{"id":"https://openalex.org/W1921016406","doi":"https://doi.org/10.1145/2717316","title":"Online Planning for Large Markov Decision Processes with Hierarchical Decomposition","display_name":"Online Planning for Large Markov Decision Processes with Hierarchical Decomposition","publication_year":2015,"publication_date":"2015-07-15","ids":{"openalex":"https://openalex.org/W1921016406","doi":"https://doi.org/10.1145/2717316","mag":"1921016406"},"language":"en","primary_location":{"id":"doi:10.1145/2717316","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2717316","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-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/A5083303426","display_name":"Aijun Bai","orcid":"https://orcid.org/0000-0002-5164-4629"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aijun Bai","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029102289","display_name":"Feng Wu","orcid":"https://orcid.org/0000-0003-3989-0509"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Wu","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084710341","display_name":"Xiaoping Chen","orcid":"https://orcid.org/0000-0001-8992-9286"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoping Chen","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.239,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.98080292,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"6","issue":"4","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9894000291824341,"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/T10260","display_name":"Software Engineering Research","score":0.9783999919891357,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9020698666572571},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7419157028198242},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6084288954734802},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5585188865661621},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5390348434448242},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5105468034744263},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.49045464396476746},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4711536169052124},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46105659008026123},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4513480067253113},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.43611469864845276},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4316447973251343},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3314201831817627},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2848401665687561}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9020698666572571},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7419157028198242},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6084288954734802},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5585188865661621},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5390348434448242},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5105468034744263},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.49045464396476746},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4711536169052124},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46105659008026123},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4513480067253113},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.43611469864845276},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4316447973251343},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3314201831817627},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2848401665687561},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2717316","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2717316","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6800000071525574,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3900523166","display_name":null,"funder_award_id":"60745002,61175057","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W7119785","https://openalex.org/W108082272","https://openalex.org/W134602879","https://openalex.org/W178169250","https://openalex.org/W1515851193","https://openalex.org/W1540839255","https://openalex.org/W1545006598","https://openalex.org/W1577509784","https://openalex.org/W1578521162","https://openalex.org/W1586162706","https://openalex.org/W1589901344","https://openalex.org/W1592847719","https://openalex.org/W1598052524","https://openalex.org/W1619459736","https://openalex.org/W1625390266","https://openalex.org/W1631187438","https://openalex.org/W1792278168","https://openalex.org/W1857173971","https://openalex.org/W1899715700","https://openalex.org/W1976800061","https://openalex.org/W1997840820","https://openalex.org/W2009533501","https://openalex.org/W2009796613","https://openalex.org/W2028838947","https://openalex.org/W2089561656","https://openalex.org/W2090170171","https://openalex.org/W2097381042","https://openalex.org/W2098432798","https://openalex.org/W2099619710","https://openalex.org/W2104641222","https://openalex.org/W2105757562","https://openalex.org/W2105809411","https://openalex.org/W2109910161","https://openalex.org/W2110654099","https://openalex.org/W2116708838","https://openalex.org/W2119567691","https://openalex.org/W2121517924","https://openalex.org/W2126316555","https://openalex.org/W2127412976","https://openalex.org/W2141754131","https://openalex.org/W2152475379","https://openalex.org/W2153668164","https://openalex.org/W2157136665","https://openalex.org/W2161252410","https://openalex.org/W2164102968","https://openalex.org/W2168024904","https://openalex.org/W2168359464","https://openalex.org/W2168405694","https://openalex.org/W2169977622","https://openalex.org/W2225974540","https://openalex.org/W2295500160","https://openalex.org/W2341171179","https://openalex.org/W2341906087","https://openalex.org/W2397240726","https://openalex.org/W2531563875","https://openalex.org/W2560674852","https://openalex.org/W2561675875","https://openalex.org/W2623660146","https://openalex.org/W2735260544","https://openalex.org/W3010488986","https://openalex.org/W3023151133","https://openalex.org/W4233840023","https://openalex.org/W4249441547"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4404955202"],"abstract_inverted_index":{"Markov":[0],"decision":[1],"processes":[2],"(MDPs)":[3],"provide":[4],"a":[5,15,46,63,86,104,111,189,194,202],"rich":[6],"framework":[7],"for":[8,48,124,177],"planning":[9,122,139],"under":[10],"uncertainty.":[11],"However,":[12],"exactly":[13],"solving":[14],"large":[16,125,240],"MDP":[17,99],"is":[18,74,85,142],"usually":[19],"intractable":[20],"due":[21],"to":[22,61,136,144,238],"the":[23,27,33,49,54,71,79,93,97,151,171,180,216,230,234],"\u201ccurse":[24],"of":[25,35,81,96,106,182,220,236],"dimensionality\u201d\u2014":[26],"state":[28,36,51],"space":[29],"grows":[30],"exponentially":[31],"with":[32,154],"number":[34],"variables.":[37],"Online":[38],"algorithms":[39],"tackle":[40],"this":[41,115],"problem":[42],"by":[43,159],"avoiding":[44],"computing":[45],"policy":[47],"entire":[50],"space.":[52],"On":[53],"other":[55],"hand,":[56],"since":[57],"online":[58,66,121,133,138],"algorithm":[59,123,169],"has":[60,207],"find":[62],"near-optimal":[64],"action":[65],"in":[67,132,150,170,193,215,229],"almost":[68],"real":[69],"time,":[70],"computation":[72,157],"time":[73,158],"often":[75],"very":[76,239],"limited.":[77],"In":[78,114],"context":[80],"reinforcement":[82],"learning,":[83],"MAXQ":[84,129,161],"value":[87],"function":[88],"decomposition":[89,131,163],"method":[90],"that":[91,127,206],"exploits":[92],"underlying":[94],"structure":[95],"original":[98],"and":[100,200,212],"decomposes":[101],"it":[102],"into":[103],"combination":[105],"smaller":[107],"subproblems":[108],"arranged":[109],"over":[110],"task":[112],"hierarchy.":[113],"article,":[116],"we":[117],"present":[118],"MAXQ-OP\u2014a":[119],"novel":[120],"MDPs":[126],"utilizes":[128],"hierarchical":[130,162],"settings.":[134],"Compared":[135],"traditional":[137],"algorithms,":[140],"MAXQ-OP":[141,237],"able":[143],"reach":[145],"much":[146],"more":[147],"deeper":[148],"states":[149],"search":[152],"tree":[153],"relatively":[155],"less":[156],"exploiting":[160],"online.":[164],"We":[165,185],"empirically":[166],"evaluate":[167],"our":[168,183],"standard":[172],"Taxi":[173],"domain\u2014a":[174],"common":[175],"benchmark":[176],"MDPs\u2014to":[178],"show":[179],"effectiveness":[181],"approach.":[184],"have":[186],"also":[187],"conducted":[188],"long-term":[190],"case":[191],"study":[192],"highly":[195],"complex":[196],"simulated":[197],"soccer":[198],"domain":[199,232],"developed":[201],"team":[203],"named":[204],"WrightEagle":[205],"won":[208],"five":[209,213],"world":[210],"champions":[211],"runners-up":[214],"recent":[217],"10":[218],"years":[219],"RoboCup":[221,231],"Soccer":[222],"Simulation":[223],"2D":[224],"annual":[225],"competitions.":[226],"The":[227],"results":[228],"confirm":[233],"scalability":[235],"domains.":[241]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}