{"id":"https://openalex.org/W7138200830","doi":"https://doi.org/10.1609/aaai.v40i31.39875","title":"Latent State-Predictive Exploration for Deep Reinforcement Learning","display_name":"Latent State-Predictive Exploration for Deep Reinforcement Learning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138200830","doi":"https://doi.org/10.1609/aaai.v40i31.39875"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i31.39875","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39875","pdf_url":null,"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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i31.39875","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129737998","display_name":"Yiming Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiming Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129729231","display_name":"Kaiyan Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaiyan Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129720064","display_name":"Borong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Borong Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129650031","display_name":"Yan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129737652","display_name":"Leong Hou U","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leong Hou U","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20107831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"31","first_page":"26661","last_page":"26669"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6194999814033508,"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":0.6194999814033508,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.14030000567436218,"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":0.04230000078678131,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6298999786376953},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4596000015735626},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4465000033378601},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.38510000705718994},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.36719998717308044},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3571000099182129},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.35280001163482666},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3255000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6966000199317932},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6298999786376953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6148999929428101},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46389999985694885},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4596000015735626},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4465000033378601},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.26570001244544983},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i31.39875","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39875","pdf_url":null,"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"},{"id":"pmh:oai:ojs.aaai.org:article/39875","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39875","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39875/43836","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i31.39875","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39875","pdf_url":null,"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":[],"awards":[{"id":"https://openalex.org/G5622060990","display_name":null,"funder_award_id":"001/2024/SKL","funder_id":"https://openalex.org/F4320322841","funder_display_name":"Universidade de Macau"},{"id":"https://openalex.org/G7980548823","display_name":null,"funder_award_id":"62402325","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8070309574","display_name":null,"funder_award_id":"001/2024/SKL","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320313851","display_name":"Shenzhen Polytechnic","ror":"https://ror.org/00d2w9g53"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322841","display_name":"Universidade de Macau","ror":"https://ror.org/01r4q9n85"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3],"achieved":[4],"promising":[5],"results":[6,201],"in":[7,39,81,162,195],"continuous":[8],"control":[9],"tasks,":[10,37,178],"where":[11],"efficient":[12,158],"exploration":[13,34,56,80,130,161,207],"of":[14,76,172],"the":[15,71,146],"state":[16,46,88],"space":[17],"is":[18,68],"crucial":[19],"for":[20,35],"success.":[21],"However,":[22],"many":[23],"recent":[24],"RL":[25],"approaches":[26],"still":[27],"struggle":[28],"with":[29,73],"sample":[30],"inefficiency":[31],"and":[32,44,109,131,159,176,185,209],"insufficient":[33],"long-horizon":[36,82,174],"particularly":[38],"environments":[40,181],"characterized":[41],"by":[42,123],"high-dimensional":[43,96,214],"complex":[45,163],"spaces.":[47],"To":[48,106],"address":[49],"these":[50,111],"challenges,":[51],"we":[52,113,136],"propose":[53],"a":[54,74,87,115,169,192,196],"novel":[55,150],"framework,":[57],"Latent":[58],"State":[59],"Predictive":[60],"Exploration":[61,139],"(LSPE).":[62],"The":[63],"core":[64],"idea":[65],"behind":[66],"LSPE":[67,85,167,204],"to":[69,78,90,148,212],"endow":[70],"agent":[72,147],"form":[75],"``foresight\"":[77],"enhance":[79],"settings.":[83],"Specifically,":[84],"employs":[86],"encoder":[89],"learn":[91],"compact":[92],"latent":[93,151],"representations":[94],"from":[95],"visual":[97],"observations,":[98],"effectively":[99,211],"filtering":[100],"out":[101],"irrelevant":[102],"or":[103],"noisy":[104],"information.":[105],"further":[107],"enrich":[108],"stabilize":[110],"representations,":[112],"incorporate":[114],"diffusion-based":[116],"self-predictive":[117],"module":[118],"that":[119,143,203],"enforces":[120],"temporal":[121],"consistency":[122],"predicting":[124],"future":[125],"states,":[126],"thereby":[127],"improving":[128],"both":[129],"downstream":[132],"predictive":[133],"control.":[134],"Additionally,":[135],"introduce":[137],"an":[138],"Reward":[140],"Function":[141],"(ERF)":[142],"explicitly":[144],"encourages":[145],"visit":[149],"states.":[152],"This":[153],"reward":[154],"signal":[155],"promotes":[156],"more":[157],"scalable":[160],"environments.":[164],"We":[165],"evaluate":[166],"across":[168],"diverse":[170],"set":[171],"challenging":[173],"navigation":[175],"manipulation":[177],"spanning":[179],"simulation":[180],"such":[182],"as":[183,187,189],"Habitat":[184],"Robosuite,":[186],"well":[188],"deployment":[190],"on":[191],"real":[193],"robot":[194],"**physical":[197],"indoor":[198],"environment**.":[199],"Experimental":[200],"show":[202],"substantially":[205],"enhances":[206],"efficiency":[208],"scales":[210],"complex,":[213],"tasks.":[215]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2026-03-18T00:00:00"}