{"id":"https://openalex.org/W4317107930","doi":"https://doi.org/10.3390/e25020188","title":"Maximum Entropy Exploration in Contextual Bandits with Neural Networks and Energy Based Models","display_name":"Maximum Entropy Exploration in Contextual Bandits with Neural Networks and Energy Based Models","publication_year":2023,"publication_date":"2023-01-18","ids":{"openalex":"https://openalex.org/W4317107930","doi":"https://doi.org/10.3390/e25020188","pmid":"https://pubmed.ncbi.nlm.nih.gov/36832555"},"language":"en","primary_location":{"id":"doi:10.3390/e25020188","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/e25020188","pdf_url":"https://www.mdpi.com/1099-4300/25/2/188/pdf","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1099-4300/25/2/188/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073889597","display_name":"Adam Elwood","orcid":"https://orcid.org/0000-0002-6706-8443"},"institutions":[{"id":"https://openalex.org/I305386","display_name":"Colgate-Palmolive (Switzerland)","ror":"https://ror.org/04etgav66","country_code":"CH","type":"company","lineage":["https://openalex.org/I305386","https://openalex.org/I4210135004"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Adam Elwood","raw_affiliation_strings":["lastminute.com Group, Vicolo de Calvi, 2, 6830 Chiasso, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-6706-8443","affiliations":[{"raw_affiliation_string":"lastminute.com Group, Vicolo de Calvi, 2, 6830 Chiasso, Switzerland","institution_ids":["https://openalex.org/I305386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032821603","display_name":"Marco Leonardi","orcid":"https://orcid.org/0000-0002-7989-1162"},"institutions":[{"id":"https://openalex.org/I305386","display_name":"Colgate-Palmolive (Switzerland)","ror":"https://ror.org/04etgav66","country_code":"CH","type":"company","lineage":["https://openalex.org/I305386","https://openalex.org/I4210135004"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Marco Leonardi","raw_affiliation_strings":["lastminute.com Group, Vicolo de Calvi, 2, 6830 Chiasso, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-7989-1162","affiliations":[{"raw_affiliation_string":"lastminute.com Group, Vicolo de Calvi, 2, 6830 Chiasso, Switzerland","institution_ids":["https://openalex.org/I305386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101807440","display_name":"A. Mohamed","orcid":"https://orcid.org/0000-0002-6753-7254"},"institutions":[{"id":"https://openalex.org/I305386","display_name":"Colgate-Palmolive (Switzerland)","ror":"https://ror.org/04etgav66","country_code":"CH","type":"company","lineage":["https://openalex.org/I305386","https://openalex.org/I4210135004"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ashraf Mohamed","raw_affiliation_strings":["lastminute.com Group, Vicolo de Calvi, 2, 6830 Chiasso, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-6753-7254","affiliations":[{"raw_affiliation_string":"lastminute.com Group, Vicolo de Calvi, 2, 6830 Chiasso, Switzerland","institution_ids":["https://openalex.org/I305386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011098514","display_name":"Alessandro Rozza","orcid":"https://orcid.org/0000-0001-6269-1351"},"institutions":[{"id":"https://openalex.org/I305386","display_name":"Colgate-Palmolive (Switzerland)","ror":"https://ror.org/04etgav66","country_code":"CH","type":"company","lineage":["https://openalex.org/I305386","https://openalex.org/I4210135004"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Alessandro Rozza","raw_affiliation_strings":["lastminute.com Group, Vicolo de Calvi, 2, 6830 Chiasso, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-6269-1351","affiliations":[{"raw_affiliation_string":"lastminute.com Group, Vicolo de Calvi, 2, 6830 Chiasso, Switzerland","institution_ids":["https://openalex.org/I305386"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032821603"],"corresponding_institution_ids":["https://openalex.org/I305386"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":0.2466,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53171478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"25","issue":"2","first_page":"188","last_page":"188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9980000257492065,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9980000257492065,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9959999918937683,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9918000102043152,"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/computer-science","display_name":"Computer science","score":0.7526614665985107},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7073087692260742},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.6301794052124023},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5744355916976929},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5662721991539001},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45306262373924255},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4456963539123535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4454357922077179},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.42780473828315735},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3602362871170044},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14415627717971802}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7526614665985107},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7073087692260742},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.6301794052124023},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5744355916976929},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5662721991539001},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45306262373924255},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4456963539123535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4454357922077179},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.42780473828315735},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3602362871170044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14415627717971802},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/e25020188","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/e25020188","pdf_url":"https://www.mdpi.com/1099-4300/25/2/188/pdf","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},{"id":"pmid:36832555","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36832555","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":"Entropy (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9955972","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9955972","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9955972/pdf/entropy-25-00188.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:9894cdbeeb1d45ed9d7ed600fdc99920","is_oa":true,"landing_page_url":"https://doaj.org/article/9894cdbeeb1d45ed9d7ed600fdc99920","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy, Vol 25, Iss 2, p 188 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1099-4300/25/2/188/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/e25020188","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Entropy; Volume 25; Issue 2; Pages: 188","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/e25020188","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/e25020188","pdf_url":"https://www.mdpi.com/1099-4300/25/2/188/pdf","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4317107930.pdf","grobid_xml":"https://content.openalex.org/works/W4317107930.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W148122774","https://openalex.org/W1596437242","https://openalex.org/W1994892978","https://openalex.org/W2009551863","https://openalex.org/W2014114527","https://openalex.org/W2024390895","https://openalex.org/W2033422410","https://openalex.org/W2039522160","https://openalex.org/W2107726111","https://openalex.org/W2113690490","https://openalex.org/W2119738618","https://openalex.org/W2147008239","https://openalex.org/W2148764920","https://openalex.org/W2157376352","https://openalex.org/W2166253248","https://openalex.org/W2182304831","https://openalex.org/W2257979135","https://openalex.org/W2542898981","https://openalex.org/W2594103415","https://openalex.org/W2788991205","https://openalex.org/W2801206439","https://openalex.org/W2896702309","https://openalex.org/W2954040150","https://openalex.org/W2959300817","https://openalex.org/W2963929932","https://openalex.org/W2979605429","https://openalex.org/W2997528551","https://openalex.org/W3083184774","https://openalex.org/W3123802877","https://openalex.org/W3129424093","https://openalex.org/W3135028703","https://openalex.org/W3138288323","https://openalex.org/W3187338714","https://openalex.org/W4226023986","https://openalex.org/W4249083122","https://openalex.org/W6638674303","https://openalex.org/W6639087296","https://openalex.org/W6694077575","https://openalex.org/W6738568706","https://openalex.org/W6751915836","https://openalex.org/W6779558354","https://openalex.org/W6797866537"],"related_works":["https://openalex.org/W4287880334","https://openalex.org/W4366700029","https://openalex.org/W4285230481","https://openalex.org/W4385769873","https://openalex.org/W4281634296","https://openalex.org/W4319161863","https://openalex.org/W2371687270","https://openalex.org/W4311888330","https://openalex.org/W2970690932","https://openalex.org/W2110715801"],"abstract_inverted_index":{"Contextual":[0],"bandits":[1],"can":[2],"solve":[3,15],"a":[4],"huge":[5],"range":[6],"of":[7,41,74,94,106],"real-world":[8],"problems.":[9],"However,":[10],"current":[11],"popular":[12],"algorithms":[13],"to":[14,32,57,166],"them":[16],"either":[17],"rely":[18],"on":[19,54],"linear":[20],"models":[21,108,141],"or":[22],"unreliable":[23],"uncertainty":[24],"estimation":[25],"in":[26,61,109,156],"non-linear":[27,167],"models,":[28,75,89],"which":[29,90],"are":[30,162],"required":[31],"deal":[33],"with":[34,63,77,86,150,169],"the":[35,84,92,104,143],"exploration-exploitation":[36],"trade-off.":[37],"Inspired":[38],"by":[39],"theories":[40],"human":[42],"cognition,":[43],"we":[44],"introduce":[45],"novel":[46],"techniques":[47,121,152],"that":[48,119,153],"use":[49],"maximum":[50],"entropy":[51],"exploration,":[52],"relying":[53],"neural":[55,78],"networks":[56,79],"find":[58],"optimal":[59,97],"policies":[60],"settings":[62],"both":[64,120],"continuous":[65,170],"and":[66,83,111,135,158,161],"discrete":[67],"action":[68,171],"spaces.":[69,172],"We":[70,102,117],"present":[71],"two":[72],"classes":[73],"one":[76],"as":[80,127],"reward":[81,98],"estimators,":[82],"other":[85],"energy":[87,139],"based":[88,140],"model":[91],"probability":[93],"obtaining":[95],"an":[96,100],"given":[99],"action.":[101],"evaluate":[103],"performance":[105],"these":[107],"static":[110,157],"dynamic":[112,159],"contextual":[113],"bandit":[114],"simulation":[115],"environments.":[116],"show":[118],"outperform":[122],"standard":[123],"baseline":[124],"algorithms,":[125],"such":[126],"NN":[128,130],"HMC,":[129],"Discrete,":[131],"Upper":[132],"Confidence":[133],"Bound,":[134],"Thompson":[136],"Sampling,":[137],"where":[138],"have":[142],"best":[144],"overall":[145],"performance.":[146],"This":[147],"provides":[148],"practitioners":[149],"new":[151],"perform":[154],"well":[155,164],"settings,":[160],"particularly":[163],"suited":[165],"scenarios":[168]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-08T06:56:09.383167","created_date":"2025-10-10T00:00:00"}
