{"id":"https://openalex.org/W13310149","doi":null,"title":"Decision tree methods for finding reusable MDP homomorphisms","display_name":"Decision tree methods for finding reusable MDP homomorphisms","publication_year":2006,"publication_date":"2006-07-16","ids":{"openalex":"https://openalex.org/W13310149","mag":"13310149"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.710","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aaai.org/Papers/AAAI/2006/AAAI06-085.pdf","raw_type":"text"},"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/A5055698707","display_name":"Alicia Peregrin Wolfe","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alicia P. Wolfe","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts, Amherst, Amherst, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Amherst, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089808068","display_name":"Andrew G. Barto","orcid":"https://orcid.org/0000-0002-3581-1896","observed_orcids":["https://orcid.org/0000-0002-3581-1896"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew G. Barto","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts, Amherst, Amherst, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Amherst, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":2.4699,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88677307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"530","last_page":"535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0012000000569969416,"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":9.999999747378752e-05,"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/state-abstraction","display_name":"state abstraction","score":0.8429999947547913},{"id":"https://openalex.org/keywords/decision-tree","display_name":"decision tree","score":0.8420000076293945},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.7139999866485596},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.3889999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343431711196899},{"id":"https://openalex.org/C4042151","wikidata":"https://www.wikidata.org/wiki/Q215111","display_name":"Homomorphism","level":2,"score":0.7058943510055542},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.619641900062561},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.6142643094062805},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5965660214424133},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5695438385009766},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5169069766998291},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.48711156845092773},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44313088059425354},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4414759576320648},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41363003849983215},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3560901880264282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2784002721309662},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23850256204605103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18687313795089722},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.10230618715286255},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07515904307365417},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.710","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aaai.org/Papers/AAAI/2006/AAAI06-085.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.91.2049","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.91.2049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-all.cs.umass.edu/~pippin/publications/AAAI0613WolfeA.pdf","raw_type":"text"},{"id":"mag:13310149","doi":null,"is_oa":false,"landing_page_url":"https://www.aaai.org/Papers/AAAI/2006/AAAI06-085.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306420577","display_name":"National Conference on Artificial Intelligence","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"National Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W79394677","https://openalex.org/W1486866330","https://openalex.org/W1519179592","https://openalex.org/W1530444831","https://openalex.org/W1564393562","https://openalex.org/W1583380718","https://openalex.org/W1598052524","https://openalex.org/W1640646391","https://openalex.org/W1800916125","https://openalex.org/W1988217924","https://openalex.org/W2052117683","https://openalex.org/W2058735307","https://openalex.org/W2107628283","https://openalex.org/W2109910161","https://openalex.org/W2120346334","https://openalex.org/W2128321349","https://openalex.org/W2138089556","https://openalex.org/W2170198047"],"related_works":["https://openalex.org/W2397240726","https://openalex.org/W2902272628","https://openalex.org/W7095488843","https://openalex.org/W2118022839","https://openalex.org/W1564393562","https://openalex.org/W7096945523","https://openalex.org/W7097197202","https://openalex.org/W7099617017","https://openalex.org/W6996751013","https://openalex.org/W7098386219"],"abstract_inverted_index":{"State":[0],"abstraction":[1,35],"is":[2],"a":[3,123,149],"useful":[4],"tool":[5],"for":[6,47],"agents":[7],"interacting":[8],"with":[9,103],"complex":[10],"environments.":[11],"Good":[12],"state":[13,34,63],"abstractions":[14],"are":[15,99,135],"compact,":[16,136],"reuseable,":[17],"and":[18,28,57,144],"easy":[19],"to":[20,37],"learn":[21,76],"from":[22,84,141],"sample":[23,85,142],"data.":[24,86],"This":[25],"paper":[26],"combines":[27],"extends":[29],"two":[30],"existing":[31],"classes":[32],"of":[33,44,55,68,79,151],"methods":[36,45,110],"achieve":[38],"these":[39],"criteria.":[40],"The":[41,65],"first":[42],"class":[43,67,150],"search":[46],"MDP":[48,90],"homomorphisms":[49,91],"(Ravindran":[50],"2004),":[51],"which":[52],"produce":[53],"models":[54,78,134],"reward":[56,105,152],"transition":[58],"probabilities":[59],"in":[60,116],"an":[61],"abstract":[62],"space.":[64],"second":[66],"methods,":[69],"like":[70,111],"the":[71,80,132],"UTree":[72,112],"algorithm":[73,126],"(McCallum":[74],"1995),":[75],"compact":[77],"value":[81,108],"function":[82],"quickly":[83,140],"Models":[87],"based":[88,109],"on":[89],"can":[92,137,145],"easily":[93],"be":[94,114,138,146],"extended":[95,115],"such":[96],"that":[97,127],"they":[98],"usable":[100],"across":[101,148],"tasks":[102],"similar":[104],"functions.":[106,153],"However,":[107],"cannot":[113],"this":[117],"fashion.":[118],"We":[119],"present":[120],"results":[121],"showing":[122],"new,":[124],"combined":[125],"fulfills":[128],"all":[129],"three":[130],"criteria:":[131],"resulting":[133],"learned":[139],"data,":[143],"used":[147]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}