{"id":"https://openalex.org/W2048984163","doi":"https://doi.org/10.1016/0004-3702(94)00012-p","title":"Reinforcement learning of non-Markov decision processes","display_name":"Reinforcement learning of non-Markov decision processes","publication_year":1995,"publication_date":"1995-02-01","ids":{"openalex":"https://openalex.org/W2048984163","doi":"https://doi.org/10.1016/0004-3702(94)00012-p","mag":"2048984163"},"language":"en","primary_location":{"id":"doi:10.1016/0004-3702(94)00012-p","is_oa":false,"landing_page_url":"https://doi.org/10.1016/0004-3702(94)00012-p","pdf_url":null,"source":{"id":"https://openalex.org/S196139623","display_name":"Artificial Intelligence","issn_l":"0004-3702","issn":["0004-3702","1872-7921"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence","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/A5049870971","display_name":"Steven D. Whitehead","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Steven D. Whitehead","raw_affiliation_strings":["GTE Laboratories Incorporated, 40 Sylvan Road, Waltham, MA 02254, USA"],"affiliations":[{"raw_affiliation_string":"GTE Laboratories Incorporated, 40 Sylvan Road, Waltham, MA 02254, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107841673","display_name":"Long-Ji Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Long-Ji Lin","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA","School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA;"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA;","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049870971"],"corresponding_institution_ids":[],"apc_list":{"value":3670,"currency":"USD","value_usd":3670},"apc_paid":null,"fwci":2.3531,"has_fulltext":false,"cited_by_count":131,"citation_normalized_percentile":{"value":0.89420227,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"73","issue":"1-2","first_page":"271","last_page":"306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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":0.9976999759674072,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8428893089294434},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.719143271446228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7148019075393677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6244651079177856},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5672498941421509},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5270609855651855},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4906865358352661},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45845431089401245},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.4574238061904907},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4551326334476471},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4371865391731262},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.408974826335907},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2992279529571533},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1243424117565155}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8428893089294434},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.719143271446228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7148019075393677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6244651079177856},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5672498941421509},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5270609855651855},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4906865358352661},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45845431089401245},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4574238061904907},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4551326334476471},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4371865391731262},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.408974826335907},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2992279529571533},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1243424117565155},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/0004-3702(94)00012-p","is_oa":false,"landing_page_url":"https://doi.org/10.1016/0004-3702(94)00012-p","pdf_url":null,"source":{"id":"https://openalex.org/S196139623","display_name":"Artificial Intelligence","issn_l":"0004-3702","issn":["0004-3702","1872-7921"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence","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":95,"referenced_works":["https://openalex.org/W3185548","https://openalex.org/W38453897","https://openalex.org/W50296447","https://openalex.org/W80823096","https://openalex.org/W111328409","https://openalex.org/W168365783","https://openalex.org/W293526712","https://openalex.org/W309749295","https://openalex.org/W1491843047","https://openalex.org/W1497976081","https://openalex.org/W1499371387","https://openalex.org/W1504212531","https://openalex.org/W1507087299","https://openalex.org/W1529303739","https://openalex.org/W1538393421","https://openalex.org/W1545148916","https://openalex.org/W1545378070","https://openalex.org/W1569296262","https://openalex.org/W1588388339","https://openalex.org/W1592377142","https://openalex.org/W1593772383","https://openalex.org/W1595483645","https://openalex.org/W1596324102","https://openalex.org/W1607817625","https://openalex.org/W1628475528","https://openalex.org/W1931792391","https://openalex.org/W1995663008","https://openalex.org/W1997449813","https://openalex.org/W2012036715","https://openalex.org/W2035446426","https://openalex.org/W2048226872","https://openalex.org/W2052117683","https://openalex.org/W2061361125","https://openalex.org/W2091565802","https://openalex.org/W2100677568","https://openalex.org/W2101767921","https://openalex.org/W2103626435","https://openalex.org/W2110485445","https://openalex.org/W2112483970","https://openalex.org/W2115121720","https://openalex.org/W2139232801","https://openalex.org/W2140256637","https://openalex.org/W2141559645","https://openalex.org/W2149706766","https://openalex.org/W2157445228","https://openalex.org/W2160371091","https://openalex.org/W2341171179","https://openalex.org/W2766736793","https://openalex.org/W2911283634","https://openalex.org/W2913060459","https://openalex.org/W2913472862","https://openalex.org/W2913703059","https://openalex.org/W2914112863","https://openalex.org/W2914331897","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W3198350258","https://openalex.org/W3207342693","https://openalex.org/W4236137412","https://openalex.org/W4243970992","https://openalex.org/W4245108548","https://openalex.org/W4253365321","https://openalex.org/W4301914554","https://openalex.org/W6601531290","https://openalex.org/W6602038105","https://openalex.org/W6603207585","https://openalex.org/W6610461261","https://openalex.org/W6610832093","https://openalex.org/W6629916206","https://openalex.org/W6629993198","https://openalex.org/W6630225054","https://openalex.org/W6630317190","https://openalex.org/W6631623598","https://openalex.org/W6632197581","https://openalex.org/W6632878570","https://openalex.org/W6634103402","https://openalex.org/W6635230855","https://openalex.org/W6635465357","https://openalex.org/W6635693572","https://openalex.org/W6636241757","https://openalex.org/W6640629700","https://openalex.org/W6675100737","https://openalex.org/W6676724595","https://openalex.org/W6676920640","https://openalex.org/W6680243060","https://openalex.org/W6680579481","https://openalex.org/W6680666887","https://openalex.org/W6682610290","https://openalex.org/W6683182819","https://openalex.org/W6683821272","https://openalex.org/W6758506881","https://openalex.org/W6764708042","https://openalex.org/W6775686901","https://openalex.org/W7018193019","https://openalex.org/W7071595823"],"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":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}