{"id":"https://openalex.org/W4360584370","doi":"https://doi.org/10.1109/tcyb.2023.3254596","title":"Implicit Posteriori Parameter Distribution Optimization in Reinforcement Learning","display_name":"Implicit Posteriori Parameter Distribution Optimization in Reinforcement Learning","publication_year":2023,"publication_date":"2023-03-22","ids":{"openalex":"https://openalex.org/W4360584370","doi":"https://doi.org/10.1109/tcyb.2023.3254596","pmid":"https://pubmed.ncbi.nlm.nih.gov/37030741"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2023.3254596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2023.3254596","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","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/A5100460614","display_name":"Tianyi Li","orcid":"https://orcid.org/0000-0002-9423-6369"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianyi Li","raw_affiliation_strings":["Ningbo Artificial Intelligence Institute, Department of Automation, Shanghai Jiao Tong University, Shanghai, China","Ningbo Artificial Intelligence Institute and the Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Ningbo Artificial Intelligence Institute, Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Ningbo Artificial Intelligence Institute and the Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001818611","display_name":"Genke Yang","orcid":"https://orcid.org/0000-0003-3492-0211"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Genke Yang","raw_affiliation_strings":["Ningbo Artificial Intelligence Institute, Department of Automation, Shanghai Jiao Tong University, Shanghai, China","Ningbo Artificial Intelligence Institute and the Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Ningbo Artificial Intelligence Institute, Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Ningbo Artificial Intelligence Institute and the Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013715544","display_name":"Jian Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Chu","raw_affiliation_strings":["Ningbo Artificial Intelligence Institute, Department of Automation, Shanghai Jiao Tong University, Shanghai, China","Ningbo Artificial Intelligence Institute and the Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Ningbo Artificial Intelligence Institute, Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Ningbo Artificial Intelligence Institute and the Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100460614"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.9202,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88270778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"54","issue":"5","first_page":"3051","last_page":"3064"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9932000041007996,"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/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.6310005187988281},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6304891705513},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6051317453384399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5021910667419434},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.483767032623291},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.47423499822616577},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4526687264442444},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.45113688707351685},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44803473353385925},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4364163279533386},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.43019479513168335},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.40192368626594543},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3396530747413635},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29339540004730225},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08191227912902832}],"concepts":[{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.6310005187988281},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6304891705513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6051317453384399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5021910667419434},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.483767032623291},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.47423499822616577},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4526687264442444},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.45113688707351685},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44803473353385925},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4364163279533386},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.43019479513168335},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.40192368626594543},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3396530747413635},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29339540004730225},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08191227912902832},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2023.3254596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2023.3254596","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:37030741","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37030741","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 cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2158782408","https://openalex.org/W2586702902","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2765302304","https://openalex.org/W2788904251","https://openalex.org/W2887063112","https://openalex.org/W2919115771","https://openalex.org/W2963523627","https://openalex.org/W2963746531","https://openalex.org/W2982316857","https://openalex.org/W2982570199","https://openalex.org/W2996695841","https://openalex.org/W3018036994","https://openalex.org/W3092253573","https://openalex.org/W3096831136","https://openalex.org/W3110392801","https://openalex.org/W3129322645","https://openalex.org/W3130292943","https://openalex.org/W3173586751","https://openalex.org/W4206024271","https://openalex.org/W4214717370","https://openalex.org/W4280508537","https://openalex.org/W6617145748","https://openalex.org/W6683300800","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6695011786","https://openalex.org/W6716474083","https://openalex.org/W6725708968","https://openalex.org/W6729956949","https://openalex.org/W6731334075","https://openalex.org/W6734517396","https://openalex.org/W6739193204","https://openalex.org/W6740092555","https://openalex.org/W6748839928","https://openalex.org/W6751500528","https://openalex.org/W6756303580","https://openalex.org/W6758552157","https://openalex.org/W6764214684","https://openalex.org/W6770190457","https://openalex.org/W6775002472","https://openalex.org/W6775098822","https://openalex.org/W6782022165","https://openalex.org/W6788186211","https://openalex.org/W6794739717","https://openalex.org/W7000968630"],"related_works":["https://openalex.org/W1839961359","https://openalex.org/W2075146114","https://openalex.org/W2150865841","https://openalex.org/W2100805585","https://openalex.org/W2138865713","https://openalex.org/W2169353922","https://openalex.org/W2164129707","https://openalex.org/W4292122269","https://openalex.org/W2949366006","https://openalex.org/W2015071961"],"abstract_inverted_index":{"Efficient":[0],"and":[1,66,76,102,200,222],"intelligent":[2],"exploration":[3,30,77],"remains":[4],"a":[5,19,54,84,96,119,170,219],"major":[6],"challenge":[7],"in":[8,129],"the":[9,29,33,61,68,100,130,155,183,196,209,214],"field":[10],"of":[11,32,63],"deep":[12],"reinforcement":[13],"learning":[14,185],"(DRL).":[15],"Bayesian":[16,39,80],"inference":[17],"with":[18,105,150,190],"distributional":[20,97],"representation":[21,65],"is":[22,110,159],"usually":[23],"an":[24,48,106,139,146],"effective":[25],"way":[26],"to":[27,46,72,118,133,137,153,181],"improve":[28,73,182],"ability":[31],"RL":[34],"agent.":[35],"However,":[36],"when":[37],"optimizing":[38],"neural":[40],"networks":[41],"(BNNs),":[42],"most":[43],"algorithms":[44,194],"need":[45],"specify":[47],"explicit":[49],"parameter":[50,88,101,142,215],"distribution":[51,89,157],"such":[52],"as":[53],"multivariate":[55],"Gaussian":[56],"distribution.":[57],"This":[58],"may":[59],"reduce":[60],"flexibility":[62],"model":[64,103,116,148,184],"affect":[67],"algorithm":[69,172,211],"performance.":[70],"Therefore,":[71],"sample":[74],"efficiency":[75],"based":[78,173],"on":[79,99,174,195,204],"methods,":[81],"we":[82,94,144,168],"propose":[83],"novel":[85],"implicit":[86,107,140,156],"posteriori":[87,141],"optimization":[90],"(IPPDO)":[91],"algorithm.":[92],"First,":[93],"adopt":[95],"perspective":[98],"it":[104,135],"distribution,":[108,143],"which":[109,158],"approximated":[111],"by":[112,162],"generative":[113],"models.":[114],"Each":[115],"corresponds":[117],"learned":[120,220],"latent":[121],"space,":[122],"providing":[123],"structured":[124],"stochasticity":[125],"for":[126,218],"each":[127],"layer":[128],"network.":[131],"Next,":[132],"make":[134],"possible":[136],"optimize":[138],"build":[145],"energy-based":[147],"(EBM)":[149],"value":[151],"function":[152],"represent":[154,213],"not":[160],"constrained":[161],"any":[163],"analytic":[164],"density":[165],"function.":[166],"Then,":[167],"design":[169],"training":[171],"amortized":[175],"Stein":[176],"variational":[177],"gradient":[178],"descent":[179],"(SVGD)":[180],"efficiency.":[186],"We":[187],"compare":[188],"IPPDO":[189],"other":[191],"prevailing":[192],"DRL":[193],"OpenAI":[197],"Gym,":[198],"MuJoCo,":[199],"Box2D":[201],"platforms.":[202],"Experiments":[203],"various":[205],"tasks":[206],"demonstrate":[207],"that":[208],"proposed":[210],"can":[212,223],"uncertainty":[216],"implicitly":[217],"policy":[221],"consistently":[224],"outperform":[225],"competing":[226],"approaches.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}