{"id":"https://openalex.org/W4387246115","doi":"https://doi.org/10.1145/3626570.3626585","title":"Markov Decision Process Framework for Control-Based Reinforcement Learning","display_name":"Markov Decision Process Framework for Control-Based Reinforcement Learning","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387246115","doi":"https://doi.org/10.1145/3626570.3626585"},"language":"en","primary_location":{"id":"doi:10.1145/3626570.3626585","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626570.3626585","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMETRICS Performance Evaluation Review","raw_type":"journal-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/A5082596545","display_name":"Yingdong Lu","orcid":"https://orcid.org/0000-0002-3672-0865"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingdong Lu","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013152760","display_name":"Mark S. Squillante","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark S. Squillante","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038483763","display_name":"Chai Wah Wu","orcid":"https://orcid.org/0000-0002-0657-0683"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chai Wah Wu","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":0.4759,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69352943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"51","issue":"2","first_page":"39","last_page":"41"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.964900016784668,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.964900016784668,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9232000112533569,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8819020986557007},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8060479164123535},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6644356846809387},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6487197875976562},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5890451669692993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5170632004737854},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4494030177593231},{"id":"https://openalex.org/keywords/decision-process","display_name":"Decision process","score":0.43423426151275635},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.4301041066646576},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41411516070365906},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.370816171169281},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.2946542203426361},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.1937902271747589},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.16346538066864014},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14818930625915527},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08628150820732117}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8819020986557007},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8060479164123535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6644356846809387},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6487197875976562},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5890451669692993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5170632004737854},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4494030177593231},{"id":"https://openalex.org/C2984634286","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision process","level":2,"score":0.43423426151275635},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4301041066646576},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41411516070365906},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.370816171169281},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2946542203426361},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.1937902271747589},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.16346538066864014},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14818930625915527},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08628150820732117},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626570.3626585","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626570.3626585","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMETRICS Performance Evaluation Review","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2100919908","https://openalex.org/W2116479686","https://openalex.org/W3039845099","https://openalex.org/W3171210634","https://openalex.org/W4387246115"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W3096874164","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W2937181779","https://openalex.org/W2386410636"],"abstract_inverted_index":{"For":[0],"many":[1],"years,":[2],"reinforcement":[3],"learning":[4,18],"(RL)":[5],"has":[6],"proven":[7],"to":[8,29,47],"be":[9],"very":[10],"successful":[11],"in":[12],"solving":[13],"a":[14],"wide":[15],"variety":[16],"of":[17,42],"and":[19,32],"decision":[20],"making":[21],"under":[22],"uncertainty":[23],"(DMuU)":[24],"problems,":[25],"including":[26],"those":[27],"related":[28],"game":[30],"playing":[31],"robotic":[33],"control.":[34],"Many":[35],"different":[36],"RL":[37],"approaches,":[38],"with":[39],"varying":[40],"levels":[41],"success,":[43],"have":[44],"been":[45],"developed":[46],"address":[48],"these":[49],"problems.":[50]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}