{"id":"https://openalex.org/W4416249631","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229044","title":"Value of Information-Enhanced Exploration in Bootstrapped DQN","display_name":"Value of Information-Enhanced Exploration in Bootstrapped DQN","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416249631","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229044"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5120301898","display_name":"Stergios Plataniotis","orcid":null},"institutions":[{"id":"https://openalex.org/I55741626","display_name":"Technical University of Crete","ror":"https://ror.org/03f8bz564","country_code":"GR","type":"education","lineage":["https://openalex.org/I55741626"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Stergios Plataniotis","raw_affiliation_strings":["Technical University of Crete,Chania,Greece"],"affiliations":[{"raw_affiliation_string":"Technical University of Crete,Chania,Greece","institution_ids":["https://openalex.org/I55741626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086892944","display_name":"Charilaos Akasiadis","orcid":"https://orcid.org/0000-0003-0785-4036"},"institutions":[{"id":"https://openalex.org/I55741626","display_name":"Technical University of Crete","ror":"https://ror.org/03f8bz564","country_code":"GR","type":"education","lineage":["https://openalex.org/I55741626"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Charilaos Akasiadis","raw_affiliation_strings":["Technical University of Crete & NCSR \"Demokritos\",Chania,Greece"],"affiliations":[{"raw_affiliation_string":"Technical University of Crete & NCSR \"Demokritos\",Chania,Greece","institution_ids":["https://openalex.org/I55741626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029088756","display_name":"Georgios Chalkiadakis","orcid":"https://orcid.org/0000-0002-0716-2972"},"institutions":[{"id":"https://openalex.org/I55741626","display_name":"Technical University of Crete","ror":"https://ror.org/03f8bz564","country_code":"GR","type":"education","lineage":["https://openalex.org/I55741626"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Georgios Chalkiadakis","raw_affiliation_strings":["Technical University of Crete,Chania,Greece"],"affiliations":[{"raw_affiliation_string":"Technical University of Crete,Chania,Greece","institution_ids":["https://openalex.org/I55741626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5120301898"],"corresponding_institution_ids":["https://openalex.org/I55741626"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19386101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.6728000044822693,"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":0.6728000044822693,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.14669999480247498,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.02070000022649765,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6277999877929688},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5856000185012817},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.569100022315979},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5677000284194946},{"id":"https://openalex.org/keywords/value-of-information","display_name":"Value of information","score":0.475600004196167},{"id":"https://openalex.org/keywords/information-gain","display_name":"Information gain","score":0.4616999924182892},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.3411000072956085}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6277999877929688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6243000030517578},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5856000185012817},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.569100022315979},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5677000284194946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48030000925064087},{"id":"https://openalex.org/C92424840","wikidata":"https://www.wikidata.org/wiki/Q7912772","display_name":"Value of information","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C2983203078","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Information gain","level":2,"score":0.4616999924182892},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3549000024795532},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.3411000072956085},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3402999937534332},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C199354608","wikidata":"https://www.wikidata.org/wiki/Q7316287","display_name":"Restricted Boltzmann machine","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C141042865","wikidata":"https://www.wikidata.org/wiki/Q200125","display_name":"Expected value","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C21031990","wikidata":"https://www.wikidata.org/wiki/Q355020","display_name":"Probability measure","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1557517019","https://openalex.org/W1965555277","https://openalex.org/W2046033161","https://openalex.org/W2128643385","https://openalex.org/W2142971854","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2168405694","https://openalex.org/W2746553466","https://openalex.org/W2996868001","https://openalex.org/W3100366369","https://openalex.org/W3100789280","https://openalex.org/W4296288933","https://openalex.org/W4319165238","https://openalex.org/W4394998532"],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"exploration":[1,21,35,42,70,111],"in":[2,11,140],"deep":[3,69],"reinforcement":[4],"learning":[5,84],"remains":[6],"a":[7],"fundamental":[8],"challenge,":[9],"especially":[10],"environments":[12],"characterized":[13],"by":[14],"high-dimensional":[15],"states":[16],"and":[17,33,43,109,126],"sparse":[18],"rewards.":[19],"Traditional":[20],"strategies":[22],"that":[23,78],"rely":[24],"on":[25],"random":[26,135],"local":[27],"policy":[28],"noise,":[29],"such":[30],"as":[31],"\u03f5-greedy":[32],"Boltzmann":[34],"methods,":[36],"often":[37],"struggle":[38],"to":[39,65,99,124,129],"efficiently":[40],"balance":[41],"exploitation.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,73],"integrate":[49],"the":[50,59,67,80,85,101,115,149],"notion":[51],"of":[52,55,87,96,103,154],"(expected)":[53],"value":[54,86,95],"information":[56,88,97],"(EVOI)":[57],"within":[58],"well-known":[60],"Bootstrapped":[61,90],"DQN":[62],"algorithmic":[63],"framework,":[64],"enhance":[66],"algorithm\u2019s":[68],"ability.":[71],"Specifically,":[72],"develop":[74],"two":[75],"novel":[76],"algorithms":[77,121],"incorporate":[79],"expected":[81],"gain":[82],"from":[83,134],"into":[89],"DQN.":[91],"Our":[92,138],"methods":[93],"use":[94,153],"estimates":[98],"measure":[100],"discrepancies":[102],"opinions":[104],"among":[105],"distinct":[106],"network":[107,136],"heads,":[108],"drive":[110],"towards":[112],"areas":[113],"with":[114,122],"most":[116],"potential.":[117],"We":[118],"evaluate":[119],"our":[120],"respect":[123],"performance":[125],"their":[127],"ability":[128],"exploit":[130],"inherent":[131],"uncertainty":[132],"arising":[133],"initialization.":[137],"experiments":[139],"complex,":[141],"sparse-reward":[142],"Atari":[143],"games":[144],"demonstrate":[145],"increased":[146],"performance,":[147],"all":[148],"while":[150],"making":[151],"better":[152],"uncertainty,":[155],"and,":[156],"importantly,":[157],"without":[158],"introducing":[159],"extra":[160],"hyperparameters.":[161]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}