{"id":"https://openalex.org/W2291938632","doi":null,"title":"Adaptive Abstraction for Model-Based Reinforcement Learning","display_name":"Adaptive Abstraction for Model-Based Reinforcement Learning","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2291938632","mag":"2291938632"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.159.9489","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.159.9489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mykel.kochenderfer.com/publications/Kochenderfer-2006-tech.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/A5068326377","display_name":"Mykel J. Kochenderfer","orcid":"https://orcid.org/0000-0002-7238-9663","observed_orcids":["https://orcid.org/0000-0002-7238-9663"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mykel J. Kochenderfer","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7238-9663","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5068326377"],"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":null,"issue":null,"first_page":null,"last_page":null},"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/T10906","display_name":"AI-based Problem Solving and Planning","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"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","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/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.8970000147819519},{"id":"https://openalex.org/keywords/state-abstraction","display_name":"state abstraction","score":0.6370000243186951},{"id":"https://openalex.org/keywords/region-splitting-and-merging","display_name":"region splitting and merging","score":0.8169999718666077},{"id":"https://openalex.org/keywords/planning","display_name":"planning","score":0.35600000619888306},{"id":"https://openalex.org/keywords/replanning","display_name":"replanning","score":0.8090000152587891},{"id":"https://openalex.org/keywords/large-state-and-action-spaces","display_name":"large state and action spaces","score":0.675000011920929}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7965710163116455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7528274059295654},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6964178085327148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5924637317657471},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5584725737571716},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5574119687080383},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5431209802627563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5103675723075867},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4881635308265686},{"id":"https://openalex.org/C171018156","wikidata":"https://www.wikidata.org/wiki/Q7370306","display_name":"Rotation formalisms in three dimensions","level":2,"score":0.46893763542175293},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.432447224855423},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42444413900375366},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4170484244823456},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1218283474445343},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.159.9489","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.159.9489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mykel.kochenderfer.com/publications/Kochenderfer-2006-tech.pdf","raw_type":"text"},{"id":"mag:2291938632","doi":null,"is_oa":false,"landing_page_url":"http://mykel.kochenderfer.com/files/Kochenderfer-2006-tech.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"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":65,"referenced_works":["https://openalex.org/W33980390","https://openalex.org/W65193931","https://openalex.org/W80760317","https://openalex.org/W1486747874","https://openalex.org/W1490760466","https://openalex.org/W1501627097","https://openalex.org/W1510073064","https://openalex.org/W1511887321","https://openalex.org/W1552830313","https://openalex.org/W1557414194","https://openalex.org/W1563088657","https://openalex.org/W1583380718","https://openalex.org/W1583993172","https://openalex.org/W1640646391","https://openalex.org/W1804031886","https://openalex.org/W1857789879","https://openalex.org/W1891931698","https://openalex.org/W1966195676","https://openalex.org/W1975152892","https://openalex.org/W1982997797","https://openalex.org/W1989388297","https://openalex.org/W1995875735","https://openalex.org/W1995945562","https://openalex.org/W2009533501","https://openalex.org/W2027154457","https://openalex.org/W2031692264","https://openalex.org/W2032427901","https://openalex.org/W2038044292","https://openalex.org/W2046577860","https://openalex.org/W2048226872","https://openalex.org/W2058735307","https://openalex.org/W2061945428","https://openalex.org/W2063301486","https://openalex.org/W2065528935","https://openalex.org/W2079100340","https://openalex.org/W2084224084","https://openalex.org/W2101167844","https://openalex.org/W2107726111","https://openalex.org/W2112483970","https://openalex.org/W2114054213","https://openalex.org/W2114882146","https://openalex.org/W2117303033","https://openalex.org/W2117629901","https://openalex.org/W2119567691","https://openalex.org/W2121733891","https://openalex.org/W2122111042","https://openalex.org/W2124817418","https://openalex.org/W2125113001","https://openalex.org/W2136719210","https://openalex.org/W2141559645","https://openalex.org/W2147169507","https://openalex.org/W2149706766","https://openalex.org/W2153233077","https://openalex.org/W2154727892","https://openalex.org/W2160805324","https://openalex.org/W2163952039","https://openalex.org/W2185346292","https://openalex.org/W2337490104","https://openalex.org/W2341171179","https://openalex.org/W2521833123","https://openalex.org/W2913433435","https://openalex.org/W2951539267","https://openalex.org/W3011120880","https://openalex.org/W3020831056","https://openalex.org/W3139831614"],"related_works":["https://openalex.org/W6989004762","https://openalex.org/W1844343792","https://openalex.org/W2786957659","https://openalex.org/W3215958329","https://openalex.org/W2998443480","https://openalex.org/W4385517529","https://openalex.org/W7096793844","https://openalex.org/W3041880230","https://openalex.org/W2801113701","https://openalex.org/W6947978711"],"abstract_inverted_index":{"This":[0,233],"paper":[1,234],"presents":[2],"a":[3,20,33,92,117,133,142,156],"novel":[4],"model-based":[5,21],"reinforcement":[6,22],"learning":[7,23,147,244],"framework":[8],"called":[9],"the":[10,29,43,59,77,80,99,170,204,210,215,219,224,236],"Adaptive":[11],"Modelling":[12],"and":[13,40,55,61,106,124,148,222,238],"Planning":[14],"System":[15],"(AMPS).":[16],"The":[17,137,161],"challenge":[18],"of":[19,67,95,120,135,159,169,240],"agent":[24,44,225],"is":[25,149],"using":[26,116,141],"experience":[27,49],"in":[28,76,128,203,209,230,243],"world":[30],"to":[31,112,132,145,154,194,207,214],"generate":[32],"model.":[34],"In":[35],"problems":[36,115],"with":[37],"large":[38,93],"state":[39,60],"action":[41,62],"spaces,":[42],"must":[45],"generalise":[46,103],"from":[47],"limited":[48],"by":[50],"grouping":[51],"together":[52],"similar":[53],"states":[54],"actions,":[56,105],"effectively":[57],"partitioning":[58],"spaces":[63],"into":[64],"finite":[65],"sets":[66],"regions.":[68,232],"Several":[69],"different":[70,182],"abstraction":[71,130,205],"approaches":[72],"have":[73,83],"been":[74],"proposed":[75],"literature,":[78],"but":[79],"existing":[81,126,164],"algorithms":[82],"many":[84],"limitations.":[85],"They":[86],"generally":[87],"only":[88],"increase":[89],"resolution,":[90],"require":[91,185],"amount":[94],"data":[96],"before":[97],"changing":[98],"abstraction,":[100],"do":[101],"not":[102],"over":[104],"are":[107,200],"computationally":[108],"expensive.":[109],"AMPS":[110,122,153,191,217],"aims":[111],"solve":[113],"these":[114],"new":[118],"kind":[119],"approach.":[121],"splits":[123,140],"merges":[125,163],"regions":[127,165,183],"its":[129],"according":[131],"set":[134],"heuristics.":[136],"system":[138,162],"introduces":[139],"mechanism":[143],"related":[144],"supervised":[146],"defined":[150],"generally,":[151],"allowing":[152],"leverage":[155],"wide":[157],"variety":[158],"representations.":[160],"when":[166,223],"an":[167],"analysis":[168],"current":[171],"plan":[172],"indicates":[173],"that":[174],"doing":[175],"so":[176],"could":[177],"be":[178],"useful.":[179],"Because":[180],"several":[181],"may":[184],"revision":[186,193],"at":[187],"any":[188],"given":[189],"time,":[190,227],"prioritises":[192,218],"best":[195],"utilise":[196],"whatever":[197],"computational":[198],"resources":[199],"available.":[201],"Changes":[202],"lead":[206],"changes":[208,213],"model,":[211],"requiring":[212],"plan.":[216],"planning":[220],"process,":[221],"has":[226],"it":[228],"replans":[229],"high-priority":[231],"demonstrates":[235],"flexibility":[237],"strength":[239],"this":[241],"approach":[242]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}