{"id":"https://openalex.org/W91039700","doi":null,"title":"Incremental methods for computing bounds in partially observable Markov decision processes","display_name":"Incremental methods for computing bounds in partially observable Markov decision processes","alternate_titles":[],"publication_year":1997,"publication_date":"1997-07-27","ids":{"openalex":"https://openalex.org/W91039700","mag":"91039700"},"language":"en","primary_location":{"id":"mag:91039700","doi":null,"is_oa":false,"landing_page_url":"http://cs.pitt.edu/~milos/research/AAAI-97.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},"parent_works":[],"lineage":["https://openalex.org/W91039700"],"child_works_count":0,"type":"conference-paper","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/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/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Milo\u0161 Hauskrecht","raw_affiliation_strings":["MIT, Laboratory for Computer Science, Cambridge, MA"],"raw_orcid":"https://orcid.org/0000-0002-7818-0633","affiliations":[{"raw_affiliation_string":"MIT, Laboratory for Computer Science, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5012461386"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":2.0495,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.85112108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"734","last_page":"739"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9814000129699707,"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":0.9814000129699707,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.00430000014603138,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.003100000089034438,"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/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.996999979019165},{"id":"https://openalex.org/keywords/value-function-bounds","display_name":"value function bounds","score":0.9319999814033508},{"id":"https://openalex.org/keywords/incremental-approach","display_name":"incremental method","score":0.6610000133514404},{"id":"https://openalex.org/keywords/lower-bounds","display_name":"lower bounds","score":0.8040000200271606},{"id":"https://openalex.org/keywords/upper-bounds","display_name":"upper bounds","score":0.8510000109672546},{"id":"https://openalex.org/keywords/belief-space","display_name":"belief space","score":0.8140000104904175},{"id":"https://openalex.org/keywords/dynamic-optimization","display_name":"dynamic optimization","score":0.4320000112056732}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.7399265170097351},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.7311590909957886},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.7283352613449097},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7252554297447205},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.6780809164047241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.606218695640564},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4751308262348175},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4627532958984375},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.46015551686286926},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4256798326969147},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35120153427124023},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.16952615976333618},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:91039700","doi":null,"is_oa":false,"landing_page_url":"http://cs.pitt.edu/~milos/research/AAAI-97.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},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.46.8853","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.46.8853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://wilma.cs.brown.edu/people/milos/././research/AAAI-97.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W131709709","https://openalex.org/W1483935885","https://openalex.org/W1527073666","https://openalex.org/W1538075516","https://openalex.org/W1558845053","https://openalex.org/W1964050508","https://openalex.org/W2011418219","https://openalex.org/W2034725503","https://openalex.org/W2149476049"],"related_works":["https://openalex.org/W2123365683","https://openalex.org/W2149476049","https://openalex.org/W1558845053","https://openalex.org/W7124252972","https://openalex.org/W1508297888","https://openalex.org/W1491973539","https://openalex.org/W2118538898","https://openalex.org/W2904996164","https://openalex.org/W2974424662","https://openalex.org/W1506128430"],"abstract_inverted_index":{"Partially":[0],"observable":[1],"Markov":[2],"decision":[3,12],"processes":[4],"(POMDPs)":[5],"allow":[6],"one":[7],"to":[8,138],"model":[9],"complex":[10],"dynamic":[11,32],"or":[13,41],"control":[14,26,65],"problems":[15,66],"that":[16],"include":[17,77],"both":[18],"action":[19],"outcome":[20],"uncertainty":[21],"and":[22,52,75,86,106,144],"imperfect":[23],"observability.":[24],"The":[25,72],"problem":[27,34],"is":[28,118,136],"formulated":[29],"as":[30],"a":[31,36,119],"optimization":[33],"with":[35,67,91,99],"value":[37,62],"function":[38,63],"combining":[39],"costs":[40],"rewards":[42],"from":[43],"multiple":[44],"steps.":[45],"In":[46],"this":[47],"paper":[48],"we":[49],"propose,":[50],"analyse":[51],"test":[53],"various":[54,111],"incremental":[55,79],"methods":[56,73],"for":[57,64,122],"computing":[58,123],"bounds":[59],"on":[60,141],"the":[61,103,129,142],"infinite":[68],"discounted":[69],"horizon":[70],"criteria.":[71],"described":[74],"tested":[76],"novel":[78],"versions":[80],"of":[81,95,102],"grid-based":[82],"linear":[83],"interpolation":[84],"method":[85,90,121,135],"simple":[87],"lower":[88],"bound":[89,127,132],"Sondik's":[92],"updates.":[93],"Both":[94],"these":[96],"can":[97,107],"work":[98],"arbitrary":[100],"points":[101],"belief":[104],"space":[105],"be":[108],"enhanced":[109],"by":[110],"heuristic":[112],"point":[113],"selection":[114],"strategies.":[115],"Also":[116],"introduced":[117],"new":[120],"an":[124],"initial":[125],"upper":[126,147],"--":[128],"fast":[130],"informed":[131],"method.":[133],"This":[134],"able":[137],"improve":[139],"significantly":[140],"standard":[143],"commonly":[145],"used":[146],"boun...":[148]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W91039700","counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":3}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2016-06-24T00:00:00"}
