46,60,158,163],"higher":[47,118],"variance":[48,142,160],"policy":[51,71,107,155],"gradient":[52],"(PG)":[53],"estimator.":[54],"In":[55],"this":[56,65],"article,":[57],"we":[58],"introduce":[59],"architecture":[62,81],"that":[63,104,149],"addresses":[64],"issue":[66],"by":[67],"constraining":[68],"be":[73],"unimodal":[74,80,95,110,153],"using":[75,93],"Poisson":[76],"probability":[77,96,111],"distributions.":[78,97],"This":[79],"better":[83],"leverage":[84],"continuity":[86],"underlying":[89],"explicit":[94],"We":[98,136],"conduct":[99],"extensive":[100],"experiments":[101],"show":[103],"with":[108],"distribution":[112],"provides":[113],"significantly":[114],"faster":[115],"convergence":[116],"performance":[119],"RL":[122],"algorithms":[123],"challenging":[125],"tasks,":[127],"especially":[128],"highly":[130],"complex":[131],"tasks":[132],"such":[133],"as":[134],"Humanoid.":[135],"provide":[137],"theoretical":[138],"analysis":[139],"on":[140],"PG":[145],"estimator,":[146],"which":[147],"suggests":[148],"our":[150],"attentively":[151],"designed":[152],"retain":[157],"lower":[159],"yield":[162],"stable":[164],"process.":[166]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}