{"id":"https://openalex.org/W4214894289","doi":"https://doi.org/10.1109/icaiic54071.2022.9722618","title":"A Survey of Markov Model in Reinforcement Learning","display_name":"A Survey of Markov Model in Reinforcement Learning","publication_year":2022,"publication_date":"2022-02-21","ids":{"openalex":"https://openalex.org/W4214894289","doi":"https://doi.org/10.1109/icaiic54071.2022.9722618"},"language":"en","primary_location":{"id":"doi:10.1109/icaiic54071.2022.9722618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic54071.2022.9722618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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/A5101904686","display_name":"Tianhan Gao","orcid":"https://orcid.org/0000-0002-0272-194X"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianhan Gao","raw_affiliation_strings":["Northeastern University,Software College,Shenyang,China","Software College, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Software College,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Software College, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052722416","display_name":"Baicheng Chen","orcid":"https://orcid.org/0000-0001-8329-9295"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baicheng Chen","raw_affiliation_strings":["Northeastern University,Software College,Shenyang,China","Software College, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Software College,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Software College, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069192290","display_name":"Qingwei Mi","orcid":"https://orcid.org/0000-0002-8807-0585"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingwei Mi","raw_affiliation_strings":["Northeastern University,Software College,Shenyang,China","Software College, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Software College,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Software College, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101904686"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":0.5147,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.60087443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"284","last_page":"287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9610999822616577,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9610999822616577,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13283","display_name":"Mental Health Research Topics","score":0.9043999910354614,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7399780750274658},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.7336456775665283},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.7164315581321716},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.591526210308075},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.5749413967132568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.536831796169281},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.47395825386047363},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4487072229385376},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24690911173820496},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.21968114376068115}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7399780750274658},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.7336456775665283},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.7164315581321716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.591526210308075},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.5749413967132568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.536831796169281},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.47395825386047363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4487072229385376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24690911173820496},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21968114376068115}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaiic54071.2022.9722618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic54071.2022.9722618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W52153049","https://openalex.org/W115452890","https://openalex.org/W139596442","https://openalex.org/W1771410628","https://openalex.org/W2010645467","https://openalex.org/W2105594594","https://openalex.org/W2123674401","https://openalex.org/W2172933221","https://openalex.org/W2290354866","https://openalex.org/W2414577866","https://openalex.org/W2610593146","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2736601468","https://openalex.org/W2787938642","https://openalex.org/W2946606218","https://openalex.org/W2949963774","https://openalex.org/W2950471160","https://openalex.org/W2963658727","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W4235646468","https://openalex.org/W4295598622","https://openalex.org/W4298857966","https://openalex.org/W4302570325","https://openalex.org/W6637967152","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6741002519","https://openalex.org/W6748839928","https://openalex.org/W6749304979"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":{"There":[0],"was":[1],"a":[2],"famous":[3],"mathematician":[4],"from":[5],"Russian":[6],"in":[7,33,42],"the":[8,24,27,34,65,70],"early":[9],"20":[10],"<sup":[11],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[12],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">th</sup>":[13],"century":[14],"whose":[15],"name":[16],"is":[17],"Andrey":[18],"Andreyevich":[19],"Markov.":[20],"After":[21],"he":[22],"proposed":[23],"Markov":[25,54],"process,":[26],"theories":[28,74],"have":[29,38,76],"been":[30,39],"effectively":[31],"developed":[32],"past":[35],"years":[36],"and":[37,49,75],"widely":[40],"adopted":[41],"different":[43],"fields.":[44],"This":[45],"paper":[46],"both":[47],"summarizes":[48],"does":[50],"incomplete":[51],"statistics":[52],"on":[53],"models":[55],"which":[56],"are":[57],"related":[58],"to":[59,67],"reinforcement":[60],"learning.":[61],"It":[62],"will":[63],"help":[64],"readers":[66],"quickly":[68],"clarify":[69],"relationship":[71],"between":[72],"these":[73],"an":[77],"overall":[78],"understanding":[79],"of":[80],"them.":[81]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}