{"id":"https://openalex.org/W4289861370","doi":"https://doi.org/10.3390/s22155845","title":"Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning","display_name":"Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-08-04","ids":{"openalex":"https://openalex.org/W4289861370","doi":"https://doi.org/10.3390/s22155845","pmid":"https://pubmed.ncbi.nlm.nih.gov/35957399"},"language":"en","primary_location":{"id":"doi:10.3390/s22155845","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22155845","pdf_url":"https://www.mdpi.com/1424-8220/22/15/5845/pdf?version=1660213704","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"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":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/22/15/5845/pdf?version=1660213704","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070677616","display_name":"Sooyoung Jang","orcid":"https://orcid.org/0000-0002-6931-9592"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sooyoung Jang","raw_affiliation_strings":["Intelligence Convergence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon 34129, Korea"],"raw_orcid":"https://orcid.org/0000-0002-6931-9592","affiliations":[{"raw_affiliation_string":"Intelligence Convergence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon 34129, Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038009350","display_name":"Hyung-Il Kim","orcid":"https://orcid.org/0000-0001-6425-549X"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyung-Il Kim","raw_affiliation_strings":["Artificial Intelligence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon 34129, Korea"],"raw_orcid":"https://orcid.org/0000-0001-6425-549X","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon 34129, Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038009350"],"corresponding_institution_ids":["https://openalex.org/I142401562"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":0.9711,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79635233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"22","issue":"15","first_page":"5845","last_page":"5845"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.982200026512146,"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/T10260","display_name":"Software Engineering Research","score":0.9708999991416931,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8018561005592346},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7800979614257812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6682134866714478},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.6568917036056519},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6053106784820557},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5216027498245239}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8018561005592346},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7800979614257812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6682134866714478},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.6568917036056519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6053106784820557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5216027498245239},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001364","descriptor_name":"Awareness","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001364","descriptor_name":"Awareness","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001364","descriptor_name":"Awareness","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.3390/s22155845","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22155845","pdf_url":"https://www.mdpi.com/1424-8220/22/15/5845/pdf?version=1660213704","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"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":"Sensors","raw_type":"journal-article"},{"id":"pmid:35957399","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35957399","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":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:arXiv.org:2108.10533","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.10533","pdf_url":"https://arxiv.org/pdf/2108.10533","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:doaj.org/article:4a5931f0a87e49218d6a991285c879f3","is_oa":true,"landing_page_url":"https://doaj.org/article/4a5931f0a87e49218d6a991285c879f3","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":"Sensors, Vol 22, Iss 15, p 5845 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/22/15/5845/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s22155845","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":"Sensors; Volume 22; Issue 15; Pages: 5845","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:9371101","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9371101","pdf_url":null,"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":"Sensors (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s22155845","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22155845","pdf_url":"https://www.mdpi.com/1424-8220/22/15/5845/pdf?version=1660213704","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"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":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1523036375","display_name":null,"funder_award_id":"2020-0-00004","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G2482303134","display_name":null,"funder_award_id":"22ZR1100","funder_id":"https://openalex.org/F4320322093","funder_display_name":"Electronics and Telecommunications Research Institute"},{"id":"https://openalex.org/G2965168667","display_name":null,"funder_award_id":"21ZR1100","funder_id":"https://openalex.org/F4320322093","funder_display_name":"Electronics and Telecommunications Research Institute"},{"id":"https://openalex.org/G300623544","display_name":null,"funder_award_id":"2022-0-00124","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G3919315814","display_name":null,"funder_award_id":"No. 2020-0-00004","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G7695953040","display_name":null,"funder_award_id":"2022-0-00124","funder_id":"https://openalex.org/F4320322093","funder_display_name":"Electronics and Telecommunications Research Institute"},{"id":"https://openalex.org/G8936703760","display_name":null,"funder_award_id":"2020-0-00004","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320322093","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4289861370.pdf","grobid_xml":"https://content.openalex.org/works/W4289861370.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W2119333483","https://openalex.org/W2119717200","https://openalex.org/W2125930537","https://openalex.org/W2260756217","https://openalex.org/W2419612459","https://openalex.org/W2619989803","https://openalex.org/W2766447205","https://openalex.org/W2769428625","https://openalex.org/W2771590529","https://openalex.org/W2781726626","https://openalex.org/W2791797404","https://openalex.org/W2811374584","https://openalex.org/W2903383131","https://openalex.org/W2939856125","https://openalex.org/W2946723315","https://openalex.org/W2963403593","https://openalex.org/W2965140792","https://openalex.org/W2969489794","https://openalex.org/W2997902164","https://openalex.org/W3100789280","https://openalex.org/W3120947768","https://openalex.org/W3128395826","https://openalex.org/W3131871335","https://openalex.org/W3137745307","https://openalex.org/W3175186743","https://openalex.org/W3188746815","https://openalex.org/W3214679404","https://openalex.org/W4225728089"],"related_works":["https://openalex.org/W164946830","https://openalex.org/W4297802199","https://openalex.org/W2963910368","https://openalex.org/W3074294383","https://openalex.org/W2374512474","https://openalex.org/W2374442885","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W4319083788"],"abstract_inverted_index":{"Effective":[0],"exploration":[1],"is":[2,27],"one":[3],"of":[4,44,59,77,83],"the":[5,19,30,42,53,75,81,99,109,162],"critical":[6],"factors":[7],"affecting":[8],"performance":[9,37],"in":[10,52],"deep":[11,151],"reinforcement":[12,152],"learning.":[13],"Agents":[14],"acquire":[15],"data":[16,31],"to":[17,36,117,128,141,149],"learn":[18],"optimal":[20],"policy":[21],"through":[22],"exploration,":[23,50,96],"and":[24,97,112,170,174],"if":[25],"it":[26,115],"not":[28],"guaranteed,":[29],"quality":[32],"deteriorates,":[33],"which":[34,47],"leads":[35],"degradation.":[38],"This":[39],"study":[40,61],"investigates":[41],"effect":[43],"initial":[45,72,84,100,110,147],"entropy,":[46],"significantly":[48,166],"influences":[49],"especially":[51],"early":[54],"learning":[55,78,126,153,164,168,175],"stage.":[56],"The":[57,137],"results":[58],"this":[60],"on":[62],"tasks":[63,88],"with":[64,107,130,145],"discrete":[65,103],"action":[66,104],"space":[67,105],"show":[68],"that":[69,94,161],"(1)":[70],"low":[71,92],"entropy":[73,85,101,148],"increases":[74],"probability":[76],"failure,":[79],"(2)":[80],"distributions":[82],"for":[86,102,155],"various":[87],"are":[89],"biased":[90],"towards":[91],"values":[93],"inhibit":[95],"(3)":[98],"varies":[106],"both":[108],"weight":[111],"task,":[113],"making":[114],"hard":[116],"control.":[118],"We":[119],"then":[120],"devise":[121],"a":[122,143,150],"simple":[123],"yet":[124],"powerful":[125],"strategy":[127,165],"deal":[129],"these":[131],"limitations,":[132],"namely,":[133],"entropy-aware":[134],"model":[135,144],"initialization.":[136],"proposed":[138],"algorithm":[139,154],"aims":[140],"provide":[142],"high":[146],"effective":[156],"exploration.":[157],"Our":[158],"experiments":[159],"showed":[160],"devised":[163],"reduces":[167],"failures":[169],"enhances":[171],"performance,":[172],"stability,":[173],"speed.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
