{"id":"https://openalex.org/W1680286194","doi":"https://doi.org/10.1007/978-0-387-09823-4_20","title":"A Review of Reinforcement Learning Methods","display_name":"A Review of Reinforcement Learning Methods","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W1680286194","doi":"https://doi.org/10.1007/978-0-387-09823-4_20","mag":"1680286194"},"language":"en","primary_location":{"id":"doi:10.1007/978-0-387-09823-4_20","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-0-387-09823-4_20","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery Handbook","raw_type":"book-chapter"},"type":"review","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/A5109252775","display_name":"Oded Maimon","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Oded Maimon","raw_affiliation_strings":[", Dept. Industrial Engineering, Tel Aviv University, Ramat Aviv, 69978, Israel","Department of Industrial Engineering, Tel-Aviv University, Ramat-Aviv, 69978, Israel"],"affiliations":[{"raw_affiliation_string":", Dept. Industrial Engineering, Tel Aviv University, Ramat Aviv, 69978, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"Department of Industrial Engineering, Tel-Aviv University, Ramat-Aviv, 69978, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071620349","display_name":"Shahar Cohen","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shahar Cohen","raw_affiliation_strings":["Department of Industrial Engineering, Tel-Aviv University, Ramat-Aviv, 69978, Israel"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, Tel-Aviv University, Ramat-Aviv, 69978, Israel","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109252775"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.14996266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"401","last_page":"417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9969000220298767,"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":0.9969000220298767,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9925000071525574,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9914000034332275,"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":0.8604168891906738},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6439653635025024},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6083834171295166},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6071723699569702},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6050652265548706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5632381439208984},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46757107973098755},{"id":"https://openalex.org/keywords/situated","display_name":"Situated","score":0.45989635586738586},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4247605502605438},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42242926359176636},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2645765542984009},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13427266478538513},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09176182746887207},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05934980511665344}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8604168891906738},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6439653635025024},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6083834171295166},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6071723699569702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6050652265548706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5632381439208984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46757107973098755},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.45989635586738586},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4247605502605438},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42242926359176636},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2645765542984009},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13427266478538513},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09176182746887207},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05934980511665344},{"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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-0-387-09823-4_20","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-0-387-09823-4_20","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery Handbook","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W46831063","https://openalex.org/W54548619","https://openalex.org/W189950281","https://openalex.org/W197638027","https://openalex.org/W578719842","https://openalex.org/W633040745","https://openalex.org/W1496590343","https://openalex.org/W1513468570","https://openalex.org/W1519783625","https://openalex.org/W1525019474","https://openalex.org/W1542941925","https://openalex.org/W1545148916","https://openalex.org/W1557517019","https://openalex.org/W1573474865","https://openalex.org/W1576452626","https://openalex.org/W1583837637","https://openalex.org/W1587157779","https://openalex.org/W1976223873","https://openalex.org/W1981276685","https://openalex.org/W1985921566","https://openalex.org/W1991001460","https://openalex.org/W2002830978","https://openalex.org/W2021834189","https://openalex.org/W2028145673","https://openalex.org/W2035446426","https://openalex.org/W2041367235","https://openalex.org/W2043594632","https://openalex.org/W2059582437","https://openalex.org/W2072758956","https://openalex.org/W2073993390","https://openalex.org/W2079488265","https://openalex.org/W2089415692","https://openalex.org/W2091171277","https://openalex.org/W2104602264","https://openalex.org/W2107726111","https://openalex.org/W2117341272","https://openalex.org/W2121863487","https://openalex.org/W2131600418","https://openalex.org/W2135311261","https://openalex.org/W2142839172","https://openalex.org/W2148173263","https://openalex.org/W2165131254","https://openalex.org/W2166101542","https://openalex.org/W2243662349","https://openalex.org/W2334782222","https://openalex.org/W2341171179","https://openalex.org/W2787259794","https://openalex.org/W2907549378","https://openalex.org/W2913077577","https://openalex.org/W3011120880","https://openalex.org/W4214717370","https://openalex.org/W4237924395","https://openalex.org/W4246165039","https://openalex.org/W4250042253"],"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":null,"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
