{"id":"https://openalex.org/W2904410128","doi":"https://doi.org/10.1609/aaai.v33i01.33017941","title":"Memory Bounded Open-Loop Planning in Large POMDPs Using Thompson Sampling","display_name":"Memory Bounded Open-Loop Planning in Large POMDPs Using Thompson Sampling","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2904410128","doi":"https://doi.org/10.1609/aaai.v33i01.33017941","mag":"2904410128"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33017941","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33017941","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4794/4672","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4794/4672","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024645861","display_name":"Thomy Phan","orcid":"https://orcid.org/0000-0002-4390-8954"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Thomy Phan","raw_affiliation_strings":["Ludwig Maximilian University of Munich"],"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068564686","display_name":"Lenz Belzner","orcid":"https://orcid.org/0009-0002-4683-5460"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lenz Belzner","raw_affiliation_strings":["MaibornWolff"],"affiliations":[{"raw_affiliation_string":"MaibornWolff","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049582113","display_name":"Marie Kiermeier","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marie Kiermeier","raw_affiliation_strings":["Ludwig Maximilian University of Munich"],"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062492780","display_name":"Markus Friedrich","orcid":"https://orcid.org/0000-0001-5719-3198"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Markus Friedrich","raw_affiliation_strings":["Ludwig Maximilian University of Munich"],"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061867637","display_name":"Kyrill Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kyrill Schmid","raw_affiliation_strings":["Ludwig Maximilian University of Munich"],"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064469861","display_name":"Claudia Linnhoff\u2010Popien","orcid":"https://orcid.org/0000-0001-6284-9286"},"institutions":[{"id":"https://openalex.org/I2800496153","display_name":"Global Viral","ror":"https://ror.org/04b3f3k27","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2800496153"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Claudia Linnhoff-Popien","raw_affiliation_strings":["Virality GmbH"],"affiliations":[{"raw_affiliation_string":"Virality GmbH","institution_ids":["https://openalex.org/I2800496153"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5024645861"],"corresponding_institution_ids":["https://openalex.org/I8204097"],"apc_list":null,"apc_paid":null,"fwci":0.3936,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65638389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"33","issue":"01","first_page":"7941","last_page":"7948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9993000030517578,"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":0.9993000030517578,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9937000274658203,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8125987648963928},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7503091096878052},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.7495657205581665},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.6612221002578735},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6445128917694092},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6115235686302185},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.5221555233001709},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4340510368347168},{"id":"https://openalex.org/keywords/stack","display_name":"Stack (abstract data type)","score":0.4103911817073822},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15356937050819397}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8125987648963928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7503091096878052},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.7495657205581665},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6612221002578735},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6445128917694092},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6115235686302185},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5221555233001709},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4340510368347168},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.4103911817073822},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15356937050819397},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v33i01.33017941","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33017941","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4794/4672","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33017941","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33017941","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4794/4672","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2904410128.pdf","grobid_xml":"https://content.openalex.org/works/W2904410128.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W130797843","https://openalex.org/W1625390266","https://openalex.org/W1704036460","https://openalex.org/W2025400977","https://openalex.org/W2039522160","https://openalex.org/W2108738385","https://openalex.org/W2110962519","https://openalex.org/W2124595631","https://openalex.org/W2134802714","https://openalex.org/W2141645258","https://openalex.org/W2144913588","https://openalex.org/W2158319693","https://openalex.org/W2164102968","https://openalex.org/W2168359464","https://openalex.org/W2169511307","https://openalex.org/W2171084228","https://openalex.org/W2197494948","https://openalex.org/W2257979135","https://openalex.org/W2757144228","https://openalex.org/W2766447205","https://openalex.org/W2797082086","https://openalex.org/W2798304540","https://openalex.org/W2952446394","https://openalex.org/W2955744109","https://openalex.org/W2962896606","https://openalex.org/W4234228486","https://openalex.org/W4289766000","https://openalex.org/W6636578284","https://openalex.org/W6676077707","https://openalex.org/W6678541622","https://openalex.org/W6679977494","https://openalex.org/W6681571045","https://openalex.org/W6684679486","https://openalex.org/W6684973485","https://openalex.org/W6734786676","https://openalex.org/W6744117469","https://openalex.org/W7075680496"],"related_works":["https://openalex.org/W1994680671","https://openalex.org/W2378211422","https://openalex.org/W2002320543","https://openalex.org/W2000283393","https://openalex.org/W3106170641","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W2150232912","https://openalex.org/W2086519370"],"abstract_inverted_index":{"State-of-the-art":[0],"approaches":[1,16],"to":[2,35,54,95],"partially":[3,108],"observable":[4,109],"planning":[5,56,98,110],"like":[6],"POMCP":[7],"are":[8,17],"based":[9],"on":[10],"stochastic":[11],"tree":[12],"search.":[13],"While":[14],"these":[15],"computationally":[18],"efficient,":[19],"they":[20],"may":[21],"still":[22],"construct":[23],"search":[24],"trees":[25],"of":[26,66],"considerable":[27],"size,":[28],"which":[29,60],"could":[30],"limit":[31],"the":[32],"performance":[33,82,93],"due":[34],"restricted":[36,113],"memory":[37,51,116],"resources.":[38,117],"In":[39],"this":[40],"paper,":[41],"we":[42],"propose":[43],"Partially":[44],"Observable":[45],"Stacked":[46],"Thompson":[47,67],"Sampling":[48,68],"(POSTS),":[49],"a":[50,62,101],"bounded":[52],"approach":[53],"openloop":[55],"in":[57,74],"large":[58,76],"POMDPs,":[59],"optimizes":[61],"fixed":[63],"size":[64],"stack":[65],"bandits.":[69],"We":[70,87],"empirically":[71],"evaluate":[72],"POSTS":[73,90],"four":[75],"benchmark":[77],"problems":[78],"and":[79,99,115],"compare":[80],"its":[81],"with":[83,111],"different":[84],"tree-based":[85,96],"approaches.":[86],"show":[88],"that":[89],"achieves":[91],"competitive":[92],"compared":[94],"open-loop":[97],"offers":[100],"performancememory":[102],"tradeoff,":[103],"making":[104],"it":[105],"suitable":[106],"for":[107],"highly":[112],"computational":[114]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}