{"id":"https://openalex.org/W2039109166","doi":"https://doi.org/10.1109/sii.2012.6427332","title":"Rule abstraction and transfer in reinforcement learning by decision tree","display_name":"Rule abstraction and transfer in reinforcement learning by decision tree","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2039109166","doi":"https://doi.org/10.1109/sii.2012.6427332","mag":"2039109166"},"language":"en","primary_location":{"id":"doi:10.1109/sii.2012.6427332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii.2012.6427332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE/SICE International Symposium on System Integration (SII)","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/A5100340964","display_name":"Min Wu","orcid":"https://orcid.org/0000-0003-0977-3600"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Min Wu","raw_affiliation_strings":["Department of Precision Engineering, University of Tokyo, Hongo, Tokyo, Japan","Department of Precision Engineering, the University of Tokyo, Hongo 7-3-1, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Precision Engineering, University of Tokyo, Hongo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Department of Precision Engineering, the University of Tokyo, Hongo 7-3-1, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021260328","display_name":"Atsushi Yamashita","orcid":"https://orcid.org/0000-0003-1280-069X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Yamashita","raw_affiliation_strings":["Faculty of Precision Engineering, University of Tokyo, Hongo, Tokyo, Japan","Faculty of Precision Engineering, the University of Tokyo, Hongo 7-3-1, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Precision Engineering, University of Tokyo, Hongo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Faculty of Precision Engineering, the University of Tokyo, Hongo 7-3-1, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064103302","display_name":"Hajime Asama","orcid":"https://orcid.org/0000-0002-9482-497X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hajime Asama","raw_affiliation_strings":["Faculty of Department of Precision Engineering, University of Tokyo, Hongo, Tokyo, Japan","Faculty of Departement of Precision Engineering, the University of Tokyo, Hongo 7-3-1, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Department of Precision Engineering, University of Tokyo, Hongo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Faculty of Departement of Precision Engineering, the University of Tokyo, Hongo 7-3-1, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100340964"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.09658968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"529","last_page":"534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9883000254631042,"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/computer-science","display_name":"Computer science","score":0.7665150761604309},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7438799738883972},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6112380623817444},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5762837529182434},{"id":"https://openalex.org/keywords/decision-table","display_name":"Decision table","score":0.5707201957702637},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5656600594520569},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.532306432723999},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5286881327629089},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4867127239704132},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.48471522331237793},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.47821876406669617},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4654358923435211},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.4291786551475525},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.22422710061073303},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12126216292381287},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09006857872009277}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7665150761604309},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7438799738883972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6112380623817444},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5762837529182434},{"id":"https://openalex.org/C172967692","wikidata":"https://www.wikidata.org/wiki/Q747762","display_name":"Decision table","level":3,"score":0.5707201957702637},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5656600594520569},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.532306432723999},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5286881327629089},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4867127239704132},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.48471522331237793},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.47821876406669617},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4654358923435211},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.4291786551475525},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.22422710061073303},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12126216292381287},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09006857872009277},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111012933","wikidata":"https://www.wikidata.org/wiki/Q3137210","display_name":"Rough set","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sii.2012.6427332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii.2012.6427332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W190675879","https://openalex.org/W1555801537","https://openalex.org/W1783866091","https://openalex.org/W2097381042","https://openalex.org/W2107726111","https://openalex.org/W2119475352","https://openalex.org/W2121863487","https://openalex.org/W2126357802","https://openalex.org/W2149706766","https://openalex.org/W2153947321","https://openalex.org/W2158316397","https://openalex.org/W2952485636","https://openalex.org/W3020831056","https://openalex.org/W4214717370","https://openalex.org/W4236137412","https://openalex.org/W6607768588","https://openalex.org/W6638076483","https://openalex.org/W6682802936"],"related_works":["https://openalex.org/W2047835521","https://openalex.org/W2045155990","https://openalex.org/W4313163053","https://openalex.org/W64552174","https://openalex.org/W4300973204","https://openalex.org/W2539548808","https://openalex.org/W4312280743","https://openalex.org/W3159301561","https://openalex.org/W273478400","https://openalex.org/W2362185709"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,67],"agents":[2],"store":[3],"their":[4],"knowledge":[5,62],"such":[6],"as":[7],"state-action":[8],"value":[9],"in":[10,63],"look-up":[11,28],"tables.":[12],"However,":[13],"loop-up":[14],"table":[15,29],"requires":[16],"large":[17],"memory":[18],"space":[19],"when":[20],"number":[21],"of":[22],"states":[23],"become":[24],"large.":[25],"Learning":[26],"from":[27,65],"is":[30,33,53],"tabularasa":[31],"therefore":[32],"very":[34],"slow.":[35],"To":[36],"overcome":[37],"this":[38,48],"disadvantage,":[39],"generalization":[40],"methods":[41],"are":[42],"used":[43,54],"to":[44,55,59],"abstract":[45,61],"knowledge.":[46],"In":[47],"paper,":[49],"decision":[50],"tree":[51],"technology":[52],"enable":[56],"the":[57],"agent":[58],"represent":[60],"rule":[64,71],"during":[66],"progress":[68],"and":[69],"form":[70],"base":[72],"for":[73],"each":[74],"individual":[75],"task.":[76]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}