{"id":"https://openalex.org/W3204750342","doi":"https://doi.org/10.1007/978-3-030-82014-5_44","title":"Markov-Chain-Based Agents for k-Armed Bandit Problem","display_name":"Markov-Chain-Based Agents for k-Armed Bandit Problem","publication_year":2021,"publication_date":"2021-07-22","ids":{"openalex":"https://openalex.org/W3204750342","doi":"https://doi.org/10.1007/978-3-030-82014-5_44","mag":"3204750342"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-82014-5_44","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-82014-5_44","pdf_url":null,"source":{"id":"https://openalex.org/S4210216571","display_name":"Lecture notes on data engineering and communications technologies","issn_l":"2367-4512","issn":["2367-4512","2367-4520"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes on Data Engineering and Communications Technologies","raw_type":"book-chapter"},"type":"book-chapter","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/A5068244543","display_name":"Vladyslav Sarnatskyi","orcid":"https://orcid.org/0000-0001-5231-6136"},"institutions":[{"id":"https://openalex.org/I202483615","display_name":"National Technical University of Ukraine \u201cIgor Sikorsky Kyiv Polytechnic Institute\u201d","ror":"https://ror.org/00syn5v21","country_code":"UA","type":"education","lineage":["https://openalex.org/I202483615"]}],"countries":["UA"],"is_corresponding":true,"raw_author_name":"Vladyslav Sarnatskyi","raw_affiliation_strings":["National Technical University of Ukraine \u201cIgor Sikorsky Kyiv Polytechnic Institute\u201d, Kyiv, Ukraine","National Technical University of Ukraine \"Igor Sikorsky Kyiv Polytechnic Institute\", Kyiv, Ukraine"],"raw_orcid":"https://orcid.org/0000-0001-5231-6136","affiliations":[{"raw_affiliation_string":"National Technical University of Ukraine \u201cIgor Sikorsky Kyiv Polytechnic Institute\u201d, Kyiv, Ukraine","institution_ids":["https://openalex.org/I202483615"]},{"raw_affiliation_string":"National Technical University of Ukraine \"Igor Sikorsky Kyiv Polytechnic Institute\", Kyiv, Ukraine","institution_ids":["https://openalex.org/I202483615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078109445","display_name":"Igor Baklan","orcid":"https://orcid.org/0000-0002-5274-5261"},"institutions":[{"id":"https://openalex.org/I202483615","display_name":"National Technical University of Ukraine \u201cIgor Sikorsky Kyiv Polytechnic Institute\u201d","ror":"https://ror.org/00syn5v21","country_code":"UA","type":"education","lineage":["https://openalex.org/I202483615"]}],"countries":["UA"],"is_corresponding":false,"raw_author_name":"Igor Baklan","raw_affiliation_strings":["National Technical University of Ukraine \u201cIgor Sikorsky Kyiv Polytechnic Institute\u201d, Kyiv, Ukraine","National Technical University of Ukraine \"Igor Sikorsky Kyiv Polytechnic Institute\", Kyiv, Ukraine"],"raw_orcid":"https://orcid.org/0000-0002-5274-5261","affiliations":[{"raw_affiliation_string":"National Technical University of Ukraine \u201cIgor Sikorsky Kyiv Polytechnic Institute\u201d, Kyiv, Ukraine","institution_ids":["https://openalex.org/I202483615"]},{"raw_affiliation_string":"National Technical University of Ukraine \"Igor Sikorsky Kyiv Polytechnic Institute\", Kyiv, Ukraine","institution_ids":["https://openalex.org/I202483615"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068244543"],"corresponding_institution_ids":["https://openalex.org/I202483615"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20530583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"634","last_page":"644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9991000294685364,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9940000176429749,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.7787784337997437},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.746597170829773},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6863905191421509},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5937268137931824},{"id":"https://openalex.org/keywords/additive-markov-chain","display_name":"Additive Markov chain","score":0.5919755101203918},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5768739581108093},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5565144419670105},{"id":"https://openalex.org/keywords/multi-armed-bandit","display_name":"Multi-armed bandit","score":0.48520973324775696},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4791702330112457},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4785350263118744},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.4438386559486389},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4355885088443756},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4265800714492798},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.42110493779182434},{"id":"https://openalex.org/keywords/continuous-time-markov-chain","display_name":"Continuous-time Markov chain","score":0.41380375623703003},{"id":"https://openalex.org/keywords/markov-property","display_name":"Markov property","score":0.39638209342956543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3803275525569916},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.31423282623291016},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2872546315193176},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24710404872894287},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0609891414642334}],"concepts":[{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.7787784337997437},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.746597170829773},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6863905191421509},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5937268137931824},{"id":"https://openalex.org/C96810086","wikidata":"https://www.wikidata.org/wiki/Q17003273","display_name":"Additive Markov chain","level":5,"score":0.5919755101203918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5768739581108093},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5565144419670105},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.48520973324775696},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4791702330112457},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4785350263118744},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4438386559486389},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4355885088443756},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4265800714492798},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.42110493779182434},{"id":"https://openalex.org/C147080032","wikidata":"https://www.wikidata.org/wiki/Q176720","display_name":"Continuous-time Markov chain","level":5,"score":0.41380375623703003},{"id":"https://openalex.org/C189973286","wikidata":"https://www.wikidata.org/wiki/Q176695","display_name":"Markov property","level":4,"score":0.39638209342956543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3803275525569916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31423282623291016},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2872546315193176},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24710404872894287},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0609891414642334},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-82014-5_44","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-82014-5_44","pdf_url":null,"source":{"id":"https://openalex.org/S4210216571","display_name":"Lecture notes on data engineering and communications technologies","issn_l":"2367-4512","issn":["2367-4512","2367-4520"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes on Data Engineering and Communications Technologies","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1658008008","https://openalex.org/W2091565802","https://openalex.org/W2257979135","https://openalex.org/W2772709170","https://openalex.org/W6603932791","https://openalex.org/W6637967152","https://openalex.org/W6732837357","https://openalex.org/W6748440607"],"related_works":["https://openalex.org/W2364406457","https://openalex.org/W2173087131","https://openalex.org/W3046162988","https://openalex.org/W1997350370","https://openalex.org/W2349429754","https://openalex.org/W2375491161","https://openalex.org/W1189343304","https://openalex.org/W597892100","https://openalex.org/W4285326015","https://openalex.org/W4391063672"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}