{"id":"https://openalex.org/W2132096648","doi":null,"title":"Max-norm Projections for Factored MDPs","display_name":"Max-norm Projections for Factored MDPs","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2132096648","mag":"2132096648"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.10.7912","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.7912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://robotics.stanford.edu/~koller/papers/ijcai01gkp.ps","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/A5090739892","display_name":"Carlos Guestrin","orcid":"https://orcid.org/0000-0001-6348-5939","observed_orcids":["https://orcid.org/0000-0001-6348-5939"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Guestrin","raw_affiliation_strings":["Computer Science Dept., Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept., Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051658526","display_name":"Daphne Koller","orcid":"https://orcid.org/0000-0002-2361-6479","observed_orcids":["https://orcid.org/0000-0002-2361-6479","https://orcid.org/0009-0007-1645-951X"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daphne Koller","raw_affiliation_strings":["Computer Science Dept., Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept., Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109839104","display_name":"Ronald Parr","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ronald Parr","raw_affiliation_strings":["Computer Science Dept., Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept., Duke University","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.2928,"has_fulltext":false,"cited_by_count":105,"citation_normalized_percentile":{"value":0.98253518,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"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":0.8931000232696533,"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":0.8931000232696533,"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":0.050700001418590546,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.010599999688565731,"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/markov-decision-process","display_name":"Markov decision process","score":0.8899999856948853},{"id":"https://openalex.org/keywords/factored-mdps","display_name":"factored MDPs","score":0.9789999723434448},{"id":"https://openalex.org/keywords/planning-under-uncertainty","display_name":"planning under uncertainty","score":0.777999997138977}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7601810693740845},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.7056035995483398},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6571087837219238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5919925570487976},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.5591409802436829},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.47969552874565125},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.47942274808883667},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.4371945261955261},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.37535491585731506},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37407588958740234},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31711041927337646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10100361704826355},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.10.7912","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.7912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://robotics.stanford.edu/~koller/papers/ijcai01gkp.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.160.1985","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.160.1985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://select.cs.cmu.edu/publications/paperdir/ijcai2001-guestrin-koller-parr.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.24.4163","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.24.4163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://robotics.stanford.edu/~guestrin/Publications/AAAISpringSymposium2001/aaai-spring-2001.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.28.3552","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.28.3552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://robotics.stanford.edu/~guestrin/Publications/IJCAI2001/ijcai2001.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.329.5607","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.329.5607","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/Symposia/Spring/2001/SS-01-03/SS01-03-004.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1502893368","https://openalex.org/W1588316674","https://openalex.org/W1590986876","https://openalex.org/W1982333717","https://openalex.org/W1997696513","https://openalex.org/W2020294948","https://openalex.org/W2033697467","https://openalex.org/W2061504687","https://openalex.org/W2091579301","https://openalex.org/W2119567691","https://openalex.org/W2122410182","https://openalex.org/W2169982856","https://openalex.org/W2231883621","https://openalex.org/W2320420931","https://openalex.org/W2798987218"],"related_works":["https://openalex.org/W3004360271","https://openalex.org/W7095497806","https://openalex.org/W7096844209","https://openalex.org/W4393941660","https://openalex.org/W2148501150","https://openalex.org/W28736093","https://openalex.org/W2110338773","https://openalex.org/W2149385746","https://openalex.org/W2123557770","https://openalex.org/W7095334428"],"abstract_inverted_index":{"Markov":[0],"Decision":[1],"Processes":[2],"(MDPs)":[3],"provide":[4,73],"a":[5,22,27,43,66,74,171],"coherent":[6],"mathematical":[7],"framework":[8],"for":[9,29,41,105],"planning":[10],"under":[11],"uncertainty.":[12],"However,":[13],"exact":[14,52],"MDP":[15,53,106,124],"solution":[16,57,125],"algorithms":[17,58,85,153],"require":[18],"the":[19,33,49,78,91,99,121,139,144,159,165],"manipulation":[20],"of":[21,51,63,69,83,101,109,161],"value":[23,28,79,128],"function,":[24],"which":[25,64,110],"specifies":[26],"each":[30],"state":[31],"in":[32,158,182],"system.":[34],"Most":[35],"real-world":[36],"MDPs":[37],"are":[38],"too":[39],"large":[40],"such":[42],"representation":[44],"to":[45,72,77,142],"be":[46,155,178],"feasible,":[47],"preventing":[48],"use":[50,65,86,111,133],"algorithms.":[54],"Various":[55],"approximate":[56,123],"have":[59],"been":[60],"proposed,":[61],"many":[62],"linear":[67],"combination":[68],"basis":[70],"functions":[71],"compact":[75],"approximation":[76,88],"function.":[80],"Almost":[81],"all":[82,108],"these":[84,152],"an":[87],"based":[89],"on":[90],"(weighted)":[92],"Z~2norm":[93],"(Euclidean":[94],"distance);":[95],"this":[96],"approach":[97],"prevents":[98],"application":[100],"standard":[102],"convergence":[103],"results":[104],"algorithms,":[107],"max-norm.":[112],"This":[113],"paper":[114],"makes":[115],"two":[116],"contributions.":[117],"First,":[118],"it":[119,149],"presents":[120],"first":[122],"algorithms--":[126],"both":[127],"and":[129,175],"policy":[130],"iteration--":[131],"that":[132],"max-norm":[134],"projection,":[135],"thereby":[136],"directly":[137],"optimizing":[138],"quantity":[140],"required":[141],"obtain":[143],"best":[145],"error":[146],"bounds.":[147],"Second,":[148],"shows":[150],"how":[151],"can":[154],"applied":[156],"efficiently":[157],"context":[160],"factored":[162],"MDPs,":[163],"where":[164],"transition":[166],"model":[167],"is":[168],"specified":[169],"using":[170],"dynamic":[172],"Bayesian":[173],"network":[174],"actions":[176],"may":[177],"taken":[179],"sequentially":[180],"or":[181],"parallel.":[183]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":9}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}