{"id":"https://openalex.org/W4393141297","doi":"https://doi.org/10.1109/healthcom56612.2023.10472341","title":"Optimizing Blood Glucose Control through Reward Shaping in Reinforcement Learning","display_name":"Optimizing Blood Glucose Control through Reward Shaping in Reinforcement Learning","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4393141297","doi":"https://doi.org/10.1109/healthcom56612.2023.10472341"},"language":"en","primary_location":{"id":"doi:10.1109/healthcom56612.2023.10472341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/healthcom56612.2023.10472341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on E-health Networking, Application & Services (Healthcom)","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/A5009613277","display_name":"Fatemeh Sarani Rad","orcid":"https://orcid.org/0000-0001-7088-2561"},"institutions":[{"id":"https://openalex.org/I57328836","display_name":"North Dakota State University","ror":"https://ror.org/05h1bnb22","country_code":"US","type":"education","lineage":["https://openalex.org/I57328836"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fatemeh Sarani Rad","raw_affiliation_strings":["North Dakota State University,Department of Computer Science,Fargo,USA"],"affiliations":[{"raw_affiliation_string":"North Dakota State University,Department of Computer Science,Fargo,USA","institution_ids":["https://openalex.org/I57328836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100420982","display_name":"Juan Li","orcid":"https://orcid.org/0000-0001-7721-6596"},"institutions":[{"id":"https://openalex.org/I57328836","display_name":"North Dakota State University","ror":"https://ror.org/05h1bnb22","country_code":"US","type":"education","lineage":["https://openalex.org/I57328836"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Li","raw_affiliation_strings":["North Dakota State University,Department of Computer Science,Fargo,USA"],"affiliations":[{"raw_affiliation_string":"North Dakota State University,Department of Computer Science,Fargo,USA","institution_ids":["https://openalex.org/I57328836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5009613277"],"corresponding_institution_ids":["https://openalex.org/I57328836"],"apc_list":null,"apc_paid":null,"fwci":0.8294,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77129972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"342","last_page":"347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10560","display_name":"Diabetes Management and Research","score":0.8574000000953674,"subfield":{"id":"https://openalex.org/subfields/2712","display_name":"Endocrinology, Diabetes and Metabolism"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10560","display_name":"Diabetes Management and Research","score":0.8574000000953674,"subfield":{"id":"https://openalex.org/subfields/2712","display_name":"Endocrinology, Diabetes and Metabolism"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8070120811462402},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5745850205421448},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5338253974914551},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5305476784706116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3232951760292053},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21754086017608643},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1148093044757843}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8070120811462402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5745850205421448},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5338253974914551},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5305476784706116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3232951760292053},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21754086017608643},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1148093044757843}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/healthcom56612.2023.10472341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/healthcom56612.2023.10472341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on E-health Networking, Application & Services (Healthcom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1966850311","https://openalex.org/W2001273251","https://openalex.org/W2034725503","https://openalex.org/W2062573090","https://openalex.org/W2129995532","https://openalex.org/W2155639879","https://openalex.org/W2167160009","https://openalex.org/W2786963919","https://openalex.org/W2805206708","https://openalex.org/W2981121978","https://openalex.org/W3008110675","https://openalex.org/W3100358445","https://openalex.org/W3156139209","https://openalex.org/W4223612868","https://openalex.org/W4225966252","https://openalex.org/W4236126199","https://openalex.org/W4255078542","https://openalex.org/W4289761856","https://openalex.org/W6638088447","https://openalex.org/W6747473740","https://openalex.org/W6783106408"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291"],"abstract_inverted_index":{"Achieving":[0],"optimal":[1],"blood":[2,44,82,98,107,126],"glucose":[3,45,83,99,108,127,164],"control":[4,109],"is":[5,118],"a":[6,14,78,124,149],"complex":[7],"challenge":[8],"for":[9,43],"individuals":[10],"with":[11,143,153],"diabetes,":[12],"necessitating":[13],"delicate":[15],"balance":[16],"among":[17],"insulin":[18,166],"dosage,":[19],"food":[20],"consumption,":[21],"physical":[22],"activity,":[23],"and":[24,40,62,80,93,110,121,168],"stress":[25],"management.":[26],"This":[27,85],"paper":[28],"introduces":[29],"an":[30,67],"innovative":[31],"approach":[32],"utilizing":[33],"reinforcement":[34],"learning":[35],"(RL)":[36],"to":[37,71],"develop":[38],"personalized":[39],"effective":[41],"strategies":[42],"regulation.":[46],"Specifically,":[47],"we":[48],"employ":[49],"the":[50,90,94,97,102,112,132],"state-of-the-art":[51],"soft":[52],"actorcritic":[53],"(SAC)":[54],"RL":[55],"algorithm,":[56],"which":[57],"concurrently":[58],"maximizes":[59],"anticipated":[60],"rewards":[61],"policy":[63],"entropy.":[64],"We":[65],"devise":[66],"entropydriven":[68],"reward":[69,86,145,156,169],"function":[70,87,157],"incentivize":[72],"diverse":[73],"action":[74],"exploration":[75],"while":[76],"ensuring":[77],"secure":[79],"consistent":[81],"profile.":[84],"considers":[88],"both":[89],"policy's":[91],"entropy":[92],"deviation":[95],"of":[96,114,161],"level":[100],"from":[101],"target":[103],"range,":[104],"thus":[105],"optimizing":[106],"minimizing":[111],"risk":[113,162],"complications.":[115],"Our":[116],"methodology":[117],"applied,":[119],"trained,":[120],"assessed":[122],"using":[123],"sophisticated":[125],"dynamics":[128],"simulator":[129],"based":[130],"on":[131],"UVA/Padova":[133],"model.":[134],"The":[135],"results":[136],"demonstrate":[137],"that":[138],"our":[139],"proposed":[140],"method,":[141],"SAC":[142,152],"entropy-based":[144],"shaping":[146],"(SAC+RS),":[147],"outperforms":[148],"comparative":[150],"approach,":[151],"Magni's":[154],"risk-based":[155],"(SAC+MRS),":[158],"in":[159],"terms":[160],"scores,":[163],"levels,":[165,167],"values.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}