{"id":"https://openalex.org/W4403675785","doi":"https://doi.org/10.1109/case59546.2024.10711499","title":"State Entropy Optimization in Markov Decision Processes","display_name":"State Entropy Optimization in Markov Decision Processes","publication_year":2024,"publication_date":"2024-08-28","ids":{"openalex":"https://openalex.org/W4403675785","doi":"https://doi.org/10.1109/case59546.2024.10711499"},"language":"en","primary_location":{"id":"doi:10.1109/case59546.2024.10711499","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/case59546.2024.10711499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)","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/A5022564470","display_name":"Shuai Ma","orcid":"https://orcid.org/0000-0002-0325-9347"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Ma","raw_affiliation_strings":["Sun Yat-Sen University,School of Business,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,School of Business,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100646502","display_name":"Li Xia","orcid":"https://orcid.org/0000-0002-3193-7336"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Xia","raw_affiliation_strings":["Sun Yat-Sen University,School of Business,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,School of Business,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014109600","display_name":"Qianchuan Zhao","orcid":"https://orcid.org/0000-0002-7952-5621"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianchuan Zhao","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2846","last_page":"2851"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.4772000014781952,"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"}},"topics":[{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.4772000014781952,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.4715000092983246,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6195144057273865},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5144541263580322},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5066843628883362},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4674423933029175},{"id":"https://openalex.org/keywords/maximum-entropy-markov-model","display_name":"Maximum-entropy Markov model","score":0.44124317169189453},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4345836341381073},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41051095724105835},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.35231319069862366},{"id":"https://openalex.org/keywords/statistical-physics","display_name":"Statistical physics","score":0.33756643533706665},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.23000475764274597},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22026219964027405},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19097942113876343},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1727558672428131},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08550578355789185},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07586279511451721},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.07346963882446289}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6195144057273865},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5144541263580322},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5066843628883362},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4674423933029175},{"id":"https://openalex.org/C196956702","wikidata":"https://www.wikidata.org/wiki/Q6795829","display_name":"Maximum-entropy Markov model","level":5,"score":0.44124317169189453},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4345836341381073},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41051095724105835},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.35231319069862366},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.33756643533706665},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.23000475764274597},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22026219964027405},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19097942113876343},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1727558672428131},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08550578355789185},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07586279511451721},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.07346963882446289}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case59546.2024.10711499","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/case59546.2024.10711499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1998783985","https://openalex.org/W2003031375","https://openalex.org/W2099111195","https://openalex.org/W2807575755","https://openalex.org/W2847132741","https://openalex.org/W3096120809","https://openalex.org/W4210609986","https://openalex.org/W4213251304","https://openalex.org/W4214717370","https://openalex.org/W4221021751","https://openalex.org/W4313071410","https://openalex.org/W6640715660","https://openalex.org/W6757058172"],"related_works":["https://openalex.org/W2379651310","https://openalex.org/W4211010039","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2084326697","https://openalex.org/W2027903142","https://openalex.org/W2354322608","https://openalex.org/W2804608325","https://openalex.org/W2077211377","https://openalex.org/W2100055350"],"abstract_inverted_index":{"We":[0,15,71,105],"examine":[1],"the":[2,28,33,49,64,93,107,110],"state":[3,89],"entropy":[4,19,29,36,45,66,68,81,102],"optimization":[5,20,31,37,100],"in":[6,21,84,90,101,113],"both":[7,27,73],"discounted":[8,23,35],"and":[9,25,32,76],"average":[10],"Markov":[11],"decision":[12],"processes":[13],"(MDPs).":[14],"suggest":[16],"a":[17,22,114],"total":[18,34,65],"setting,":[24],"solve":[26],"rate":[30,69],"with":[38,98],"iterative":[39],"algorithms.":[40],"An":[41],"optimal":[42],"solution":[43],"to":[44,62],"maximization":[46,103],"ensures":[47],"that":[48],"system":[50],"remains":[51],"as":[52,54],"unpredictable":[53],"possible.":[55],"Previous":[56],"works":[57],"apply":[58],"nonlinear":[59],"programming":[60],"methods":[61],"either":[63],"or":[67],"optimizations.":[70],"present":[72],"value":[74],"iteration":[75,78],"policy":[77],"for":[79],"synthesizing":[80],"optimizing":[82],"policies":[83],"ergodic":[85],"MDPs.":[86],"For":[87],"each":[88,91],"iteration,":[92],"action":[94],"distribution":[95],"is":[96],"optimized":[97],"convex":[99],"problems.":[104],"illustrate":[106],"validity":[108],"of":[109],"proposed":[111],"algorithms":[112],"numerical":[115],"experiment.":[116]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}