{"id":"https://openalex.org/W87596044","doi":null,"title":"Generalization in Reinforcement Learning","display_name":"Generalization in Reinforcement Learning","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W87596044","mag":"87596044"},"language":"en","primary_location":{"id":"mag:87596044","doi":null,"is_oa":false,"landing_page_url":"http://staff.science.uva.nl/~bredeweg/pdf/BSc/20082009/Honours/Josemans.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"parent_works":[],"lineage":["https://openalex.org/W87596044"],"child_works_count":0,"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/A5090636718","display_name":"Wouter Josemans","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wouter Josemans","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5090636718"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7133,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84548469,"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":null,"last_page":null},"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/T11574","display_name":"Artificial Intelligence in Games","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/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/generalization","display_name":"generalization","score":0.8209999799728394},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"temporal difference learning","score":0.9739999771118164},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8240000009536743},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8970000147819519},{"id":"https://openalex.org/keywords/function-approximation","display_name":"function approximation","score":0.7310000061988831},{"id":"https://openalex.org/keywords/radial-basis-functions","display_name":"radial basis functions","score":0.902999997138977},{"id":"https://openalex.org/keywords/discrete-action-space","display_name":"discrete action space","score":0.9409999847412109},{"id":"https://openalex.org/keywords/hyperparameter-sensitivity","display_name":"hyperparameter sensitivity","score":0.6370000243186951}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8044970035552979},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6967133283615112},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6649989485740662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5516869425773621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5072779059410095},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5058550834655762},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4905966818332672},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.468788743019104},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.41799306869506836},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4105633497238159},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3731728792190552},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.36099666357040405},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3434060215950012},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15532264113426208},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13253238797187805},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.09041810035705566},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07810160517692566},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:87596044","doi":null,"is_oa":false,"landing_page_url":"http://staff.science.uva.nl/~bredeweg/pdf/BSc/20082009/Honours/Josemans.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"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":14,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W182596629","https://openalex.org/W1600046456","https://openalex.org/W1646707810","https://openalex.org/W1949804828","https://openalex.org/W2048993376","https://openalex.org/W2124175081","https://openalex.org/W2125074935","https://openalex.org/W2131600418","https://openalex.org/W2131831090","https://openalex.org/W2139418546","https://openalex.org/W2341171179","https://openalex.org/W3011120880","https://openalex.org/W3139377883"],"related_works":["https://openalex.org/W7096556623","https://openalex.org/W3013662176","https://openalex.org/W4281634883","https://openalex.org/W3164513830","https://openalex.org/W2998146683","https://openalex.org/W7161398820","https://openalex.org/W4406665674","https://openalex.org/W1760981091","https://openalex.org/W2118144213"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"evaluate":[4],"two":[5],"Temporal":[6],"Difference":[7],"Reinforcement":[8,63],"Learning":[9,64],"methods":[10,20,78],"on":[11],"several":[12],"different":[13],"tasks":[14,23,53],"to":[15,81],"see":[16],"how":[17],"well":[18],"these":[19],"generalize.":[21],"The":[22,52],"were":[24,54,79],"modeled":[25],"as":[26,50],"Markov":[27],"Decision":[28],"Processes":[29],"with":[30,48],"a":[31,36,88],"continuous":[32],"observation":[33],"space":[34],"and":[35],"discrete":[37],"action":[38],"space.":[39],"Function":[40],"approximation":[41],"was":[42,67],"done":[43],"using":[44],"linear":[45],"gradient":[46],"descent":[47],"RBFs":[49],"features.":[51],"taken":[55],"from":[56],"the":[57,61,70],"Polyathlon":[58],"domain":[59],"of":[60,90],"2009":[62],"Competition.":[65],"It":[66],"found":[68],"that":[69],"more":[71],"sophisticated":[72],"method":[73],"generalized":[74],"better,":[75],"but":[76],"both":[77],"sensitive":[80],"changes":[82],"in":[83],"parameters,":[84],"so":[85],"there":[86],"is":[87],"lot":[89],"room":[91],"for":[92],"improvement.":[93]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}
