{"id":"https://openalex.org/W4395661371","doi":"https://doi.org/10.1109/tnnls.2024.3386225","title":"Distributional Policy Gradient With Distributional Value Function","display_name":"Distributional Policy Gradient With Distributional Value Function","publication_year":2024,"publication_date":"2024-04-26","ids":{"openalex":"https://openalex.org/W4395661371","doi":"https://doi.org/10.1109/tnnls.2024.3386225","pmid":"https://pubmed.ncbi.nlm.nih.gov/38669170"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3386225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3386225","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/A5100453159","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0001-7485-6344"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Liu","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677178","display_name":"Yanjie Li","orcid":"https://orcid.org/0000-0001-7890-9677"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjie Li","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101540977","display_name":"Xiongtao Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongtao Shi","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055451322","display_name":"Ke Lin","orcid":"https://orcid.org/0000-0002-3429-5877"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Lin","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064580686","display_name":"Yuecheng Liu","orcid":"https://orcid.org/0000-0002-3683-7959"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuecheng Liu","raw_affiliation_strings":["Huawei Noah’s Ark Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087749601","display_name":"Yunjiang Lou","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjiang Lou","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100453159"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":2.4326,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.89907286,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"36","issue":"4","first_page":"6556","last_page":"6568"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9886000156402588,"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":0.9886000156402588,"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/quantile","display_name":"Quantile","score":0.5648829340934753},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.540594220161438},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.5147204995155334},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5005617141723633},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4854724705219269},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.48514875769615173},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4783365726470947},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.46409884095191956},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4252963662147522},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.35308003425598145},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31686925888061523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1387403905391693},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06288430094718933}],"concepts":[{"id":"https://openalex.org/C118671147","wikidata":"https://www.wikidata.org/wiki/Q578714","display_name":"Quantile","level":2,"score":0.5648829340934753},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.540594220161438},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.5147204995155334},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5005617141723633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4854724705219269},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.48514875769615173},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4783365726470947},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.46409884095191956},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4252963662147522},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.35308003425598145},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31686925888061523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1387403905391693},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06288430094718933},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3386225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3386225","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:38669170","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38669170","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":[{"display_name":"Reduced inequalities","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1665521743","display_name":null,"funder_award_id":"61977019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7386022970","display_name":null,"funder_award_id":"U1813206","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2046765929","https://openalex.org/W2067707835","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2158782408","https://openalex.org/W2172968643","https://openalex.org/W2328111639","https://openalex.org/W2746553466","https://openalex.org/W2765302304","https://openalex.org/W2910568379","https://openalex.org/W2990211277","https://openalex.org/W2999778183","https://openalex.org/W3000642679","https://openalex.org/W3015082424","https://openalex.org/W3126763268","https://openalex.org/W3173211893","https://openalex.org/W4241996101","https://openalex.org/W4306830960","https://openalex.org/W4382239271","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6683204974","https://openalex.org/W6683300800","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6737327832","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748554570","https://openalex.org/W6748839928","https://openalex.org/W6750645735","https://openalex.org/W6751629939","https://openalex.org/W6759679099","https://openalex.org/W6763153117","https://openalex.org/W6767112054","https://openalex.org/W6857414025","https://openalex.org/W6858087789"],"related_works":["https://openalex.org/W1488761988","https://openalex.org/W2044551864","https://openalex.org/W1572557500","https://openalex.org/W3124946120","https://openalex.org/W4390690393","https://openalex.org/W2047938026","https://openalex.org/W2585269888","https://openalex.org/W3132003399","https://openalex.org/W4293365552","https://openalex.org/W2042102171"],"abstract_inverted_index":{"In":[0,202,213],"this":[1,98],"article,":[2],"we":[3,101,136,148,223],"propose":[4,102,137,149],"a":[5,28,39,103,109,150,167,231],"distributional":[6,11,32,77,94,104,110,179],"policy-gradient":[7,89,105,132,139,156,180,228],"method":[8,106,152,181,207,229],"based":[9],"on":[10,240],"reinforcement":[12],"learning":[13],"(RL)":[14],"and":[15,42,193,243],"policy":[16,115,123,145,187],"gradient.":[17],"Conventional":[18],"RL":[19,33,78,85,133],"algorithms":[20,34],"typically":[21],"estimate":[22,43,119],"the":[23,36,44,50,60,114,120,127,155,160,177,183,186,190,205,209,216,226,235,248,251],"expectation":[24,128],"of":[25,52,93,122,126,163,185,234,250],"return,":[26],"given":[27],"state-action":[29],"pair.":[30],"Furthermore,":[31,135],"consider":[35],"return":[37,45,61,164],"as":[38],"random":[40],"variable":[41],"distribution":[46,62,121],"that":[47,153,225],"can":[48],"characterize":[49],"probability":[51,162],"different":[53],"returns":[54],"resulted":[55],"by":[56,107],"environmental":[57],"uncertainties.":[58],"Thus,":[59],"provides":[63],"more":[64],"valuable":[65],"information":[66],"than":[67],"its":[68],"expectation,":[69],"leading":[70],"to":[71,113,143,159,195],"superior":[72],"policies":[73],"in":[74,83,130,256],"general.":[75],"Although":[76],"has":[79],"been":[80],"investigated":[81],"widely":[82],"value-based":[84],"methods,":[86],"very":[87],"few":[88],"methods":[90],"take":[91],"advantage":[92],"RL.":[95],"To":[96],"bridge":[97],"research":[99],"gap,":[100],"introducing":[108],"value":[111,140,157],"function":[112],"gradient":[116,124],"(DVDPG).":[117],"We":[118],"instead":[125],"estimated":[129],"conventional":[131,227],"methods.":[134],"two":[138,217],"sampling":[141],"mechanisms":[142,219],"do":[144],"improvement.":[146],"First,":[147],"distribution-probability-sampling":[151,206],"samples":[154],"according":[158],"quantile":[161],"distribution.":[165],"Second,":[166],"uniform":[168,210],"sample":[169,175,211,218],"mechanism":[170],"is":[171,230],"proposed.":[172],"With":[173],"our":[174],"mechanisms,":[176],"proposed":[178,236,252],"enhances":[182],"stochasticity":[184],"gradient,":[188],"improving":[189],"exploration":[191],"efficiency":[192,249],"benefiting":[194],"avoid":[196],"falling":[197],"into":[198],"local":[199],"optimal":[200],"solutions.":[201],"sparse-reward":[203,242],"tasks,":[204,215],"outperforms":[208],"mechanism.":[212],"dense-reward":[214,244],"perform":[220],"similarly.":[221],"Moreover,":[222],"show":[224],"special":[232],"case":[233],"method.":[237],"Experimental":[238],"results":[239],"various":[241],"OpenAI-gym":[245],"tasks":[246],"illustrate":[247],"method,":[253],"outperforming":[254],"baselines":[255],"almost":[257],"environments.":[258]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}