{"id":"https://openalex.org/W4240117034","doi":"https://doi.org/10.4249/scholarpedia.1448","title":"Reinforcement learning","display_name":"Reinforcement learning","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W4240117034","doi":"https://doi.org/10.4249/scholarpedia.1448"},"language":"en","primary_location":{"id":"doi:10.4249/scholarpedia.1448","doi":"https://doi.org/10.4249/scholarpedia.1448","is_oa":true,"landing_page_url":"https://doi.org/10.4249/scholarpedia.1448","pdf_url":null,"source":{"id":"https://openalex.org/S177062229","display_name":"Scholarpedia","issn_l":"1941-6016","issn":["1941-6016"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1"],"host_organization":"https://openalex.org/P4310316840","host_organization_name":"Scholarpedia Corporation","host_organization_lineage":["https://openalex.org/P4310316840"],"host_organization_lineage_names":["Scholarpedia Corporation"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scholarpedia","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.4249/scholarpedia.1448","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023811677","display_name":"Florentin W\u00f6rg\u00f6tter","orcid":"https://orcid.org/0000-0001-8206-9738","observed_orcids":["https://orcid.org/0000-0001-8206-9738"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florentin Woergoetter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5091850362","display_name":"Bernd Porr","orcid":"https://orcid.org/0000-0001-8157-998X","observed_orcids":["https://orcid.org/0000-0001-8157-998X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bernd Porr","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4049,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.81584813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"3","issue":"3","first_page":"1448","last_page":"1448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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":0.0,"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":0.9279999732971191},{"id":"https://openalex.org/keywords/learning-through-interaction","display_name":"learning from interaction","score":0.5770000219345093},{"id":"https://openalex.org/keywords/optimal-control","display_name":"optimal control","score":0.6890000104904175},{"id":"https://openalex.org/keywords/decision-making","display_name":"decision-making","score":0.4519999921321869},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.621999979019165}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.44277462363243103},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43206971883773804},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.41887032985687256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.29858624935150146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21421441435813904},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08254018425941467}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.4249/scholarpedia.1448","doi":"https://doi.org/10.4249/scholarpedia.1448","is_oa":true,"landing_page_url":"https://doi.org/10.4249/scholarpedia.1448","pdf_url":null,"source":{"id":"https://openalex.org/S177062229","display_name":"Scholarpedia","issn_l":"1941-6016","issn":["1941-6016"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1"],"host_organization":"https://openalex.org/P4310316840","host_organization_name":"Scholarpedia Corporation","host_organization_lineage":["https://openalex.org/P4310316840"],"host_organization_lineage_names":["Scholarpedia Corporation"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scholarpedia","raw_type":"journal-article"},{"id":"pmh:oai:eprints.gla.ac.uk:46466","doi":null,"is_oa":false,"landing_page_url":"http://eprints.gla.ac.uk/46466/","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":false,"is_in_doaj":true,"is_core":false,"listed_in":["doaj"],"host_organization":"https://openalex.org/I4405259220","host_organization_name":"Institut Agama Islam Negeri Langsa","host_organization_lineage":["https://openalex.org/I4405259220"],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Articles"}],"best_oa_location":{"id":"doi:10.4249/scholarpedia.1448","doi":"https://doi.org/10.4249/scholarpedia.1448","is_oa":true,"landing_page_url":"https://doi.org/10.4249/scholarpedia.1448","pdf_url":null,"source":{"id":"https://openalex.org/S177062229","display_name":"Scholarpedia","issn_l":"1941-6016","issn":["1941-6016"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1"],"host_organization":"https://openalex.org/P4310316840","host_organization_name":"Scholarpedia Corporation","host_organization_lineage":["https://openalex.org/P4310316840"],"host_organization_lineage_names":["Scholarpedia Corporation"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scholarpedia","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2911283634","https://openalex.org/W4396692931","https://openalex.org/W6884305255","https://openalex.org/W4241843487","https://openalex.org/W4214717370","https://openalex.org/W4300341211","https://openalex.org/W4301513923","https://openalex.org/W7115060773","https://openalex.org/W4250629717","https://openalex.org/W7128112917"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2022-05-12T00:00:00"}