{"id":"https://openalex.org/W2808100232","doi":"https://doi.org/10.24963/ijcai.2018/662","title":"Goal-HSVI: Heuristic Search Value Iteration for Goal POMDPs","display_name":"Goal-HSVI: Heuristic Search Value Iteration for Goal POMDPs","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2808100232","doi":"https://doi.org/10.24963/ijcai.2018/662","mag":"2808100232"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/662","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/662","pdf_url":"https://www.ijcai.org/proceedings/2018/0662.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0662.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103017905","display_name":"Karel Hor\u00e1k","orcid":"https://orcid.org/0000-0003-0307-6281"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Karel Hor\u00e1k","raw_affiliation_strings":["Department of Computer Science, FEE, Czech Technical University in Prague"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, FEE, Czech Technical University in Prague","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052350897","display_name":"Branislav Bo\u0161ansk\u00fd","orcid":"https://orcid.org/0000-0002-3841-9515"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Branislav Bo\u0161ansk\u00fd","raw_affiliation_strings":["Department of Computer Science, FEE, Czech Technical University in Prague"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, FEE, Czech Technical University in Prague","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052607806","display_name":"Krishnendu Chatterjee","orcid":"https://orcid.org/0000-0002-4561-241X"},"institutions":[{"id":"https://openalex.org/I157556583","display_name":"Institute of Science and Technology Austria","ror":"https://ror.org/03gnh5541","country_code":"AT","type":"education","lineage":["https://openalex.org/I157556583"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Krishnendu Chatterjee","raw_affiliation_strings":["IST Austria, Klosterneuburg, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IST Austria, Klosterneuburg, Austria","institution_ids":["https://openalex.org/I157556583"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4764","last_page":"4770"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10142","display_name":"Formal Methods in Verification","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9894000291824341,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.726012647151947},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6639388203620911},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6341515779495239},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6256369352340698},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6130322813987732},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5714884400367737},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5270286202430725},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.5188159346580505},{"id":"https://openalex.org/keywords/aka","display_name":"AKA","score":0.49092963337898254},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.28859907388687134},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2167031168937683}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.726012647151947},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6639388203620911},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6341515779495239},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6256369352340698},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6130322813987732},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5714884400367737},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5270286202430725},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.5188159346580505},{"id":"https://openalex.org/C121158502","wikidata":"https://www.wikidata.org/wiki/Q4652161","display_name":"AKA","level":2,"score":0.49092963337898254},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.28859907388687134},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2167031168937683},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2018/662","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/662","pdf_url":"https://www.ijcai.org/proceedings/2018/0662.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/662","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/662","pdf_url":"https://www.ijcai.org/proceedings/2018/0662.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2043895709","display_name":null,"funder_award_id":"W911NF-13-2-0045","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G2554063606","display_name":"Efficient Algorithms for Computer Aided Verification","funder_award_id":"ICT15-003","funder_id":"https://openalex.org/F4320321003","funder_display_name":"Vienna Science and Technology Fund"},{"id":"https://openalex.org/G2655136877","display_name":null,"funder_award_id":"S11407","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G3732666562","display_name":null,"funder_award_id":"W911NF-13","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G4360933436","display_name":null,"funder_award_id":"Project ICT15-003","funder_id":"https://openalex.org/F4320321003","funder_display_name":"Vienna Science and Technology Fund"},{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G683671635","display_name":null,"funder_award_id":"S11407-N23","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G8763038417","display_name":null,"funder_award_id":"Cooperative Agreement Number W911NF-13-2-0045","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320321003","display_name":"Vienna Science and Technology Fund","ror":"https://ror.org/01f9mc681"},{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2808100232.pdf","grobid_xml":"https://content.openalex.org/works/W2808100232.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W15573929","https://openalex.org/W135762054","https://openalex.org/W288011047","https://openalex.org/W656816899","https://openalex.org/W1496590343","https://openalex.org/W1515891729","https://openalex.org/W1539216098","https://openalex.org/W1839854015","https://openalex.org/W2009533501","https://openalex.org/W2009570821","https://openalex.org/W2032100464","https://openalex.org/W2098432798","https://openalex.org/W2099430963","https://openalex.org/W2107726111","https://openalex.org/W2125529971","https://openalex.org/W2134802714","https://openalex.org/W2151958719","https://openalex.org/W2165464423","https://openalex.org/W2169294731","https://openalex.org/W2287282975","https://openalex.org/W2321292752","https://openalex.org/W2405532007","https://openalex.org/W2545350044","https://openalex.org/W2963889160","https://openalex.org/W4234727937","https://openalex.org/W4255985591","https://openalex.org/W4300395467","https://openalex.org/W4307347247"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1515117609","https://openalex.org/W1589140671","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W3169161914","https://openalex.org/W4321379664","https://openalex.org/W2211790881"],"abstract_inverted_index":{"Partially":[0],"observable":[1],"Markov":[2],"decision":[3],"processes":[4],"(POMDPs)":[5],"are":[6],"the":[7,21,51,57,68,102,108,118],"standard":[8],"models":[9],"for":[10,33,48,80],"planning":[11],"under":[12],"uncertainty":[13],"with":[14],"both":[15],"finite":[16],"and":[17,44,91,113,134],"infinite":[18],"horizon.":[19],"Besides":[20],"well-known":[22,153],"discounted-sum":[23],"objective,":[24],"indefinite-horizon":[25],"objective":[26,32,53],"(aka":[27],"Goal-POMDPs)":[28],"is":[29,54,65],"another":[30],"classical":[31],"POMDPs.":[34],"In":[35,67],"this":[36],"case,":[37],"given":[38],"a":[39,45,62,126,150],"set":[40,151],"of":[41,84,152],"target":[42,63],"states":[43],"positive":[46],"cost":[47,60],"each":[49],"transition,":[50],"optimization":[52],"to":[55,96],"minimize":[56],"expected":[58],"total":[59],"until":[61],"state":[64],"reached.":[66],"literature,":[69],"RTDP-Bel":[70,148],"or":[71],"heuristic":[72],"search":[73],"value":[74],"iteration":[75],"(HSVI)":[76],"have":[77],"been":[78],"used":[79],"solving":[81],"Goal-POMDPs.":[82],"Neither":[83],"these":[85],"algorithms":[86],"has":[87,139],"theoretical":[88],"convergence":[89,140],"guarantees,":[90],"HSVI":[92,120],"may":[93],"even":[94],"fail":[95],"terminate":[97],"its":[98],"trials.":[99],"We":[100,106,124,143],"give":[101],"following":[103],"contributions:":[104],"(1)":[105],"discuss":[107],"challenges":[109],"introduced":[110],"in":[111],"Goal-POMDPs":[112],"illustrate":[114],"how":[115],"they":[116],"prevent":[117],"original":[119],"from":[121],"converging.":[122],"(2)":[123],"present":[125],"novel":[127],"algorithm":[128,138],"inspired":[129],"by":[130],"HSVI,":[131],"termed":[132],"Goal-HSVI,":[133],"show":[135,144],"that":[136,145],"our":[137],"guarantees.":[141],"(3)":[142],"Goal-HSVI":[146],"outperforms":[147],"on":[149],"examples.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
