{"id":"https://openalex.org/W1869302287","doi":"https://doi.org/10.48550/arxiv.2604.27563","title":"Bayesian policy gradient and actor-critic algorithms","display_name":"Bayesian policy gradient and actor-critic algorithms","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W1869302287","doi":"https://doi.org/10.48550/arxiv.2604.27563","mag":"1869302287"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2604.27563","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.27563","pdf_url":"https://arxiv.org/pdf/2604.27563","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2604.27563","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013843778","display_name":"Mohammad Ghavamzadeh","orcid":"https://orcid.org/0000-0003-0930-8688"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ghavamzadeh, Mohammad","raw_affiliation_strings":["Sequential Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sequential Learning","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044106007","display_name":"Yaakov Engel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121368","display_name":"Machine Science","ror":"https://ror.org/02hrr9v50","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210121368"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Engel, Yaakov","raw_affiliation_strings":["Machine Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning","institution_ids":["https://openalex.org/I4210121368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106038276","display_name":"Michal Valko","orcid":"https://orcid.org/0009-0007-8593-7765"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Valko, Michal","raw_affiliation_strings":["Sequential Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sequential Learning","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9973000288009644,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.5739190578460693},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.5262460112571716},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5015246868133545},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4904043674468994},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.4868027865886688},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.47980526089668274},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4292660355567932},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38816970586776733},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.34887799620628357},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.348399817943573},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.30463266372680664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2997521758079529},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09949609637260437},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08252191543579102}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5739190578460693},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5262460112571716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5015246868133545},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4904043674468994},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.4868027865886688},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.47980526089668274},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4292660355567932},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38816970586776733},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.34887799620628357},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.348399817943573},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.30463266372680664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2997521758079529},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09949609637260437},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08252191543579102},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2604.27563","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.27563","pdf_url":"https://arxiv.org/pdf/2604.27563","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/25407","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/25407","pdf_url":"http://hdl.handle.net/20.500.12210/25407","source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'Etudes en Civilisations, Langues et Litt\u00e9ratures Etrang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:HAL:hal-00776608v2","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-00776608","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research, 2016, 17 (66), pp.1-53","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2604.27563","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27563","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2604.27563","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.27563","pdf_url":"https://arxiv.org/pdf/2604.27563","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1869302287.pdf","grobid_xml":"https://content.openalex.org/works/W1869302287.grobid-xml"},"referenced_works_count":86,"referenced_works":["https://openalex.org/W52822972","https://openalex.org/W148122774","https://openalex.org/W263682811","https://openalex.org/W658381347","https://openalex.org/W1496855202","https://openalex.org/W1510073064","https://openalex.org/W1515851193","https://openalex.org/W1528131421","https://openalex.org/W1564755532","https://openalex.org/W1569296262","https://openalex.org/W1575236038","https://openalex.org/W1576452626","https://openalex.org/W1582436621","https://openalex.org/W1591675293","https://openalex.org/W1594783240","https://openalex.org/W1746819321","https://openalex.org/W1814308503","https://openalex.org/W1911551976","https://openalex.org/W1965786092","https://openalex.org/W1970602736","https://openalex.org/W1972336342","https://openalex.org/W1988071341","https://openalex.org/W2011418219","https://openalex.org/W2031571562","https://openalex.org/W2034725503","https://openalex.org/W2039091159","https://openalex.org/W2046727971","https://openalex.org/W2046765929","https://openalex.org/W2050941272","https://openalex.org/W2051195188","https://openalex.org/W2071814471","https://openalex.org/W2080759927","https://openalex.org/W2091565802","https://openalex.org/W2092092836","https://openalex.org/W2094387729","https://openalex.org/W2100785108","https://openalex.org/W2108682071","https://openalex.org/W2108738385","https://openalex.org/W2110720940","https://openalex.org/W2112925200","https://openalex.org/W2114537044","https://openalex.org/W2116459397","https://openalex.org/W2119717200","https://openalex.org/W2119914747","https://openalex.org/W2124352385","https://openalex.org/W2125612430","https://openalex.org/W2125710232","https://openalex.org/W2128643385","https://openalex.org/W2129564505","https://openalex.org/W2130801532","https://openalex.org/W2132057084","https://openalex.org/W2132849848","https://openalex.org/W2133733518","https://openalex.org/W2134197408","https://openalex.org/W2135681007","https://openalex.org/W2136602922","https://openalex.org/W2141645258","https://openalex.org/W2142592520","https://openalex.org/W2144794447","https://openalex.org/W2155027007","https://openalex.org/W2156718681","https://openalex.org/W2156737235","https://openalex.org/W2156974606","https://openalex.org/W2157580235","https://openalex.org/W2158125716","https://openalex.org/W2158319693","https://openalex.org/W2162979096","https://openalex.org/W2163037893","https://openalex.org/W2164569010","https://openalex.org/W2166253248","https://openalex.org/W2166473218","https://openalex.org/W2167061265","https://openalex.org/W2168359464","https://openalex.org/W2169743339","https://openalex.org/W2182000050","https://openalex.org/W2325958504","https://openalex.org/W2334782222","https://openalex.org/W2406242985","https://openalex.org/W2551251242","https://openalex.org/W2962901934","https://openalex.org/W2963214119","https://openalex.org/W3103182070","https://openalex.org/W3123298421","https://openalex.org/W3125634603","https://openalex.org/W3139377883","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4300066510","https://openalex.org/W1971337326","https://openalex.org/W2056958800","https://openalex.org/W4213259725","https://openalex.org/W4311388919","https://openalex.org/W1964490787","https://openalex.org/W2060696366","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"Policy":[0],"gradient":[1,16,20,57,72,79,88,92,156,232,253,262],"methods":[2,21],"are":[3,94],"reinforcement":[4,268],"learning":[5,162,269],"algorithms":[6,256],"that":[7],"adapt":[8],"a":[9,14,46,59,81,159,166,188,265],"parameterized":[10],"policy":[11,19,50,56,155,214,241,252,261],"by":[12],"following":[13],"performance":[15],"estimate.":[17],"Conventional":[18],"use":[22],"Monte-Carlo":[23,259],"techniques":[24],"to":[25,31,69,120,130,194,197,239],"estimate":[26],"the":[27,55,64,77,84,87,91,101,116,135,140,144,184,199,207,213,218,228,231,234,240,249],"gradient,":[28,51],"which":[29,165],"tend":[30],"have":[32],"high":[33],"variance,":[34],"requiring":[35],"many":[36],"samples":[37,67],"and":[38,80,126,216,254],"resulting":[39],"in":[40,86,164],"slow":[41],"convergence.":[42],"We":[43,243],"first":[44],"propose":[45],"Bayesian":[47,154,167,251],"framework":[48,103,157],"for":[49,227],"based":[52,172,260],"on":[53,173,206,264],"modeling":[54],"as":[58,107,187],"Gaussian":[60,174,189],"process.":[61],"This":[62],"reduces":[63],"number":[65,266],"of":[66,76,83,122,169,212,217,230,233,248,267],"needed":[68],"obtain":[70],"accurate":[71],"estimates.":[73],"Moreover,":[74],"estimates":[75],"natural":[78],"measure":[82],"uncertainty":[85],"estimates,":[89],"namely,":[90],"covariance,":[93],"provided":[95],"at":[96],"little":[97],"extra":[98],"cost.":[99],"Since":[100],"proposed":[102,250],"considers":[104],"system":[105,145],"trajectories":[106,119],"its":[108],"basic":[109],"observable":[110,132],"unit,":[111],"it":[112,137],"does":[113],"not":[114],"require":[115],"dynamics":[117],"within":[118],"be":[121,128,195],"any":[123],"particular":[124],"form,":[125],"can":[127],"extended":[129],"partially":[131],"problems.":[133,270],"On":[134],"downside,":[136],"cannot":[138],"exploit":[139],"Markov":[141],"property":[142],"when":[143],"is":[146,179],"Markovian.":[147],"To":[148],"address":[149],"this,":[150],"we":[151],"supplement":[152],"our":[153],"with":[158,237,257],"new":[160],"actor-critic":[161,255],"model":[163,183],"class":[168],"non-parametric":[170],"critics,":[171],"process":[175],"temporal":[176],"difference":[177],"learning,":[178],"used.":[180],"Such":[181],"critics":[182],"action-value":[185,203],"function":[186],"process,":[190],"allowing":[191],"Bayes":[192],"rule":[193],"used":[196],"compute":[198],"posterior":[200,229],"distribution":[201],"over":[202],"functions,":[204],"conditioned":[205],"observed":[208],"data.":[209],"Appropriate":[210],"choices":[211],"parameterization":[215],"prior":[219],"covariance":[220],"(kernel)":[221],"between":[222],"action-values":[223],"yield":[224],"closed-form":[225],"expressions":[226],"expected":[235],"return":[236],"respect":[238],"parameters.":[242],"perform":[244],"detailed":[245],"experimental":[246],"comparisons":[247],"classic":[258],"methods,":[263]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2016-06-24T00:00:00"}