{"id":"https://openalex.org/W3208917397","doi":"https://doi.org/10.1007/978-3-030-84337-3_11","title":"Reinforcement Learning: A Friendly Introduction","display_name":"Reinforcement Learning: A Friendly Introduction","publication_year":2021,"publication_date":"2021-08-07","ids":{"openalex":"https://openalex.org/W3208917397","doi":"https://doi.org/10.1007/978-3-030-84337-3_11","mag":"3208917397"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-84337-3_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-84337-3_11","pdf_url":null,"source":{"id":"https://openalex.org/S4210169156","display_name":"Lecture notes in networks and systems","issn_l":"2367-3370","issn":["2367-3370","2367-3389"],"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 in Networks and Systems","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/A5018648503","display_name":"Dema Daoun","orcid":"https://orcid.org/0000-0002-2861-8545"},"institutions":[{"id":"https://openalex.org/I146966710","display_name":"Asian University for Women","ror":"https://ror.org/01wp52t96","country_code":"BD","type":"education","lineage":["https://openalex.org/I146966710"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Dema Daoun","raw_affiliation_strings":["Department of Computer Science, Asian University for Women, Chittogram, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0002-2861-8545","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Asian University for Women, Chittogram, Bangladesh","institution_ids":["https://openalex.org/I146966710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084142949","display_name":"Fabiha Ibnat","orcid":"https://orcid.org/0000-0002-1694-4108"},"institutions":[{"id":"https://openalex.org/I146966710","display_name":"Asian University for Women","ror":"https://ror.org/01wp52t96","country_code":"BD","type":"education","lineage":["https://openalex.org/I146966710"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Fabiha Ibnat","raw_affiliation_strings":["Department of Computer Science, Asian University for Women, Chittogram, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0002-1694-4108","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Asian University for Women, Chittogram, Bangladesh","institution_ids":["https://openalex.org/I146966710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082090877","display_name":"Zulfikar Alom","orcid":"https://orcid.org/0000-0002-4073-0476"},"institutions":[{"id":"https://openalex.org/I146966710","display_name":"Asian University for Women","ror":"https://ror.org/01wp52t96","country_code":"BD","type":"education","lineage":["https://openalex.org/I146966710"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Zulfikar Alom","raw_affiliation_strings":["Department of Computer Science, Asian University for Women, Chittogram, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0002-4073-0476","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Asian University for Women, Chittogram, Bangladesh","institution_ids":["https://openalex.org/I146966710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005863795","display_name":"Zeyar Aung","orcid":"https://orcid.org/0000-0001-5990-9305"},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Zeyar Aung","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Khalifa University, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0001-5990-9305","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Khalifa University, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I176601375"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014109075","display_name":"Mohammad Abdul Azim","orcid":"https://orcid.org/0000-0001-5529-9482"},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Mohammad Abdul Azim","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Khalifa University, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0001-5529-9482","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Khalifa University, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I176601375"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8724,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.92689683,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"134","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9973999857902527,"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":0.9945999979972839,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9253063201904297},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7841333150863647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7284443378448486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6190570592880249},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43364861607551575},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.42709779739379883},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39133667945861816},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.2936236262321472},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2864381670951843},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.16812819242477417},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08272764086723328},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.04010838270187378}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9253063201904297},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7841333150863647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7284443378448486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6190570592880249},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43364861607551575},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.42709779739379883},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39133667945861816},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2936236262321472},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2864381670951843},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.16812819242477417},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08272764086723328},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.04010838270187378},{"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:10.1007/978-3-030-84337-3_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-84337-3_11","pdf_url":null,"source":{"id":"https://openalex.org/S4210169156","display_name":"Lecture notes in networks and systems","issn_l":"2367-3370","issn":["2367-3370","2367-3389"],"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 in Networks and Systems","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2009303086","https://openalex.org/W2041367235","https://openalex.org/W2056653303","https://openalex.org/W2080372674","https://openalex.org/W2097797606","https://openalex.org/W2107726111","https://openalex.org/W2159434869","https://openalex.org/W2169209873","https://openalex.org/W2257979135","https://openalex.org/W2546571074","https://openalex.org/W2620387295","https://openalex.org/W2774977638","https://openalex.org/W2780799698","https://openalex.org/W2787933113","https://openalex.org/W2788125442","https://openalex.org/W2913340405","https://openalex.org/W2945685808","https://openalex.org/W3103752844","https://openalex.org/W3106309118","https://openalex.org/W3198350258","https://openalex.org/W4240117034","https://openalex.org/W4298300677","https://openalex.org/W6600297719","https://openalex.org/W6600302053","https://openalex.org/W6601558329","https://openalex.org/W6601667473","https://openalex.org/W6607988376"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","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":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
