{"id":"https://openalex.org/W2027028757","doi":"https://doi.org/10.1109/mlsp.2015.7324371","title":"A model based approach to exploration of continuous-state MDPs using Divergence-to-Go","display_name":"A model based approach to exploration of continuous-state MDPs using Divergence-to-Go","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2027028757","doi":"https://doi.org/10.1109/mlsp.2015.7324371","mag":"2027028757"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2015.7324371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2015.7324371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5025034683","display_name":"Matthew S. Emigh","orcid":"https://orcid.org/0000-0002-1438-6069"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Emigh","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Florida, Gainesville, Florida","University of Florida, Department of Electrical and Computer Engineering, Gainesville, Florida 32611"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Florida, Gainesville, Florida","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"University of Florida, Department of Electrical and Computer Engineering, Gainesville, Florida 32611","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008459797","display_name":"Evan Kriminger","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evan Kriminger","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Florida, Gainesville, Florida","University of Florida, Department of Electrical and Computer Engineering, Gainesville, Florida 32611"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Florida, Gainesville, Florida","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"University of Florida, Department of Electrical and Computer Engineering, Gainesville, Florida 32611","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019504861","display_name":"Jos\u00e9 C. Pr\u0131\u0301ncipe","orcid":"https://orcid.org/0000-0002-3449-3531"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jose C. Principe","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Florida, Gainesville, Florida","University of Florida, Department of Electrical and Computer Engineering, Gainesville, Florida 32611"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Florida, Gainesville, Florida","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"University of Florida, Department of Electrical and Computer Engineering, Gainesville, Florida 32611","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9987999796867371,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9890000224113464,"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":0.734605073928833},{"id":"https://openalex.org/keywords/recursion","display_name":"Recursion (computer science)","score":0.7193408608436584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7149721384048462},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.686886727809906},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5917126536369324},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.539496660232544},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5323854684829712},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.520671010017395},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.464994341135025},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.46204113960266113},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4291931390762329},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4156873822212219},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4129827618598938},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3239603042602539},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23326992988586426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14824265241622925},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0875220000743866}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.734605073928833},{"id":"https://openalex.org/C168773036","wikidata":"https://www.wikidata.org/wiki/Q264164","display_name":"Recursion (computer science)","level":2,"score":0.7193408608436584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7149721384048462},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.686886727809906},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5917126536369324},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.539496660232544},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5323854684829712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.520671010017395},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.464994341135025},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.46204113960266113},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4291931390762329},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4156873822212219},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4129827618598938},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3239603042602539},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23326992988586426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14824265241622925},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0875220000743866},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp.2015.7324371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2015.7324371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1496855202","https://openalex.org/W1515851193","https://openalex.org/W1597173708","https://openalex.org/W1624804034","https://openalex.org/W2061504687","https://openalex.org/W2073384958","https://openalex.org/W2124674171","https://openalex.org/W2131831090","https://openalex.org/W2142971854","https://openalex.org/W2145330250","https://openalex.org/W2161966552","https://openalex.org/W2166265228","https://openalex.org/W2168165432","https://openalex.org/W2168405694","https://openalex.org/W2179284380","https://openalex.org/W2181151646","https://openalex.org/W2239029832","https://openalex.org/W2489939061","https://openalex.org/W3049172642","https://openalex.org/W3139377883","https://openalex.org/W4211221179","https://openalex.org/W4214499292","https://openalex.org/W4241649586","https://openalex.org/W4285719527","https://openalex.org/W6629614444","https://openalex.org/W6666117542","https://openalex.org/W6683603353","https://openalex.org/W6684100858","https://openalex.org/W6781870204","https://openalex.org/W6792155000"],"related_works":["https://openalex.org/W1976679120","https://openalex.org/W4281614748","https://openalex.org/W2377519369","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698","https://openalex.org/W4298375133","https://openalex.org/W2951114041","https://openalex.org/W2064126294"],"abstract_inverted_index":{"In":[0,37],"reinforcement":[1],"learning,":[2],"exploration":[3,16],"is":[4,47,83],"typically":[5],"conducted":[6],"by":[7,19],"taking":[8],"occasional":[9],"random":[10],"actions.":[11],"The":[12,81],"literature":[13],"lacks":[14],"an":[15],"method":[17,50,73],"driven":[18],"uncertainty,":[20],"in":[21,32,77],"which":[22,46],"exploratory":[23],"actions":[24],"explicitly":[25],"seek":[26],"to":[27,55,58,74],"improve":[28],"the":[29,60],"learning":[30],"process":[31],"a":[33,42,48,86],"sequential":[34],"decision":[35],"problem.":[36],"this":[38],"paper,":[39],"we":[40],"propose":[41],"framework":[43],"called":[44],"Divergence-to-Go,":[45],"model-based":[49],"that":[51],"uses":[52],"recursion":[53],"similarly":[54],"dynamic":[56],"programming":[57],"quantify":[59],"uncertainty":[61,70],"associated":[62],"with":[63],"each":[64],"state-action":[65],"pair.":[66],"Information-theoretic":[67],"estimators":[68],"of":[69],"allow":[71],"our":[72],"function":[75],"even":[76],"large,":[78],"continuous":[79],"spaces.":[80],"performance":[82],"demonstrated":[84],"on":[85],"maze":[87],"and":[88],"mountain":[89],"car":[90],"task.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}