{"id":"https://openalex.org/W2807557496","doi":"https://doi.org/10.24963/ijcai.2019/362","title":"Assumed Density Filtering Q-learning","display_name":"Assumed Density Filtering Q-learning","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2807557496","doi":"https://doi.org/10.24963/ijcai.2019/362","mag":"2807557496"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/362","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/362","pdf_url":"https://www.ijcai.org/proceedings/2019/0362.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0362.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068209902","display_name":"Heejin Jeong","orcid":"https://orcid.org/0000-0002-0122-532X"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heejin Jeong","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA","University of Pennsylvania, Philadelphia, PA 19104"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA 19104","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086323648","display_name":"Clark Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clark Zhang","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA","University of Pennsylvania, Philadelphia, PA 19104"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA 19104","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029243115","display_name":"George J. Pappas","orcid":"https://orcid.org/0000-0001-9081-0637"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George J. Pappas","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA","University of Pennsylvania, Philadelphia, PA 19104"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA 19104","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007905483","display_name":"Daniel D. Lee","orcid":"https://orcid.org/0000-0002-2163-2686"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4405261073","display_name":"Cornell Tech","ror":"https://ror.org/04qscbg47","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel D. Lee","raw_affiliation_strings":["Cornell Tech, New York, NY","Cornell Tech, New York, NY 10044"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell Tech, New York, NY","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]},{"raw_affiliation_string":"Cornell Tech, New York, NY 10044","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.656,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.73620195,"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":"2607","last_page":"2613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9904000163078308,"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"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9858999848365784,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6856522560119629},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6595567464828491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6547940373420715},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5518364906311035},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5471112728118896},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5164728164672852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5071141719818115},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4678303301334381},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4445442855358124},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.44301629066467285},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43715792894363403},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43377885222435},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4066806435585022},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28318920731544495}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6856522560119629},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6595567464828491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6547940373420715},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5518364906311035},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5471112728118896},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5164728164672852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5071141719818115},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4678303301334381},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4445442855358124},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.44301629066467285},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43715792894363403},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43377885222435},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4066806435585022},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28318920731544495},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2019/362","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/362","pdf_url":"https://www.ijcai.org/proceedings/2019/0362.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1712.03333","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.03333","pdf_url":"https://arxiv.org/pdf/1712.03333","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2019/362","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/362","pdf_url":"https://www.ijcai.org/proceedings/2019/0362.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2807557496.pdf","grobid_xml":"https://content.openalex.org/works/W2807557496.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W64088143","https://openalex.org/W163742544","https://openalex.org/W1496855202","https://openalex.org/W1497039698","https://openalex.org/W1542595278","https://openalex.org/W1559536185","https://openalex.org/W1575388622","https://openalex.org/W1582436621","https://openalex.org/W1591803298","https://openalex.org/W1595483645","https://openalex.org/W1757796397","https://openalex.org/W1945133117","https://openalex.org/W1981277868","https://openalex.org/W2039522160","https://openalex.org/W2100785108","https://openalex.org/W2107726111","https://openalex.org/W2111764152","https://openalex.org/W2115211925","https://openalex.org/W2116459397","https://openalex.org/W2132849848","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2156974606","https://openalex.org/W2157477959","https://openalex.org/W2158984235","https://openalex.org/W2201581102","https://openalex.org/W2280163991","https://openalex.org/W2398780562","https://openalex.org/W2586680856","https://openalex.org/W2746553466","https://openalex.org/W2755611049","https://openalex.org/W2787400134","https://openalex.org/W2962767126","https://openalex.org/W2963423916","https://openalex.org/W2963797557","https://openalex.org/W2963938771","https://openalex.org/W3105804532","https://openalex.org/W3123298421","https://openalex.org/W4234228486","https://openalex.org/W4285719527","https://openalex.org/W4293405734","https://openalex.org/W4298857966","https://openalex.org/W4298876402","https://openalex.org/W4300892457"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W3105579180","https://openalex.org/W4287865573","https://openalex.org/W2807018115","https://openalex.org/W2051622126","https://openalex.org/W2025663273","https://openalex.org/W3007324819","https://openalex.org/W2290470984","https://openalex.org/W1574958246","https://openalex.org/W2104958792"],"abstract_inverted_index":{"While":[0],"off-policy":[1,63],"temporal":[2],"difference":[3],"(TD)":[4],"methods":[5],"have":[6,23],"widely":[7],"been":[8,25],"used":[9,116],"in":[10,37,110,117,183],"reinforcement":[11],"learning":[12],"due":[13],"to":[14,45,62,136],"their":[15,20],"efficiency":[16],"and":[17,146],"simple":[18],"implementation,":[19],"Bayesian":[21,60,79,152],"counterparts":[22],"not":[24,113],"utilized":[26],"as":[27,67,83,138,156],"frequently.":[28],"One":[29],"reason":[30],"is":[31],"that":[32,170],"the":[33,38,50,94,103,106,111,126,139,143],"non-linear":[34],"max":[35],"operation":[36],"Bellman":[39],"optimality":[40],"equation":[41],"makes":[42],"it":[43],"difficult":[44],"define":[46],"conjugate":[47],"distributions":[48],"over":[49],"value":[51,95,127],"functions.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"introduce":[57],"a":[58,122,163,190],"novel":[59],"approach":[61],"TD":[64],"methods,":[65],"called":[66],"ADFQ,":[68],"which":[69],"updates":[70],"beliefs":[71,112],"on":[72,175],"state-action":[73],"values,":[74],"Q,":[75],"through":[76],"an":[77,89],"online":[78],"inference":[80],"method":[81],"known":[82],"Assumed":[84],"Density":[85],"Filtering.":[86],"We":[87,159],"formulate":[88],"efficient":[90],"closed-form":[91],"solution":[92],"for":[93,125],"update":[96,128],"by":[97],"approximately":[98],"estimating":[99],"analytic":[100],"parameters":[101],"of":[102,105,142,150],"posterior":[104],"Q-beliefs.":[107],"Uncertainty":[108],"measures":[109,141],"only":[114],"are":[115],"exploration":[118],"but":[119],"also":[120],"provide":[121],"natural":[123],"regularization":[124],"considering":[129],"all":[130],"next":[131],"available":[132],"actions.":[133],"ADFQ":[134,161,171],"converges":[135],"Q-learning":[137],"uncertainty":[140],"Q-beliefs":[144],"decrease":[145],"improves":[147],"common":[148],"drawbacks":[149],"other":[151],"RL":[153],"algorithms":[154,174],"such":[155],"computational":[157],"complexity.":[158],"extend":[160],"with":[162,180,189],"neural":[164],"network.":[165],"Our":[166],"empirical":[167],"results":[168],"demonstrate":[169],"outperforms":[172],"comparable":[173],"various":[176],"Atari":[177],"2600":[178],"games,":[179],"drastic":[181],"improvements":[182],"highly":[184],"stochastic":[185],"domains":[186,188],"or":[187],"large":[191],"action":[192],"space.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}