{"id":"https://openalex.org/W2048993376","doi":"https://doi.org/10.1145/1570256.1570375","title":"Reinforcement learning for games","display_name":"Reinforcement learning for games","publication_year":2009,"publication_date":"2009-07-08","ids":{"openalex":"https://openalex.org/W2048993376","doi":"https://doi.org/10.1145/1570256.1570375","mag":"2048993376"},"language":"en","primary_location":{"id":"doi:10.1145/1570256.1570375","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1570256.1570375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking Papers","raw_type":"proceedings-article"},"type":"article","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/A5057857679","display_name":"Wolfgang Konen","orcid":"https://orcid.org/0000-0002-1343-4209"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wolfgang Konen","raw_affiliation_strings":["Cologne University of Applied Sciences, Gummersbach, Germany","Cologne University of Applied Sciences, Gummersbach, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Cologne University of Applied Sciences, Gummersbach, Germany","institution_ids":[]},{"raw_affiliation_string":"Cologne University of Applied Sciences, Gummersbach, Germany#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020539256","display_name":"Thomas Bartz\u2013Beielstein","orcid":"https://orcid.org/0000-0002-5938-5158"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Bartz-Beielstein","raw_affiliation_strings":["Cologne University of Applied Sciences, Gummersbach, Germany","Cologne University of Applied Sciences, Gummersbach, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Cologne University of Applied Sciences, Gummersbach, Germany","institution_ids":[]},{"raw_affiliation_string":"Cologne University of Applied Sciences, Gummersbach, Germany#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057857679"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2581,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.89337299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2641","last_page":"2648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9993000030517578,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9987999796867371,"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":0.8874059319496155},{"id":"https://openalex.org/keywords/cma-es","display_name":"CMA-ES","score":0.7379781007766724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7117015719413757},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6725081205368042},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.6299384832382202},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5922866463661194},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.552208662033081},{"id":"https://openalex.org/keywords/evolution-strategy","display_name":"Evolution strategy","score":0.5353259444236755},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45147034525871277},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4174261689186096},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.19583067297935486},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08563441038131714}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8874059319496155},{"id":"https://openalex.org/C205555498","wikidata":"https://www.wikidata.org/wiki/Q505588","display_name":"CMA-ES","level":4,"score":0.7379781007766724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7117015719413757},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6725081205368042},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6299384832382202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5922866463661194},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.552208662033081},{"id":"https://openalex.org/C207002847","wikidata":"https://www.wikidata.org/wiki/Q2912857","display_name":"Evolution strategy","level":3,"score":0.5353259444236755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45147034525871277},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4174261689186096},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.19583067297935486},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08563441038131714},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1570256.1570375","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1570256.1570375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking Papers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W19335976","https://openalex.org/W1199234532","https://openalex.org/W1499264356","https://openalex.org/W1515851193","https://openalex.org/W1547737196","https://openalex.org/W1548589545","https://openalex.org/W1569296262","https://openalex.org/W1995875735","https://openalex.org/W2041367235","https://openalex.org/W2049287437","https://openalex.org/W2098559630","https://openalex.org/W2100677568","https://openalex.org/W2101677491","https://openalex.org/W2111935653","https://openalex.org/W2112036188","https://openalex.org/W2121863487","https://openalex.org/W2123240248","https://openalex.org/W2138178898","https://openalex.org/W2138431811","https://openalex.org/W2152164659","https://openalex.org/W2162813238","https://openalex.org/W2207319790","https://openalex.org/W3198350258"],"related_works":["https://openalex.org/W1579744901","https://openalex.org/W1492325323","https://openalex.org/W2510724351","https://openalex.org/W2145363145","https://openalex.org/W3087341323","https://openalex.org/W2465356436","https://openalex.org/W2552260697","https://openalex.org/W2341346307","https://openalex.org/W2592891920","https://openalex.org/W2048993376"],"abstract_inverted_index":{"We":[0],"apply":[1],"CMA-ES,":[2],"an":[3],"evolution":[4],"strategy":[5],"with":[6,59,81],"covariance":[7],"matrix":[8],"adaptation,":[9],"and":[10,54],"TDL":[11],"(Temporal":[12],"Difference":[13],"Learning)":[14],"to":[15,25,43,64,92],"reinforcement":[16],"learning":[17,49,52],"tasks.":[18],"In":[19],"both":[20],"cases":[21],"these":[22],"algorithms":[23],"seek":[24],"optimize":[26],"a":[27,36],"neural":[28],"network":[29],"which":[30,71],"provides":[31],"the":[32,45,65,84,93],"policy":[33],"for":[34,90],"playing":[35],"simple":[37],"game":[38],"(TicTacToe).":[39],"Our":[40],"contribution":[41],"is":[42],"study":[44],"effect":[46],"of":[47,67,86,96],"varying":[48],"conditions":[50],"on":[51],"speed":[53],"quality.":[55],"Certain":[56],"initial":[57],"failures":[58],"wrong":[60],"fitness":[61,69,77],"functions":[62,78],"lead":[63],"development":[66],"new":[68,76],"functions,":[70],"allow":[72],"fast":[73],"learning.":[74],"These":[75],"in":[79],"combination":[80],"CMA-ES":[82],"reduce":[83],"number":[85],"required":[87],"games":[88],"needed":[89],"training":[91],"same":[94],"order":[95],"magnitude":[97],"as":[98],"TDL.":[99]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}