{"id":"https://openalex.org/W4405427385","doi":"https://doi.org/10.1145/3698587.3701524","title":"gPSRM: A generative propensity score-based replay memory for deep reinforcement learnings","display_name":"gPSRM: A generative propensity score-based replay memory for deep reinforcement learnings","publication_year":2024,"publication_date":"2024-11-22","ids":{"openalex":"https://openalex.org/W4405427385","doi":"https://doi.org/10.1145/3698587.3701524"},"language":"en","primary_location":{"id":"doi:10.1145/3698587.3701524","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3698587.3701524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","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/A5032778019","display_name":"Jiang Liu","orcid":"https://orcid.org/0000-0002-2800-448X"},"institutions":[{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiang Liu","raw_affiliation_strings":["Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China","institution_ids":["https://openalex.org/I4210123021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112734701","display_name":"Changjiang Zhou","orcid":"https://orcid.org/0009-0000-0005-9465"},"institutions":[{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chan Zhou","raw_affiliation_strings":["Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China","institution_ids":["https://openalex.org/I4210123021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428128","display_name":"Yuwen Chen","orcid":"https://orcid.org/0000-0003-4032-5937"},"institutions":[{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwen Chen","raw_affiliation_strings":["Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China","institution_ids":["https://openalex.org/I4210123021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102583376","display_name":"Yihao Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihao Xie","raw_affiliation_strings":["Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China","institution_ids":["https://openalex.org/I4210123021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025577481","display_name":"Kunhua Zhong","orcid":"https://orcid.org/0000-0002-5341-9011"},"institutions":[{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kunhua Zhong","raw_affiliation_strings":["Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China","institution_ids":["https://openalex.org/I4210123021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100311129","display_name":"Qilong Sun","orcid":"https://orcid.org/0009-0003-8699-2150"},"institutions":[{"id":"https://openalex.org/I4210123021","display_name":"Chongqing Institute of Green and Intelligent Technology","ror":"https://ror.org/031npqv35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210123021"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qilong Sun","raw_affiliation_strings":["Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China","institution_ids":["https://openalex.org/I4210123021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340464","display_name":"Yujie Li","orcid":"https://orcid.org/0000-0003-3527-5859"},"institutions":[{"id":"https://openalex.org/I151075929","display_name":"Army Medical University","ror":"https://ror.org/05w21nn13","country_code":"CN","type":"education","lineage":["https://openalex.org/I151075929"]},{"id":"https://openalex.org/I4210131174","display_name":"Southwest Hospital","ror":"https://ror.org/02jn36537","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210131174"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujie Li","raw_affiliation_strings":["Department of Anesthesiology, Southwest Hospital, Third Military Medical University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Department of Anesthesiology, Southwest Hospital, Third Military Medical University, Chongqing, China","institution_ids":["https://openalex.org/I151075929","https://openalex.org/I4210131174"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084911441","display_name":"Bin Yi","orcid":"https://orcid.org/0000-0001-5840-2086"},"institutions":[{"id":"https://openalex.org/I151075929","display_name":"Army Medical University","ror":"https://ror.org/05w21nn13","country_code":"CN","type":"education","lineage":["https://openalex.org/I151075929"]},{"id":"https://openalex.org/I4210131174","display_name":"Southwest Hospital","ror":"https://ror.org/02jn36537","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210131174"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Yi","raw_affiliation_strings":["Department of Anesthesiology, Southwest Hospital, Third Military Medical University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Department of Anesthesiology, Southwest Hospital, Third Military Medical University, Chongqing, China","institution_ids":["https://openalex.org/I151075929","https://openalex.org/I4210131174"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5032778019"],"corresponding_institution_ids":["https://openalex.org/I4210123021"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21078392,"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":0.9995999932289124,"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":0.9995999932289124,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9718000292778015,"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":0.681801438331604},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6424742937088013},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5605096817016602},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4945060908794403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4537298381328583},{"id":"https://openalex.org/keywords/propensity-score-matching","display_name":"Propensity score matching","score":0.4522072970867157},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16183128952980042},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08745443820953369},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08440372347831726},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.04959756135940552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.681801438331604},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6424742937088013},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5605096817016602},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4945060908794403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4537298381328583},{"id":"https://openalex.org/C17923572","wikidata":"https://www.wikidata.org/wiki/Q7250160","display_name":"Propensity score matching","level":2,"score":0.4522072970867157},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16183128952980042},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08745443820953369},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08440372347831726},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.04959756135940552}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3698587.3701524","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3698587.3701524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","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":11,"referenced_works":["https://openalex.org/W571200655","https://openalex.org/W1975580029","https://openalex.org/W2148143831","https://openalex.org/W2152161277","https://openalex.org/W2198041288","https://openalex.org/W2963596856","https://openalex.org/W3096831136","https://openalex.org/W4285188787","https://openalex.org/W4385302721","https://openalex.org/W4389074726","https://openalex.org/W4391332834"],"related_works":["https://openalex.org/W2026576563","https://openalex.org/W3196761963","https://openalex.org/W213628847","https://openalex.org/W2036193982","https://openalex.org/W2065417422","https://openalex.org/W101468167","https://openalex.org/W4232168831","https://openalex.org/W4253956144","https://openalex.org/W3023923059","https://openalex.org/W2105161754"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"reinforcement":[3],"learning":[4],"(RL)":[5],"methods":[6,189],"have":[7],"made":[8],"significant":[9,30],"strides":[10],"in":[11,32,53,76,93,108,190,197],"medical":[12,198],"decision":[13],"optimization,":[14],"including":[15],"treatments":[16],"for":[17,34,72],"AIDS,":[18],"cancer,":[19],"and":[20,79,143],"diabetes.":[21],"However,":[22],"designing":[23],"an":[24,127],"effective":[25],"reward":[26,43],"function":[27,44],"remains":[28],"a":[29,39,50,69],"challenge":[31],"RL":[33,195],"medicine.":[35],"This":[36],"study":[37],"proposes":[38],"data-driven":[40],"approach":[41],"to":[42,90,118,135,138,149,155,163,179],"design.":[45],"The":[46,102,110],"replay":[47,74],"memory":[48,75],"plays":[49],"crucial":[51],"role":[52],"DQN-based":[54],"methods.":[55],"To":[56],"address":[57],"the":[58,73,98,121,140,146,157,184,192],"issue":[59],"of":[60,145,160,186,194],"imbalanced":[61],"sample":[62],"distribution":[63],"across":[64],"different":[65],"categories,":[66],"we":[67,152,169],"introduce":[68],"novel":[70],"design":[71],"both":[77],"DQN":[78,112,124],"Dueling":[80,123],"DQN,":[81],"based":[82],"on":[83],"propensity":[84],"scores.":[85],"We":[86],"applied":[87],"these":[88],"innovations":[89],"AI":[91],"decision-making":[92,199],"skin":[94],"cancer":[95],"diagnosis":[96],"using":[97],"public":[99],"ISIC2018":[100],"dataset.":[101],"experimental":[103],"results":[104,182],"demonstrated":[105],"substantial":[106],"improvements":[107],"accuracy.":[109],"modified":[111,122],"model's":[113],"accuracy":[114,176],"increased":[115],"from":[116,133,177],"88.2%":[117],"91.4%,":[119],"while":[120],"model":[125],"showed":[126],"even":[128],"more":[129],"impressive":[130],"improvement,":[131],"rising":[132],"87.9%":[134],"92.8%.":[136],"Besides,":[137],"discuss":[139],"generalization":[141],"ability":[142],"applicability":[144],"gPSRM":[147,174],"method":[148],"other":[150],"domains,":[151],"train":[153],"models":[154],"predict":[156],"COVID-19":[158],"status":[159],"patients":[161],"presenting":[162],"hospital":[164],"emergency":[165],"departments.":[166],"Through":[167],"experiments,":[168],"found":[170],"that":[171],"Q-imb":[172],"with":[173],"improved":[175],"79.2%":[178],"84.6%.":[180],"These":[181],"underscore":[183],"potential":[185],"our":[187],"proposed":[188],"enhancing":[191],"performance":[193],"algorithms":[196],"tasks.":[200]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}