{"id":"https://openalex.org/W4285605313","doi":"https://doi.org/10.24963/ijcai.2022/642","title":"Online Planning in POMDPs with Self-Improving Simulators","display_name":"Online Planning in POMDPs with Self-Improving Simulators","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285605313","doi":"https://doi.org/10.24963/ijcai.2022/642"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/642","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/642","pdf_url":"https://www.ijcai.org/proceedings/2022/0642.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0642.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086693782","display_name":"Jinke He","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Jinke He","raw_affiliation_strings":["Delft University of Technology","Delft University of Technology, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft University of Technology, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046313876","display_name":"Miguel Suau","orcid":"https://orcid.org/0000-0003-2607-8992"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Miguel Suau","raw_affiliation_strings":["Delft University of Technology","Delft University of Technology, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft University of Technology, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065056119","display_name":"Hendrik Baier","orcid":"https://orcid.org/0000-0002-7211-8070"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hendrik Baier","raw_affiliation_strings":["Centrum Wiskunde & Informatica","Centrum Wiskunde & Informatica, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centrum Wiskunde & Informatica","institution_ids":["https://openalex.org/I1341640284"]},{"raw_affiliation_string":"Centrum Wiskunde & Informatica, The Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069752991","display_name":"Michael Kaisers","orcid":null},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Michael Kaisers","raw_affiliation_strings":["Centrum Wiskunde & Informatica","Centrum Wiskunde & Informatica, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centrum Wiskunde & Informatica","institution_ids":["https://openalex.org/I1341640284"]},{"raw_affiliation_string":"Centrum Wiskunde & Informatica, The Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009493909","display_name":"Frans A. Oliehoek","orcid":"https://orcid.org/0000-0003-4372-5055"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Frans A. Oliehoek","raw_affiliation_strings":["Delft University of Technology","Delft University of Technology, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft University of Technology, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5086693782"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05495495,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4628","last_page":"4634"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9980999827384949,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9980999827384949,"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":0.9923999905586243,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9908999800682068,"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/computer-science","display_name":"Computer science","score":0.813147783279419},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.6536325216293335},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.6414620876312256},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.624351441860199},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5851610898971558},{"id":"https://openalex.org/keywords/computer-architecture-simulator","display_name":"Computer architecture simulator","score":0.5096840858459473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.813147783279419},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.6536325216293335},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.6414620876312256},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.624351441860199},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5851610898971558},{"id":"https://openalex.org/C201203610","wikidata":"https://www.wikidata.org/wiki/Q5157524","display_name":"Computer architecture simulator","level":2,"score":0.5096840858459473},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.24963/ijcai.2022/642","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/642","pdf_url":"https://www.ijcai.org/proceedings/2022/0642.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:cwi:oai:cwi.nl:32140","is_oa":false,"landing_page_url":"https://ir.cwi.nl/pub/32140","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencepaper"},{"id":"pmh:oai:tudelft.nl:uuid:b61ca225-4d8f-4597-bb4b-0f31c056dcc5","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:b61ca225-4d8f-4597-bb4b-0f31c056dcc5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/642","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/642","pdf_url":"https://www.ijcai.org/proceedings/2022/0642.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6100000143051147}],"awards":[{"id":"https://openalex.org/G1073366937","display_name":"Influence-based Decision-making in Uncertain Environments","funder_award_id":"758824","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285605313.pdf","grobid_xml":"https://content.openalex.org/works/W4285605313.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W52153049","https://openalex.org/W159191692","https://openalex.org/W1977046327","https://openalex.org/W1991142852","https://openalex.org/W2026709279","https://openalex.org/W2061504687","https://openalex.org/W2114771311","https://openalex.org/W2124595631","https://openalex.org/W2126316555","https://openalex.org/W2157331557","https://openalex.org/W2168359464","https://openalex.org/W2171084228","https://openalex.org/W2296576527","https://openalex.org/W2338031201","https://openalex.org/W2396836028","https://openalex.org/W2401854627","https://openalex.org/W2522635871","https://openalex.org/W2523246573","https://openalex.org/W2572919868","https://openalex.org/W2811395263","https://openalex.org/W2963725394","https://openalex.org/W2975734572","https://openalex.org/W3043919888","https://openalex.org/W3093816090","https://openalex.org/W3095363295","https://openalex.org/W3134924952","https://openalex.org/W4294560979","https://openalex.org/W6863994431"],"related_works":["https://openalex.org/W2075301230","https://openalex.org/W2379498836","https://openalex.org/W4255183762","https://openalex.org/W2096372802","https://openalex.org/W2067685039","https://openalex.org/W33416868","https://openalex.org/W2271219225","https://openalex.org/W2403379859","https://openalex.org/W2511534263","https://openalex.org/W29863057"],"abstract_inverted_index":{"How":[0],"can":[1],"we":[2,30,56],"plan":[3,46,130],"efficiently":[4,49],"in":[5,116],"a":[6,58,72],"large":[7,118],"and":[8,48,112],"complex":[9],"environment":[10],"when":[11,98,122],"the":[12,18,22,51,76,79,87,92,104],"time":[13],"budget":[14],"is":[15,54,100],"limited?":[16],"Given":[17],"original":[19,93],"simulator":[20,40,53,64,89,94],"of":[21,78],"environment,":[23],"which":[24,63],"may":[25],"be":[26],"computationally":[27],"very":[28],"demanding,":[29],"propose":[31],"to":[32,65,85,90,129],"learn":[33],"online":[34],"an":[35],"approximate":[36,52,80,88],"but":[37],"much":[38],"faster":[39,96],"that":[41,60,74,121],"improves":[42],"over":[43,134],"time.":[44,135],"To":[45],"reliably":[47],"while":[50],"learning,":[55],"develop":[57],"method":[59],"adaptively":[61],"decides":[62],"use":[66,86],"for":[67,95],"every":[68],"simulation,":[69],"based":[70],"on":[71],"statistic":[73],"measures":[75],"accuracy":[77],"simulator.":[81],"This":[82],"allows":[83,128],"us":[84],"replace":[91],"simulations":[97],"it":[99],"accurate":[101],"enough":[102],"under":[103],"current":[105],"context,":[106],"thus":[107],"trading":[108],"off":[109],"simulation":[110],"speed":[111],"accuracy.":[113],"Experimental":[114],"results":[115],"two":[117],"domains":[119],"show":[120],"integrated":[123],"with":[124,131],"POMCP,":[125],"our":[126],"approach":[127],"improving":[132],"efficiency":[133]},"counts_by_year":[],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2025-10-10T00:00:00"}