{"id":"https://openalex.org/W189342872","doi":null,"title":"Solving factored MDPs with exponential-family transition models","display_name":"Solving factored MDPs with exponential-family transition models","publication_year":2006,"publication_date":"2006-06-06","ids":{"openalex":"https://openalex.org/W189342872","mag":"189342872"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.322.7066","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.322.7066","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/ICAPS/2006/ICAPS06-012.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/A5049020775","display_name":"Branislav Kveton","orcid":"https://orcid.org/0000-0002-3965-1367","observed_orcids":["https://orcid.org/0000-0002-3965-1367"]},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Branislav Kveton","raw_affiliation_strings":["[Intelligent Systems Program - University of Pittsburgh]"],"raw_orcid":"https://orcid.org/0000-0002-3965-1367","affiliations":[{"raw_affiliation_string":"[Intelligent Systems Program - University of Pittsburgh]","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012461386","display_name":"Milo\u0161 Hauskrecht","orcid":"https://orcid.org/0000-0002-7818-0633","observed_orcids":["https://orcid.org/0000-0002-7818-0633"]},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milo\u0161 Hauskrecht","raw_affiliation_strings":["Department of Computer Science, University of Pittsburgh,"],"raw_orcid":"https://orcid.org/0000-0002-7818-0633","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Pittsburgh,","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":2.1213,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.87123881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"114","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9887999892234802,"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":0.9887999892234802,"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":0.002099999925121665,"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":0.0020000000949949026,"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":0.9269999861717224},{"id":"https://openalex.org/keywords/factored-mdps","display_name":"factored MDPs","score":0.9229999780654907},{"id":"https://openalex.org/keywords/basis-functions","display_name":"basis functions","score":0.6579999923706055},{"id":"https://openalex.org/keywords/continuous-state-action-spaces","display_name":"continuous state and action spaces","score":0.7979999780654907}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6234572529792786},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6141777634620667},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6138728857040405},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5422045588493347},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.5343213677406311},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.5296179056167603},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4546040892601013},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4423045516014099},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4335181713104248},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3596726953983307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3413122892379761},{"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.322.7066","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.322.7066","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/ICAPS/2006/ICAPS06-012.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.60.2827","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.2827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.pitt.edu/~bkveton/docs/icaps2006.pdf","raw_type":"text"},{"id":"mag:189342872","doi":null,"is_oa":false,"landing_page_url":"https://people.cs.pitt.edu/~milos/research/icaps2006.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419157","display_name":"International Conference on Automated Planning and Scheduling","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":"International Conference on Automated Planning and Scheduling","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":26,"referenced_works":["https://openalex.org/W51537834","https://openalex.org/W102626069","https://openalex.org/W1540935623","https://openalex.org/W1552830313","https://openalex.org/W1563483395","https://openalex.org/W1576452626","https://openalex.org/W1586365389","https://openalex.org/W1588316674","https://openalex.org/W1589991875","https://openalex.org/W1650504995","https://openalex.org/W1745373831","https://openalex.org/W1997696513","https://openalex.org/W2020294948","https://openalex.org/W2040766536","https://openalex.org/W2064203730","https://openalex.org/W2119567691","https://openalex.org/W2129570755","https://openalex.org/W2132096648","https://openalex.org/W2133429202","https://openalex.org/W2135194391","https://openalex.org/W2138429419","https://openalex.org/W2146290970","https://openalex.org/W2149385746","https://openalex.org/W2158479468","https://openalex.org/W2169997910","https://openalex.org/W2341171179"],"related_works":["https://openalex.org/W75459635","https://openalex.org/W2165304603","https://openalex.org/W132471711","https://openalex.org/W1555502177","https://openalex.org/W51537834","https://openalex.org/W7096559591","https://openalex.org/W7100748510","https://openalex.org/W2138429419","https://openalex.org/W7099026408","https://openalex.org/W28736093"],"abstract_inverted_index":{"Markov":[0],"decision":[1],"processes":[2],"(MDPs)":[3],"with":[4],"discrete":[5],"and":[6,9,42,77,119],"continuous":[7,117],"state":[8],"action":[10],"components":[11],"can":[12],"be":[13],"solved":[14],"efficiently":[15],"by":[16,35,45],"hybrid":[17],"approximate":[18,30],"linear":[19,37,46],"programming":[20],"(HALP).":[21],"The":[22],"main":[23],"idea":[24],"of":[25,39,60,70,99],"the":[26,31,53,58,89,106],"approach":[27],"is":[28],"to":[29,88],"optimal":[32],"value":[33],"function":[34],"a":[36,65,96,111],"combination":[38],"basis":[40,101],"functions":[41],"optimize":[43],"it":[44],"programming.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,67,94,104],"extend":[52],"existing":[54],"HALP":[55,108],"paradigm":[56],"beyond":[57],"mixture":[59],"beta":[61],"transition":[62,72],"model.":[63],"As":[64],"result,":[66],"permit":[68],"modeling":[69],"other":[71],"functions,":[73],"such":[74],"as":[75],"normal":[76],"gamma":[78],"densities,":[79],"without":[80],"approximating":[81],"them.":[82],"To":[83],"allow":[84],"for":[85],"efficient":[86],"solutions":[87],"expectation":[90],"terms":[91],"in":[92],"HALP,":[93],"identify":[95],"rich":[97],"class":[98],"conjugate":[100],"functions.":[102],"Finally,":[103],"demonstrate":[105],"generalized":[107],"framework":[109],"on":[110],"rover":[112],"planning":[113],"problem,":[114],"which":[115],"exhibits":[116],"time":[118],"resource":[120],"uncertainty.":[121]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2016-06-24T00:00:00"}