{"id":"https://openalex.org/W3034400571","doi":"https://doi.org/10.24963/ijcai.2020/579","title":"DualSMC: Tunneling Differentiable Filtering and Planning under Continuous POMDPs","display_name":"DualSMC: Tunneling Differentiable Filtering and Planning under Continuous POMDPs","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3034400571","doi":"https://doi.org/10.24963/ijcai.2020/579","mag":"3034400571"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/579","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/579","pdf_url":"https://www.ijcai.org/proceedings/2020/0579.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":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0579.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100713554","display_name":"Yunbo Wang","orcid":"https://orcid.org/0000-0002-6215-8888"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbo Wang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461646","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-3603-6617"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bo Liu","raw_affiliation_strings":["The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015588857","display_name":"Jia-Jun Wu","orcid":"https://orcid.org/0000-0003-4583-7691"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiajun Wu","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030826237","display_name":"Yuke Zhu","orcid":"https://orcid.org/0000-0002-9198-2227"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuke Zhu","raw_affiliation_strings":["The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033061754","display_name":"Simon S. Du","orcid":"https://orcid.org/0000-0003-0056-8299"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon S. Du","raw_affiliation_strings":["Institute for Advanced Study"],"affiliations":[{"raw_affiliation_string":"Institute for Advanced Study","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450462","display_name":"Li Fei-Fei","orcid":"https://orcid.org/0000-0002-7481-0810"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Fei-Fei","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071093940","display_name":"Joshua B. Tenenbaum","orcid":"https://orcid.org/0000-0002-1925-2035"},"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":false,"raw_author_name":"Joshua B. Tenenbaum","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100461646"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.6797,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76426051,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4190","last_page":"4198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9991000294685364,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9991000294685364,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/computer-science","display_name":"Computer science","score":0.7188217043876648},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.6601206064224243},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6502220034599304},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.5911630392074585},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5297737121582031},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.471189022064209},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.44602903723716736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4448513984680176},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.4210107922554016},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.41804760694503784},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35494932532310486},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22977766394615173},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.17640376091003418},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.17566147446632385},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15993276238441467},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.11970844864845276}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7188217043876648},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.6601206064224243},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6502220034599304},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.5911630392074585},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5297737121582031},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.471189022064209},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44602903723716736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4448513984680176},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.4210107922554016},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.41804760694503784},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35494932532310486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22977766394615173},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.17640376091003418},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.17566147446632385},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15993276238441467},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.11970844864845276},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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},{"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:10.24963/ijcai.2020/579","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/579","pdf_url":"https://www.ijcai.org/proceedings/2020/0579.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"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/579","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/579","pdf_url":"https://www.ijcai.org/proceedings/2020/0579.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":[{"id":"https://metadata.un.org/sdg/11","score":0.7599999904632568,"display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G3543503879","display_name":null,"funder_award_id":"00014-16-1-2007","funder_id":"https://openalex.org/F4320333591","funder_display_name":"Multidisciplinary University Research Initiative"},{"id":"https://openalex.org/G4211722790","display_name":null,"funder_award_id":"N00014-16-1-2007","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5501761068","display_name":null,"funder_award_id":"4-16-1-","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7933538243","display_name":null,"funder_award_id":"MURI N00014-16-1-2007","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034400571.pdf","grobid_xml":"https://content.openalex.org/works/W3034400571.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1539216098","https://openalex.org/W1558657492","https://openalex.org/W1824523713","https://openalex.org/W2032100464","https://openalex.org/W2098284983","https://openalex.org/W2098613108","https://openalex.org/W2107464055","https://openalex.org/W2107662876","https://openalex.org/W2111787305","https://openalex.org/W2121092017","https://openalex.org/W2124595631","https://openalex.org/W2155772159","https://openalex.org/W2158782408","https://openalex.org/W2168359464","https://openalex.org/W2171084228","https://openalex.org/W2339179100","https://openalex.org/W2607713949","https://openalex.org/W2616889532","https://openalex.org/W2795496197","https://openalex.org/W2799151646","https://openalex.org/W2918645572","https://openalex.org/W2962854145","https://openalex.org/W2963371290","https://openalex.org/W4232554840","https://openalex.org/W4289294484","https://openalex.org/W4293568259","https://openalex.org/W4297573592","https://openalex.org/W4297733427","https://openalex.org/W4320013936","https://openalex.org/W4394652010","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W2123651102","https://openalex.org/W2953027552","https://openalex.org/W2287992105","https://openalex.org/W2117555338","https://openalex.org/W2392831491","https://openalex.org/W2570299561","https://openalex.org/W1512585804","https://openalex.org/W2130339357","https://openalex.org/W4285277090","https://openalex.org/W1526144783"],"abstract_inverted_index":{"A":[0],"major":[1],"difficulty":[2],"of":[3,13,62],"solving":[4],"continuous":[5,115,147],"POMDPs":[6,116],"is":[7,140],"to":[8,19,114,142],"infer":[9],"the":[10,14,21,26,47,51,54,60,71,85,94,105,150,154],"multi-modal":[11],"distribution":[12],"unobserved":[15],"true":[16],"states":[17,49],"and":[18,33,50,58,159],"make":[20],"planning":[22,34,101,108],"algorithm":[23,102],"dependent":[24],"on":[25,93],"perceived":[27],"uncertainty.":[28],"We":[29],"cast":[30],"POMDP":[31,148],"filtering":[32,95],"problems":[35],"as":[36,130],"two":[37,64],"closely":[38],"related":[39],"Sequential":[40],"Monte":[41],"Carlo":[42],"(SMC)":[43],"processes,":[44],"one":[45],"over":[46,53],"real":[48],"other":[52],"future":[55],"optimal":[56],"trajectories,":[57],"combine":[59],"merits":[61],"these":[63],"parts":[65],"in":[66,145],"a":[67,100,160],"new":[68],"model":[69],"named":[70],"DualSMC":[72,125],"network.":[73],"In":[74],"particular,":[75],"we":[76,97],"first":[77],"introduce":[78],"an":[79,118],"adversarial":[80,86],"particle":[81],"filter":[82],"that":[83,103],"leverages":[84],"relationship":[87],"between":[88],"its":[89],"internal":[90],"components.":[91],"Based":[92],"results,":[96],"then":[98],"propose":[99],"extends":[104],"previous":[106],"SMC":[107],"approach":[109],"[Piche":[110],"et":[111],"al.,":[112],"2018]":[113],"with":[117],"uncertainty-dependent":[119],"policy.":[120],"Crucially,":[121],"not":[122],"only":[123],"can":[124],"handle":[126],"complex":[127],"observations":[128],"such":[129],"image":[131],"input":[132],"but":[133],"also":[134],"it":[135],"remains":[136],"highly":[137],"interpretable.":[138],"It":[139],"shown":[141],"be":[143],"effective":[144],"three":[146],"domains:":[149],"floor":[151],"positioning":[152],"domain,":[153,158],"3D":[155],"light-dark":[156],"navigation":[157],"modified":[161],"Reacher":[162],"domain.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}