{"id":"https://openalex.org/W2522157686","doi":"https://doi.org/10.3233/978-1-61499-672-9-46","title":"Dynamic Choice of State Abstraction in Q-Learning","display_name":"Dynamic Choice of State Abstraction in Q-Learning","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2522157686","doi":"https://doi.org/10.3233/978-1-61499-672-9-46","mag":"2522157686"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-672-9-46","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-672-9-46","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/978-1-61499-672-9-46","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016550498","display_name":"Marco Tamassia","orcid":"https://orcid.org/0000-0001-6567-1380"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]},{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]}],"countries":["AU","MK"],"is_corresponding":true,"raw_author_name":"Tamassia Marco","raw_affiliation_strings":["[RMIT University]"],"affiliations":[{"raw_affiliation_string":"[RMIT University]","institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061528333","display_name":"Fabio Zambetta","orcid":"https://orcid.org/0000-0003-4133-7913"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]},{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]}],"countries":["AU","MK"],"is_corresponding":false,"raw_author_name":"Zambetta Fabio","raw_affiliation_strings":["[RMIT University]"],"affiliations":[{"raw_affiliation_string":"[RMIT University]","institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075906421","display_name":"William Raffe","orcid":"https://orcid.org/0000-0001-5310-0943"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]},{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]}],"countries":["AU","MK"],"is_corresponding":false,"raw_author_name":"Raffe William L.","raw_affiliation_strings":["[RMIT University]"],"affiliations":[{"raw_affiliation_string":"[RMIT University]","institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071394525","display_name":"Florian Mueller","orcid":"https://orcid.org/0000-0001-6472-3476"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]},{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]}],"countries":["AU","MK"],"is_corresponding":false,"raw_author_name":"Mueller Florian &lsquo;Floyd&rsquo;","raw_affiliation_strings":["[RMIT University]"],"affiliations":[{"raw_affiliation_string":"[RMIT University]","institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100369719","display_name":"Xiaodong Li","orcid":"https://orcid.org/0000-0003-0346-1526"},"institutions":[{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]},{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU","MK"],"is_corresponding":false,"raw_author_name":"Li Xiaodong","raw_affiliation_strings":["[RMIT University]"],"affiliations":[{"raw_affiliation_string":"[RMIT University]","institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016550498"],"corresponding_institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"],"apc_list":null,"apc_paid":null,"fwci":0.6848,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69188413,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9144999980926514,"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"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9144999980926514,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.7905372381210327},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5387028455734253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5006048679351807},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.44412586092948914},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.33843278884887695},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3186439871788025},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.18670135736465454},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.11587291955947876},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07815921306610107}],"concepts":[{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.7905372381210327},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5387028455734253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5006048679351807},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.44412586092948914},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.33843278884887695},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3186439871788025},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.18670135736465454},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.11587291955947876},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07815921306610107}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3233/978-1-61499-672-9-46","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-672-9-46","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:alma.61RMIT_INST:11247165470001341","is_oa":false,"landing_page_url":"http://doi.org/10.3233/978-1-61499-672-9-46","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2522157686","is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/conf/ecai/ecai2016.html#TamassiaZRML16","pdf_url":null,"source":{"id":"https://openalex.org/S4306418308","display_name":"European Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":"European Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":{"id":"doi:10.3233/978-1-61499-672-9-46","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-672-9-46","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027","https://openalex.org/W2962838298","https://openalex.org/W2600246793"],"abstract_inverted_index":{"Q-learning":[0,77,129],"associates":[1],"states":[2,47],"and":[3,26,41],"actions":[4],"of":[5,76],"a":[6,36,74],"Markov":[7],"Decision":[8],"Process":[9],"to":[10,65,106,118],"expected":[11],"future":[12],"reward":[13],"through":[14],"online":[15],"learning.":[16],"In":[17],"practice,":[18],"however,":[19],"when":[20],"the":[21,31,51,104,119,131],"state":[22,40,55,81,108],"space":[23],"is":[24,28,86,89],"large":[25],"experience":[27,42,85],"still":[29],"limited,":[30],"algorithm":[32,105,117],"will":[33,63],"not":[34,135],"find":[35],"match":[37],"between":[38],"current":[39],"unless":[43],"some":[44],"details":[45],"describing":[46],"are":[48],"ignored.":[49],"On":[50],"other":[52],"hand,":[53],"reducing":[54],"information":[56,101],"affects":[57],"long":[58],"term":[59],"performance":[60],"because":[61],"decisions":[62],"need":[64],"be":[66],"made":[67],"on":[68],"less":[69],"informative":[70],"inputs.":[71],"We":[72],"propose":[73],"variation":[75],"that":[78,96,102,124],"gradually":[79],"enriches":[80],"descriptions,":[82],"after":[83],"enough":[84],"accumulated.":[87],"This":[88],"coupled":[90],"with":[91],"an":[92],"ad-hoc":[93],"exploration":[94],"strategy":[95],"aims":[97],"at":[98],"collecting":[99],"key":[100],"allows":[103],"enrich":[107],"descriptions":[109],"earlier.":[110],"Experimental":[111],"results":[112],"obtained":[113],"by":[114],"applying":[115],"our":[116,125],"arcade":[120],"game":[121],"Pac-Man":[122],"show":[123],"approach":[126],"significantly":[127],"outperforms":[128],"during":[130],"learning":[132],"process":[133],"while":[134],"penalizing":[136],"long-term":[137],"performance.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-09-30T00:00:00"}
