{"id":"https://openalex.org/W2979680416","doi":"https://doi.org/10.24963/ijcai.2020/572","title":"Sparse Tree Search Optimality Guarantees in POMDPs with Continuous Observation Spaces","display_name":"Sparse Tree Search Optimality Guarantees in POMDPs with Continuous Observation Spaces","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W2979680416","doi":"https://doi.org/10.24963/ijcai.2020/572","mag":"2979680416"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/572","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/572","pdf_url":"https://www.ijcai.org/proceedings/2020/0572.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0572.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Michael H. Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael H. Lim","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Claire Tomlin","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Claire Tomlin","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zachary N. Sunberg","orcid":null},"institutions":[{"id":"https://openalex.org/I2802236040","display_name":"University of Colorado System","ror":"https://ror.org/00jc20583","country_code":"US","type":"education","lineage":["https://openalex.org/I2802236040"]},{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary N. Sunberg","raw_affiliation_strings":["University of Colorado Boulder"],"affiliations":[{"raw_affiliation_string":"University of Colorado Boulder","institution_ids":["https://openalex.org/I2802236040","https://openalex.org/I188538660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.6796,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75622831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4135","last_page":"4142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9936000108718872,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9897000193595886,"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/flexibility","display_name":"Flexibility (engineering)","score":0.6473000049591064},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.6327999830245972},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5849000215530396},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5651999711990356},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5414000153541565},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4982999861240387},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4560000002384186},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.42640000581741333},{"id":"https://openalex.org/keywords/decision-theory","display_name":"Decision theory","score":0.4154999852180481}],"concepts":[{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6473000049591064},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6327999830245972},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5849000215530396},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5651999711990356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5648999810218811},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5532000064849854},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5414000153541565},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4982999861240387},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4627000093460083},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4560000002384186},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4318999946117401},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.40939998626708984},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3434999883174896},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C70136482","wikidata":"https://www.wikidata.org/wiki/Q13583781","display_name":"A-weighting","level":3,"score":0.3206000030040741},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29840001463890076},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.265500009059906},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2020/572","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/572","pdf_url":"https://www.ijcai.org/proceedings/2020/0572.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.04332","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.04332","pdf_url":"https://arxiv.org/pdf/1910.04332","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/572","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/572","pdf_url":"https://www.ijcai.org/proceedings/2020/0572.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2966665750","display_name":null,"funder_award_id":"1752814","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4759983887","display_name":null,"funder_award_id":"Grant No. DGE 1752814","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5274169913","display_name":null,"funder_award_id":"DGE 1752814","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7263137601","display_name":null,"funder_award_id":"DGE 175281","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2979680416.pdf","grobid_xml":"https://content.openalex.org/works/W2979680416.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1491973539","https://openalex.org/W1556274146","https://openalex.org/W1565394148","https://openalex.org/W1605929701","https://openalex.org/W1975244201","https://openalex.org/W1984533547","https://openalex.org/W2025217226","https://openalex.org/W2032100464","https://openalex.org/W2098432798","https://openalex.org/W2124595631","https://openalex.org/W2168165432","https://openalex.org/W2168359464","https://openalex.org/W2339179100","https://openalex.org/W2529804031","https://openalex.org/W2545546008","https://openalex.org/W2594201198","https://openalex.org/W2607868186","https://openalex.org/W2795496197","https://openalex.org/W2890597452","https://openalex.org/W3023151133","https://openalex.org/W4243421009"],"related_works":[],"abstract_inverted_index":{"Partially":[0],"observable":[1,70],"Markov":[2],"decision":[3,18],"processes":[4],"(POMDPs)":[5],"with":[6,43,79],"continuous":[7,44],"state":[8],"and":[9,19,82],"observation":[10,34,45],"spaces":[11],"have":[12,37],"powerful":[13],"flexibility":[14],"for":[15,55],"representing":[16],"real-world":[17],"control":[20],"problems":[21],"but":[22],"are":[23],"notoriously":[24],"difficult":[25],"to":[26,86],"solve.":[27],"Recent":[28],"online":[29],"sampling-based":[30],"algorithms":[31],"that":[32,65],"use":[33],"likelihood":[35],"weighting":[36],"shown":[38],"unprecedented":[39],"effectiveness":[40],"in":[41],"domains":[42],"spaces.":[46],"However":[47],"there":[48],"has":[49],"been":[50],"no":[51],"formal":[52],"theoretical":[53],"justification":[54],"this":[56],"technique.":[57],"This":[58],"work":[59],"offers":[60],"such":[61],"a":[62,66],"justification,":[63],"proving":[64],"simplified":[67],"algorithm,":[68],"partially":[69],"weighted":[71],"sparse":[72],"sampling":[73],"(POWSS),":[74],"will":[75],"estimate":[76],"Q-values":[77],"accurately":[78],"high":[80],"probability":[81],"can":[83],"be":[84],"made":[85],"perform":[87],"arbitrarily":[88],"near":[89],"the":[90],"optimal":[91],"solution":[92],"by":[93],"increasing":[94],"computational":[95],"power.":[96]},"counts_by_year":[{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2019-10-18T00:00:00"}