{"id":"https://openalex.org/W171197886","doi":null,"title":"Reinforcement Learning in a Nutshell","display_name":"Reinforcement Learning in a Nutshell","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W171197886","mag":"171197886"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.140.6913","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.140.6913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.neuroinformatik.ruhr-uni-bochum.de/thbio/members/profil/Heidrich-Meisner/H-MLIResann07.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5004382986","display_name":"Verena Heidrich-Meisner","orcid":"https://orcid.org/0000-0003-3502-8778","observed_orcids":["https://orcid.org/0000-0003-3502-8778"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Verena Heidrich-Meisner","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3502-8778","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008189468","display_name":"Martin Lauer","orcid":"https://orcid.org/0000-0003-4414-5722","observed_orcids":["https://orcid.org/0000-0003-4414-5722"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Lauer","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4414-5722","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042628612","display_name":"Christian Igel","orcid":"https://orcid.org/0000-0003-2868-0856","observed_orcids":["https://orcid.org/0000-0003-2868-0856"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian Igel","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2868-0856","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041323275","display_name":"Martin Riedmiller","orcid":"https://orcid.org/0000-0002-8465-5690","observed_orcids":["https://orcid.org/0000-0002-8465-5690"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Riedmiller","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8465-5690","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0741,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.8117222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"277","last_page":"288"},"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/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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":1.0},{"id":"https://openalex.org/keywords/policy-gradient","display_name":"policy gradient","score":0.9729999899864197},{"id":"https://openalex.org/keywords/machine-learning","display_name":"machine learning","score":0.5839999914169312}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8974380493164062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7240038514137268},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.7028456330299377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5881110429763794},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5415660738945007},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5013411045074463},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.453318327665329},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43321651220321655},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.140.6913","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.140.6913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.neuroinformatik.ruhr-uni-bochum.de/thbio/members/profil/Heidrich-Meisner/H-MLIResann07.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.218.3006","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.218.3006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dice.ucl.ac.be/Proceedings/esann/esannpdf/es2007-4.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.69.9557","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.9557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.neuroinformatik.ruhr-uni-bochum.de/ini/PEOPLE/igel/RLiaN.pdf","raw_type":"text"},{"id":"mag:171197886","doi":null,"is_oa":false,"landing_page_url":"http://homepage.ruhr-uni-bochum.de/verena.heidrich-meisner/HMLIResann2007.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306421047","display_name":"The European Symposium on Artificial Neural Networks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"The European Symposium on Artificial Neural Networks","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1491843047","https://openalex.org/W1513468570","https://openalex.org/W1519783625","https://openalex.org/W1542941925","https://openalex.org/W1576452626","https://openalex.org/W1583833196","https://openalex.org/W1592847719","https://openalex.org/W1594783240","https://openalex.org/W1646707810","https://openalex.org/W1687873425","https://openalex.org/W1914583973","https://openalex.org/W1946956835","https://openalex.org/W1965227651","https://openalex.org/W2009303086","https://openalex.org/W2032610016","https://openalex.org/W2041367235","https://openalex.org/W2045846579","https://openalex.org/W2054940200","https://openalex.org/W2071814471","https://openalex.org/W2072931156","https://openalex.org/W2096899507","https://openalex.org/W2099873296","https://openalex.org/W2100677568","https://openalex.org/W2109910161","https://openalex.org/W2113501460","https://openalex.org/W2116459397","https://openalex.org/W2119717200","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2130105540","https://openalex.org/W2132351269","https://openalex.org/W2137766593","https://openalex.org/W2144446635","https://openalex.org/W2155027007","https://openalex.org/W2156974606","https://openalex.org/W2158548602","https://openalex.org/W2159088729","https://openalex.org/W2170588376","https://openalex.org/W2489939061","https://openalex.org/W6884728263"],"related_works":["https://openalex.org/W7098155089","https://openalex.org/W2356822433","https://openalex.org/W6977152758","https://openalex.org/W1487481098","https://openalex.org/W2954232543","https://openalex.org/W6903763481","https://openalex.org/W2516180069","https://openalex.org/W3049728571","https://openalex.org/W7096245040","https://openalex.org/W7101032241"],"abstract_inverted_index":{"Abstract.":[0],"We":[1],"provide":[2],"a":[3],"concise":[4],"introduction":[5],"to":[6,9],"basic":[7],"approaches":[8],"reinforcement":[10],"learning":[11,15],"from":[12],"the":[13],"machine":[14],"perspective.":[16],"The":[17],"focus":[18],"is":[19],"on":[20],"value":[21],"function":[22],"and":[23],"policy":[24],"gradient":[25],"methods.":[26],"Some":[27],"selected":[28],"recent":[29],"trends":[30],"are":[31],"highlighted.":[32],"1":[33]},"counts_by_year":[{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}