{"id":"https://openalex.org/W4385834352","doi":"https://doi.org/10.1109/tnnls.2023.3296642","title":"Sample Efficient Deep Reinforcement Learning With Online State Abstraction and Causal Transformer Model Prediction","display_name":"Sample Efficient Deep Reinforcement Learning With Online State Abstraction and Causal Transformer Model Prediction","publication_year":2023,"publication_date":"2023-08-15","ids":{"openalex":"https://openalex.org/W4385834352","doi":"https://doi.org/10.1109/tnnls.2023.3296642","pmid":"https://pubmed.ncbi.nlm.nih.gov/37581972"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3296642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3296642","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030762555","display_name":"Yixing Lan","orcid":"https://orcid.org/0000-0003-4503-643X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixing Lan","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-4503-643X","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-3238-745X","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055651722","display_name":"Qiang Fang","orcid":"https://orcid.org/0000-0002-5063-6889"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fang","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047509839","display_name":"Jianye Hao","orcid":"https://orcid.org/0000-0002-0422-8235"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianye Hao","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-0422-8235","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5863,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85881063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"35","issue":"11","first_page":"16574","last_page":"16588"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9945999979972839,"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":0.9945999979972839,"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":0.8549357652664185},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7954843640327454},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6900495290756226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6055986285209656},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.5509296655654907},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5454677939414978},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.507281482219696},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.458712637424469},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4397774338722229},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.43541523814201355},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.43297278881073},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3158456087112427},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09819787740707397}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8549357652664185},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7954843640327454},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6900495290756226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6055986285209656},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.5509296655654907},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5454677939414978},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.507281482219696},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.458712637424469},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4397774338722229},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.43541523814201355},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.43297278881073},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3158456087112427},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09819787740707397},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3296642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3296642","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37581972","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37581972","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G5196624177","display_name":null,"funder_award_id":"61825305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8354495100","display_name":null,"funder_award_id":"U21A20518","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1995688924","https://openalex.org/W2058735307","https://openalex.org/W2111959010","https://openalex.org/W2150468603","https://openalex.org/W2516809705","https://openalex.org/W2572640103","https://openalex.org/W2761873684","https://openalex.org/W2952867909","https://openalex.org/W2963761387","https://openalex.org/W2989847975","https://openalex.org/W2997101648","https://openalex.org/W3175558129","https://openalex.org/W3200466256","https://openalex.org/W4214717370","https://openalex.org/W4243421009","https://openalex.org/W4252279978","https://openalex.org/W4309367642","https://openalex.org/W6635516443","https://openalex.org/W6638739688","https://openalex.org/W6735913928","https://openalex.org/W6747387971","https://openalex.org/W6747473740","https://openalex.org/W6751087324","https://openalex.org/W6753001025","https://openalex.org/W6757797181","https://openalex.org/W6760405395","https://openalex.org/W6763088550","https://openalex.org/W6763282038","https://openalex.org/W6765242767","https://openalex.org/W6765407481","https://openalex.org/W6765721576","https://openalex.org/W6771217966","https://openalex.org/W6771656438","https://openalex.org/W6775277072","https://openalex.org/W6776867236","https://openalex.org/W6779160628","https://openalex.org/W6779827379","https://openalex.org/W6783988234","https://openalex.org/W6785279468","https://openalex.org/W6787713516","https://openalex.org/W6790416196","https://openalex.org/W6792018038","https://openalex.org/W6796008061","https://openalex.org/W6796289742","https://openalex.org/W6804244202","https://openalex.org/W6804644115","https://openalex.org/W6804859080","https://openalex.org/W6839280558","https://openalex.org/W6842654171"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2182304831"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,45,56],"(RL)":[3],"typically":[4],"requires":[5],"a":[6,69,99,118,135,142],"tremendous":[7],"number":[8],"of":[9,64,179],"training":[10,159],"samples,":[11],"which":[12,59],"are":[13,24,93,124,188],"not":[14],"practical":[15],"in":[16,32,177],"many":[17],"applications.":[18],"State":[19],"abstraction":[20,38,72],"and":[21,39,112,164,190,202],"world":[22,40],"models":[23,41],"two":[25],"promising":[26],"approaches":[27],"for":[28],"improving":[29],"sample":[30,62,155,180],"efficiency":[31,63,156],"deep":[33,65,174],"RL.":[34,66],"However,":[35],"both":[36],"state":[37,71,84],"may":[42],"degrade":[43],"the":[44,61,87,109,131,150,158,165,191,205],"performance.":[46],"In":[47,67],"this":[48],"article,":[49],"we":[50],"propose":[51],"an":[52],"abstracted":[53,96,110,132],"model-based":[54],"policy":[55],"(AMPL)":[57],"algorithm,":[58],"improves":[60],"AMPL,":[68],"novel":[70],"method":[73],"via":[74,134],"multistep":[75,120,137],"bisimulation":[76],"is":[77,105,196],"first":[78],"developed":[79],"to":[80,107,198],"learn":[81],"task-related":[82],"latent":[83],"spaces.":[85],"Hence,":[86],"original":[88],"Markov":[89],"decision":[90],"processes":[91],"(MDPs)":[92],"compressed":[94],"into":[95],"MDPs.":[97],"Then,":[98],"causal":[100],"transformer":[101],"model":[102],"predictor":[103],"(CTMP)":[104],"designed":[106],"approximate":[108],"MDPs":[111,133],"generate":[113],"long-horizon":[114],"simulated":[115],"trajectories":[116,129],"with":[117,141,185],"smaller":[119],"prediction":[121],"error.":[122],"Policies":[123],"efficiently":[125],"learned":[126],"through":[127],"these":[128],"within":[130],"modified":[136],"soft":[138],"actor-critic":[139],"algorithm":[140,152],"\u03bb":[143],"-target.":[144],"Moreover,":[145],"theoretical":[146],"analysis":[147],"shows":[148],"that":[149,194],"AMPL":[151,170,195],"can":[153],"improve":[154],"during":[157],"process.":[160],"On":[161],"Atari":[162],"games":[163],"DeepMind":[166],"Control":[167],"(DMControl)":[168],"suite,":[169],"surpasses":[171],"current":[172],"state-of-the-art":[173],"RL":[175],"algorithms":[176],"terms":[178],"efficiency.":[181],"Furthermore,":[182],"DMControl":[183],"tasks":[184],"moving":[186],"noises":[187],"conducted,":[189],"results":[192],"demonstrate":[193],"robust":[197],"task-irrelevant":[199],"observational":[200],"distractors":[201],"significantly":[203],"outperforms":[204],"existing":[206],"approaches.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}