{"id":"https://openalex.org/W775841705","doi":null,"title":"Experimental Study on Parameter Selection for Reinforcement Learning Algorithms","display_name":"Experimental Study on Parameter Selection for Reinforcement Learning Algorithms","publication_year":2008,"publication_date":"2008-11-30","ids":{"openalex":"https://openalex.org/W775841705","mag":"775841705"},"language":"en","primary_location":{"id":"mag:775841705","doi":null,"is_oa":false,"landing_page_url":"http://yadda.icm.edu.pl/yadda/element/bwmeta1.element.baztech-article-BUJ7-0008-0040","pdf_url":null,"source":{"id":"https://openalex.org/S2764737260","display_name":"Theoretical and Applied Informatics","issn_l":"1896-5334","issn":["1896-5334","2300-889X"],"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":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Theoretical and Applied Informatics","raw_type":null},"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/A5023966172","display_name":"Roman Zajdel","orcid":"https://orcid.org/0000-0003-0903-4023","observed_orcids":["https://orcid.org/0000-0003-0903-4023"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Roman Zajdel","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0903-4023","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5023966172"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":"2","first_page":"71","last_page":"85"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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/reinforcement-learning","display_name":"reinforcement learning","score":0.871999979019165},{"id":"https://openalex.org/keywords/learning-efficiency","display_name":"learning efficiency","score":0.5249999761581421},{"id":"https://openalex.org/keywords/cart-pole-system","display_name":"cart-pole system","score":0.8349999785423279},{"id":"https://openalex.org/keywords/ball-and-beam-system","display_name":"ball and beam system","score":0.9049999713897705}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8410030603408813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8237779140472412},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6514176726341248},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5948240756988525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5625001788139343},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5237212777137756},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.5114609003067017},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.4385325312614441},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12834641337394714},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:775841705","doi":null,"is_oa":false,"landing_page_url":"http://yadda.icm.edu.pl/yadda/element/bwmeta1.element.baztech-article-BUJ7-0008-0040","pdf_url":null,"source":{"id":"https://openalex.org/S2764737260","display_name":"Theoretical and Applied Informatics","issn_l":"1896-5334","issn":["1896-5334","2300-889X"],"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":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Theoretical and Applied Informatics","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":13,"referenced_works":["https://openalex.org/W1505888104","https://openalex.org/W1549353711","https://openalex.org/W1605318140","https://openalex.org/W1996579288","https://openalex.org/W2007575508","https://openalex.org/W2028357975","https://openalex.org/W2041126907","https://openalex.org/W2057447866","https://openalex.org/W2071570156","https://openalex.org/W2101242010","https://openalex.org/W2107726111","https://openalex.org/W2121863487","https://openalex.org/W2124175081"],"related_works":["https://openalex.org/W2152164659","https://openalex.org/W2146957157","https://openalex.org/W1706571876","https://openalex.org/W4386979406","https://openalex.org/W2050024476","https://openalex.org/W5547603","https://openalex.org/W2767323719","https://openalex.org/W7010630034","https://openalex.org/W2128786740","https://openalex.org/W7096915865"],"abstract_inverted_index":{"The":[0,86,119,136],"use":[1],"of":[2,12,20,30,63,79,89,105,107,116,121,129,133,144],"the":[3,17,41,61,74,77,80,96,99,103,114,122,130,142,145,148],"reinforcement":[4,108],"learning":[5,21,32,109],"algorithms":[6,33,70,110],"is":[7,38,49,84,92,125],"contended":[8],"with":[9,73,141],"a":[10],"number":[11],"practical":[13],"problems":[14],"related":[15],"to":[16,67,93,112],"proper":[18],"choice":[19],"parameters.":[22],"There":[23],"are":[24,138],"three":[25,69],"such":[26,54],"factors":[27,106],"in":[28,127],"case":[29],"Q(lambda)-":[31],"and":[34,111,147],"five":[35],"when":[36],"AHC(lambda)":[37],"considered.":[39],"On":[40],"other":[42],"hand,":[43],"more":[44],"rarely":[45],"applied":[46],"R-learning":[47,75],"algorithm":[48],"parametrized":[50],"by":[51],"only":[52],"two":[53],"factors,":[55],"however":[56],"it":[57],"does":[58],"not":[59],"possess":[60],"method":[62,82],"accelerating.":[64],"In":[65],"order":[66],"compare":[68,113],"mentioned":[71],"earlier":[72],"algorithm,":[76],"implementation":[78],"temporal-dierence":[81],"TD(lambda)":[83],"proposed.":[85],"main":[87],"purpose":[88],"this":[90],"study":[91],"formulate,":[94],"on":[95],"empirical":[97],"way,":[98],"general":[100],"recommendation":[101],"regarding":[102],"selection":[104,124],"eciency":[115],"these":[117],"algorithms.":[118],"criterion":[120],"factor":[123],"determined":[126],"terms":[128],"highest":[131],"probability":[132],"learned":[134],"system.":[135,150],"experiments":[137],"carried":[139],"out":[140],"model":[143],"cart-pole":[146],"ball-beam":[149]},"counts_by_year":[],"updated_date":"2025-10-10T17:16:08.811792","created_date":"2016-06-24T00:00:00"}