{"id":"https://openalex.org/W4388966807","doi":"https://doi.org/10.1109/tpami.2023.3335263","title":"Model-Based Reinforcement Learning With Isolated Imaginations","display_name":"Model-Based Reinforcement Learning With Isolated Imaginations","publication_year":2023,"publication_date":"2023-11-24","ids":{"openalex":"https://openalex.org/W4388966807","doi":"https://doi.org/10.1109/tpami.2023.3335263","pmid":"https://pubmed.ncbi.nlm.nih.gov/37999968"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3335263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3335263","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5019129747","display_name":"Minting Pan","orcid":"https://orcid.org/0000-0002-4666-510X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minting Pan","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4666-510X","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100971007","display_name":"Xiangming Zhu","orcid":"https://orcid.org/0009-0008-7974-047X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangming Zhu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-7974-047X","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104202441","display_name":"Yitao Zheng","orcid":"https://orcid.org/0009-0005-3066-4910"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yitao Zheng","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-3066-4910","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100713555","display_name":"Yunbo Wang","orcid":"https://orcid.org/0000-0002-6224-2481"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbo Wang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6224-2481","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019708391","display_name":"Xiaokang Yang","orcid":"https://orcid.org/0000-0003-4029-3322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4029-3322","affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.8065,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78727803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"46","issue":"5","first_page":"2788","last_page":"2803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9905999898910522,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9818000197410583,"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":0.851358950138092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7695298194885254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6317034363746643},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5252237319946289},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.49996328353881836},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4538217782974243},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.16990375518798828},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12757766246795654}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.851358950138092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695298194885254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6317034363746643},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5252237319946289},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.49996328353881836},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4538217782974243},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.16990375518798828},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12757766246795654}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3335263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3335263","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:37999968","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37999968","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G1978429096","display_name":null,"funder_award_id":"U19B2035","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2331728944","display_name":null,"funder_award_id":"62250062","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6193193764","display_name":null,"funder_award_id":"62106144","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W2528489519","https://openalex.org/W2781585732","https://openalex.org/W2786615588","https://openalex.org/W2798788386","https://openalex.org/W2891942975","https://openalex.org/W2894961607","https://openalex.org/W2902125520","https://openalex.org/W2904246096","https://openalex.org/W2962839378","https://openalex.org/W2991019415","https://openalex.org/W3004214476","https://openalex.org/W3015437096","https://openalex.org/W3034426027","https://openalex.org/W3035265644","https://openalex.org/W3035524453","https://openalex.org/W3037581554","https://openalex.org/W3118817977","https://openalex.org/W3138340468","https://openalex.org/W3174394676","https://openalex.org/W3174549347","https://openalex.org/W3174902251","https://openalex.org/W3174944154","https://openalex.org/W3175558129","https://openalex.org/W3205321526","https://openalex.org/W4214717370","https://openalex.org/W4313152746","https://openalex.org/W4315706776","https://openalex.org/W6628877408","https://openalex.org/W6677326919","https://openalex.org/W6677477928","https://openalex.org/W6712884540","https://openalex.org/W6726983635","https://openalex.org/W6735992252","https://openalex.org/W6736803224","https://openalex.org/W6738465933","https://openalex.org/W6740836278","https://openalex.org/W6742720488","https://openalex.org/W6743858559","https://openalex.org/W6745420753","https://openalex.org/W6745829810","https://openalex.org/W6745935785","https://openalex.org/W6747387971","https://openalex.org/W6748392304","https://openalex.org/W6752279500","https://openalex.org/W6752365561","https://openalex.org/W6752643364","https://openalex.org/W6754184789","https://openalex.org/W6756256016","https://openalex.org/W6756663807","https://openalex.org/W6756908582","https://openalex.org/W6757592117","https://openalex.org/W6759669191","https://openalex.org/W6760405395","https://openalex.org/W6766861245","https://openalex.org/W6768501859","https://openalex.org/W6770086194","https://openalex.org/W6771217966","https://openalex.org/W6771703261","https://openalex.org/W6776867236","https://openalex.org/W6778000925","https://openalex.org/W6779689074","https://openalex.org/W6779809370","https://openalex.org/W6779827379","https://openalex.org/W6783988234","https://openalex.org/W6787713516","https://openalex.org/W6797309367","https://openalex.org/W6797331426","https://openalex.org/W6803185011","https://openalex.org/W6810134311","https://openalex.org/W6839409570","https://openalex.org/W6843334904","https://openalex.org/W6845657183","https://openalex.org/W6846235960","https://openalex.org/W6848588639"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"World":[0],"models":[1,188],"learn":[2,35],"the":[3,59,64,73,78,87,98,105,123,132,154,163],"consequences":[4],"of":[5,77,134,143,167],"actions":[6],"in":[7,12,122,174],"vision-based":[8],"interactive":[9],"systems.":[10],"However,":[11],"practical":[13],"scenarios":[14],"like":[15],"autonomous":[16],"driving,":[17],"noncontrollable":[18,95,160],"dynamics":[19,61,120],"that":[20,51,129,182],"are":[21],"independent":[22],"or":[23],"sparsely":[24],"dependent":[25],"on":[26,86,190],"action":[27],"signals":[28],"often":[29],"exist,":[30],"making":[31],"it":[32],"challenging":[33],"to":[34,62,67,115],"effective":[36],"world":[37,65],"models.":[38],"To":[39],"address":[40,162],"this":[41],"issue,":[42],"we":[43,57,81,92,151],"propose":[44],"Iso-Dream++,":[45],"a":[46],"model-based":[47],"reinforcement":[48,186],"learning":[49,176,187],"approach":[50,173],"has":[52],"two":[53],"main":[54],"contributions.":[55],"First,":[56],"optimize":[58],"inverse":[60],"encourage":[63],"model":[66],"isolate":[68],"controllable":[69,107,158],"state":[70,168],"transitions":[71],"from":[72,117],"mixed":[74,119],"spatiotemporal":[75],"variations":[76],"environment.":[79],"Second,":[80],"perform":[82],"policy":[83],"optimization":[84],"based":[85],"decoupled":[88],"latent":[89],"imaginations,":[90],"where":[91],"roll":[93],"out":[94],"states":[96],"into":[97],"future":[99],"and":[100,159,170,192],"adaptively":[101],"associate":[102],"them":[103],"with":[104],"current":[106],"state.":[108],"This":[109],"enables":[110],"long-horizon":[111],"visuomotor":[112],"control":[113],"tasks":[114],"benefit":[116],"isolating":[118],"sources":[121],"wild,":[124],"such":[125],"as":[126],"self-driving":[127],"cars":[128],"can":[130],"anticipate":[131],"movement":[133],"other":[135],"vehicles,":[136],"thereby":[137],"avoiding":[138],"potential":[139],"risks.":[140],"On":[141],"top":[142],"our":[144,172],"previous":[145],"work":[146],"(Pan":[147],"et":[148],"al.":[149],"2022),":[150],"further":[152],"consider":[153],"sparse":[155],"dependencies":[156],"between":[157],"states,":[161],"training":[164],"collapse":[165],"problem":[166],"decoupling,":[169],"validate":[171],"transfer":[175],"setups.":[177],"Our":[178],"empirical":[179],"study":[180],"demonstrates":[181],"Iso-Dream++":[183],"outperforms":[184],"existing":[185],"significantly":[189],"CARLA":[191],"DeepMind":[193],"Control.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}