{"id":"https://openalex.org/W2787825303","doi":"https://doi.org/10.1109/ssci.2017.8280923","title":"Exploiting structure and uncertainty of Bellman updates in Markov decision processes","display_name":"Exploiting structure and uncertainty of Bellman updates in Markov decision processes","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2787825303","doi":"https://doi.org/10.1109/ssci.2017.8280923","mag":"2787825303"},"language":"en","primary_location":{"id":"doi:10.1109/ssci.2017.8280923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2017.8280923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5001304610","display_name":"Davide Tateo","orcid":"https://orcid.org/0000-0002-7193-923X"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Tateo","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063752250","display_name":"Carlo D\u2019Eramo","orcid":"https://orcid.org/0000-0003-2712-118X"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Carlo D'Eramo","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067576188","display_name":"Alessandro Nuara","orcid":"https://orcid.org/0000-0002-6379-0260"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Nuara","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017130830","display_name":"Marcello Restelli","orcid":"https://orcid.org/0000-0002-6322-1076"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marcello Restelli","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060263666","display_name":"Andrea Bonarini","orcid":"https://orcid.org/0000-0002-4880-4521"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Bonarini","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering, Politecnico Di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.988099992275238,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.979200005531311,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7863619327545166},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7772737741470337},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7213469743728638},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5437021255493164},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5432852506637573},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.49768903851509094},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4934808015823364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47592929005622864},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4632369875907898},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4473973512649536},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44405052065849304},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4401717185974121},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.43966346979141235},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.4342729151248932},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4272571802139282},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.4241299033164978},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4193441867828369},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.3554379343986511},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2589030861854553},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2167365849018097},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18461012840270996},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10681045055389404}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7863619327545166},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7772737741470337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7213469743728638},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5437021255493164},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5432852506637573},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.49768903851509094},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4934808015823364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47592929005622864},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4632369875907898},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4473973512649536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44405052065849304},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4401717185974121},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.43966346979141235},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4342729151248932},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4272571802139282},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4241299033164978},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4193441867828369},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3554379343986511},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2589030861854553},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2167365849018097},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18461012840270996},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10681045055389404},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ssci.2017.8280923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2017.8280923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1045583","is_oa":false,"landing_page_url":"http://hdl.handle.net/11311/1045583","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W60656810","https://openalex.org/W1499669280","https://openalex.org/W1784384189","https://openalex.org/W1983264093","https://openalex.org/W1996089295","https://openalex.org/W1996579288","https://openalex.org/W2027591961","https://openalex.org/W2093253120","https://openalex.org/W2117341272","https://openalex.org/W2118686230","https://openalex.org/W2145339207","https://openalex.org/W2148032815","https://openalex.org/W2149166950","https://openalex.org/W2155355065","https://openalex.org/W2155968351","https://openalex.org/W2159309155","https://openalex.org/W2194966727","https://openalex.org/W2469051754","https://openalex.org/W2746553466","https://openalex.org/W6629881138","https://openalex.org/W6677067356","https://openalex.org/W6677347465","https://openalex.org/W6681795105"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W3096874164","https://openalex.org/W1589140671","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W1985560493","https://openalex.org/W2294884454","https://openalex.org/W2386410636"],"abstract_inverted_index":{"In":[0],"many":[1],"real-world":[2],"problems":[3],"stochasticity":[4,16],"is":[5,78],"a":[6,39,100],"critical":[7],"issue":[8],"for":[9],"the":[10,19,22,26,35,53,64,67,75,79,83,104,107,111,114,121,127],"learning":[11,84],"process.":[12],"The":[13],"sources":[14],"of":[15,25,34,42,52,66,106,113,123],"come":[17],"from":[18,31],"transition":[20],"model,":[21],"explorative":[23],"component":[24],"policy":[27],"or,":[28],"even":[29],"worse,":[30],"noisy":[32],"observations":[33],"reward":[36],"function.":[37],"For":[38],"finite":[40],"number":[41],"samples,":[43],"traditional":[44],"Reinforcement":[45],"Learning":[46],"(RL)":[47],"methods":[48],"provide":[49],"biased":[50],"estimates":[51],"action-value":[54],"function":[55],"possibly":[56],"leading":[57],"to":[58,118,152],"poor":[59],"estimates,":[60],"then":[61],"propagated":[62],"by":[63,126],"application":[65],"Bellman":[68,108],"operator.":[69],"While":[70],"some":[71,90],"approaches":[72],"assume":[73],"that":[74,88,102,159],"estimation":[76,115],"bias":[77,162],"key":[80],"problem":[81],"in":[82,89,116,145,148,150],"process,":[85],"we":[86,142],"show":[87,130],"cases":[91],"this":[92,134],"assumption":[93],"does":[94],"not":[95],"necessarily":[96],"hold.":[97],"We":[98,129],"propose":[99],"method":[101,135],"exploits":[103],"structure":[105],"update":[109],"and":[110,136,163],"uncertainty":[112],"order":[117,151],"better":[119],"use":[120],"amount":[122],"information":[124],"provided":[125],"samples.":[128],"theoretical":[131],"considerations":[132],"about":[133],"its":[137,154],"relation":[138],"w.r.t.":[139],"Q-Learning.":[140],"Moreover,":[141],"test":[143],"it":[144],"environments":[146],"available":[147],"literature":[149],"demonstrate":[153],"effectiveness":[155],"against":[156],"other":[157],"algorithms":[158],"focus":[160],"on":[161],"sample-efficiency.":[164]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}