{"id":"https://openalex.org/W2977326086","doi":"https://doi.org/10.1109/ijcnn.2019.8851736","title":"Exploration Driven by an Optimistic Bellman Equation","display_name":"Exploration Driven by an Optimistic Bellman Equation","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2977326086","doi":"https://doi.org/10.1109/ijcnn.2019.8851736","mag":"2977326086"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8851736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","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/A5051476305","display_name":"Samuele Tosatto","orcid":"https://orcid.org/0000-0002-5795-9541"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Samuele Tosatto","raw_affiliation_strings":["Intelligent Autonomous Systems, Technische Universit\u00e4t Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems, Technische Universit\u00e4t Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"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":["AIRLab, Politecnico di Milano, Milano, Italy"],"affiliations":[{"raw_affiliation_string":"AIRLab, Politecnico di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017983137","display_name":"Joni Pajarinen","orcid":"https://orcid.org/0000-0003-4469-8191"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Joni Pajarinen","raw_affiliation_strings":["Intelligent Autonomous Systems, Technische Universit\u00e4t Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems, Technische Universit\u00e4t Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"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":["AIRLab, Politecnico di Milano, Milano, Italy"],"affiliations":[{"raw_affiliation_string":"AIRLab, Politecnico di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Intelligent Autonomous Systems, Technische Universit\u00e4t Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems, Technische Universit\u00e4t Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051476305"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66045603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","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":0.9988999962806702,"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":0.9988999962806702,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9945999979972839,"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"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9782999753952026,"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":0.8466203212738037},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6920947432518005},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6607683897018433},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6495110988616943},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5676819682121277},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5582406520843506},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5467239618301392},{"id":"https://openalex.org/keywords/entropy-maximization","display_name":"Entropy maximization","score":0.48556992411613464},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4845694601535797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4784417450428009},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.42443108558654785},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41131314635276794},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.378118634223938},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20447760820388794}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8466203212738037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6920947432518005},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6607683897018433},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6495110988616943},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5676819682121277},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5582406520843506},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5467239618301392},{"id":"https://openalex.org/C127233936","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Entropy maximization","level":3,"score":0.48556992411613464},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4845694601535797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4784417450428009},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.42443108558654785},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41131314635276794},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.378118634223938},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20447760820388794},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn.2019.8851736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1121460","is_oa":false,"landing_page_url":"http://hdl.handle.net/11311/1121460","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":"","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":68,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1499669280","https://openalex.org/W1515933446","https://openalex.org/W1582436621","https://openalex.org/W1588514005","https://openalex.org/W1591803298","https://openalex.org/W1680245855","https://openalex.org/W1771410628","https://openalex.org/W1850488217","https://openalex.org/W1862757251","https://openalex.org/W2001009060","https://openalex.org/W2009551863","https://openalex.org/W2088413745","https://openalex.org/W2100805904","https://openalex.org/W2105114545","https://openalex.org/W2107726111","https://openalex.org/W2111764152","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2129620190","https://openalex.org/W2139612737","https://openalex.org/W2144744117","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2155836220","https://openalex.org/W2156974606","https://openalex.org/W2161966552","https://openalex.org/W2165131254","https://openalex.org/W2280163991","https://openalex.org/W2489939061","https://openalex.org/W2596982695","https://openalex.org/W2619268125","https://openalex.org/W2736601468","https://openalex.org/W2751973545","https://openalex.org/W2755611049","https://openalex.org/W2963169817","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2963751259","https://openalex.org/W2963797557","https://openalex.org/W2963938771","https://openalex.org/W2964043796","https://openalex.org/W3020125231","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W4293871015","https://openalex.org/W4297814233","https://openalex.org/W6634907821","https://openalex.org/W6635327058","https://openalex.org/W6637368805","https://openalex.org/W6638018090","https://openalex.org/W6639039794","https://openalex.org/W6676013068","https://openalex.org/W6676833704","https://openalex.org/W6678114464","https://openalex.org/W6680292960","https://openalex.org/W6683091424","https://openalex.org/W6683204974","https://openalex.org/W6683603353","https://openalex.org/W6692846177","https://openalex.org/W6695011786","https://openalex.org/W6717230150","https://openalex.org/W6735033012","https://openalex.org/W6738370996","https://openalex.org/W6739455066","https://openalex.org/W6741002519","https://openalex.org/W6780559895","https://openalex.org/W7062612498"],"related_works":["https://openalex.org/W3102188974","https://openalex.org/W3004810941","https://openalex.org/W4287870705","https://openalex.org/W3199097846","https://openalex.org/W624081655","https://openalex.org/W2951493954","https://openalex.org/W2576492542","https://openalex.org/W1952656308","https://openalex.org/W2073182819","https://openalex.org/W2267645079"],"abstract_inverted_index":{"Exploring":[0],"high-dimensional":[1],"state":[2],"spaces":[3],"and":[4,87,107,134,161],"finding":[5],"sparse":[6],"rewards":[7],"are":[8,16],"central":[9],"problems":[10],"in":[11,114],"reinforcement":[12,31,52],"learning.":[13],"Exploration":[14],"strategies":[15],"frequently":[17],"either":[18],"na\u00efve":[19],"(e.g.,":[20],"simplistic-greedy":[21],"or":[22,33],"Boltzmann":[23],"policies),":[24],"intractable":[25],"(i.e.,":[26],"full":[27],"Bayesian":[28],"treatment":[29],"of":[30,40,51,58,70,83,131,147,156],"learning)":[32],"rely":[34],"heavily":[35],"on":[36,67,168],"heuristics.":[37],"The":[38,120],"lack":[39],"a":[41,55,102,128,144],"tractable":[42],"but":[43],"principled":[44],"exploration":[45,61,111,116,122],"approach":[46],"unnecessarily":[47],"complicates":[48],"the":[49,68,71,77,157],"application":[50,155],"learning":[53],"to":[54,143],"broader":[56],"range":[57,146],"problems.":[59],"Efficient":[60],"can":[62,124,140],"be":[63,125,141],"accomplished":[64],"by":[65],"relying":[66],"uncertainty":[69],"state-action":[72],"value":[73,84],"function.":[74],"To":[75],"obtain":[76],"uncertainty,":[78],"we":[79],"maintain":[80],"an":[81,89,109,154],"ensemble":[82],"function":[85],"estimates":[86],"present":[88],"optimistic":[90],"Bellman":[91],"equation":[92],"(OBE)":[93],"for":[94],"such":[95],"ensembles.":[96],"This":[97],"OBE":[98,139],"is":[99],"derived":[100],"from":[101],"relative":[103],"entropy":[104],"maximization":[105],"principle":[106],"yields":[108],"implicit":[110],"bonus":[112,123],"resulting":[113],"improved":[115],"during":[117],"action":[118],"selection.":[119],"implied":[121],"seen":[126],"as":[127,153],"well-principled":[129],"type":[130],"intrinsic":[132],"motivation":[133],"exhibits":[135],"favorable":[136],"theoretical":[137],"properties.":[138],"applied":[142],"wide":[145],"algorithms.":[148],"We":[149],"propose":[150],"two":[151],"algorithms":[152],"principle:":[158],"Optimistic":[159,162],"Q-learning":[160],"DQN":[163],"which":[164],"outperform":[165],"comparison":[166],"methods":[167],"standard":[169],"benchmarks.":[170]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}