{"id":"https://openalex.org/W3206042616","doi":"https://doi.org/10.1109/icra48506.2021.9560734","title":"Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction","display_name":"Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3206042616","doi":"https://doi.org/10.1109/icra48506.2021.9560734","mag":"3206042616"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9560734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5103071688","display_name":"Masashi Okada","orcid":"https://orcid.org/0000-0002-5111-0483"},"institutions":[{"id":"https://openalex.org/I1283155146","display_name":"Panasonic (Japan)","ror":"https://ror.org/011tm7n37","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283155146"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masashi Okada","raw_affiliation_strings":["Digitan & AI Technology Center, Technology Division, Panasonic Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Digitan & AI Technology Center, Technology Division, Panasonic Corporation, Japan","institution_ids":["https://openalex.org/I1283155146"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023160093","display_name":"Tadahiro Taniguchi","orcid":"https://orcid.org/0000-0002-5682-2076"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]},{"id":"https://openalex.org/I1283155146","display_name":"Panasonic (Japan)","ror":"https://ror.org/011tm7n37","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283155146"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tadahiro Taniguchi","raw_affiliation_strings":["College of Information Science and Engineering, Ritsumeikan University, Japan","Digitan & AI Technology Center, Technology Division, Panasonic Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ritsumeikan University, Japan","institution_ids":["https://openalex.org/I135768898"]},{"raw_affiliation_string":"Digitan & AI Technology Center, Technology Division, Panasonic Corporation, Japan","institution_ids":["https://openalex.org/I1283155146"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103071688"],"corresponding_institution_ids":["https://openalex.org/I1283155146"],"apc_list":null,"apc_paid":null,"fwci":4.2243,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.95065262,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4209","last_page":"4215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9865000247955322,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7410601377487183},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7409963011741638},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7257214784622192},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6286616921424866},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5690298080444336},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5361585021018982},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5324496030807495},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.49662572145462036},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.4843619763851166},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4383430480957031},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3422706723213196},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.30153554677963257},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.24126338958740234},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19946280121803284}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7410601377487183},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7409963011741638},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7257214784622192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6286616921424866},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5690298080444336},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5361585021018982},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5324496030807495},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.49662572145462036},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.4843619763851166},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4383430480957031},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3422706723213196},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.30153554677963257},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.24126338958740234},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19946280121803284},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9560734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":84,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2140135625","https://openalex.org/W2150468603","https://openalex.org/W2157331557","https://openalex.org/W2781585732","https://openalex.org/W2781726626","https://openalex.org/W2842511635","https://openalex.org/W2890208753","https://openalex.org/W2900152462","https://openalex.org/W2920362155","https://openalex.org/W2937555108","https://openalex.org/W2946006146","https://openalex.org/W2949759968","https://openalex.org/W2953708620","https://openalex.org/W2958484796","https://openalex.org/W2963960193","https://openalex.org/W2964420626","https://openalex.org/W2977481643","https://openalex.org/W2981547136","https://openalex.org/W2982437637","https://openalex.org/W2994714051","https://openalex.org/W2994849131","https://openalex.org/W2995298643","https://openalex.org/W2995480165","https://openalex.org/W2995546843","https://openalex.org/W2995773109","https://openalex.org/W3005680577","https://openalex.org/W3012514211","https://openalex.org/W3021708257","https://openalex.org/W3023640063","https://openalex.org/W3025660841","https://openalex.org/W3029122934","https://openalex.org/W3029509103","https://openalex.org/W3030598573","https://openalex.org/W3031547186","https://openalex.org/W3031634197","https://openalex.org/W3032223429","https://openalex.org/W3032727894","https://openalex.org/W3036185205","https://openalex.org/W3041764008","https://openalex.org/W3101283005","https://openalex.org/W3103780890","https://openalex.org/W3115293622","https://openalex.org/W3125947392","https://openalex.org/W3132285497","https://openalex.org/W3132689960","https://openalex.org/W3172115140","https://openalex.org/W3175558129","https://openalex.org/W4287779179","https://openalex.org/W4287811291","https://openalex.org/W4288294128","https://openalex.org/W4289294484","https://openalex.org/W4297808394","https://openalex.org/W4298206671","https://openalex.org/W6640963894","https://openalex.org/W6680657880","https://openalex.org/W6747387971","https://openalex.org/W6747473740","https://openalex.org/W6751494529","https://openalex.org/W6754184789","https://openalex.org/W6756256016","https://openalex.org/W6760405395","https://openalex.org/W6761392374","https://openalex.org/W6762796984","https://openalex.org/W6765121789","https://openalex.org/W6765407481","https://openalex.org/W6765813175","https://openalex.org/W6766489549","https://openalex.org/W6768397756","https://openalex.org/W6769397037","https://openalex.org/W6769673253","https://openalex.org/W6771217966","https://openalex.org/W6771344510","https://openalex.org/W6771810092","https://openalex.org/W6774314701","https://openalex.org/W6774733536","https://openalex.org/W6775634482","https://openalex.org/W6776867236","https://openalex.org/W6776901495","https://openalex.org/W6778000925","https://openalex.org/W6778695474","https://openalex.org/W6779827379","https://openalex.org/W6780571964","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2810330923","https://openalex.org/W4289763776","https://openalex.org/W2988134182","https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W3042518613","https://openalex.org/W3015304056","https://openalex.org/W2470043383","https://openalex.org/W4380551139","https://openalex.org/W2953501176"],"abstract_inverted_index":{"In":[0,148],"the":[1,64,97,115,132,138,145,171],"present":[2],"paper,":[3],"we":[4,102,122],"propose":[5],"a":[6,11,22,41,105],"decoder-free":[7],"extension":[8],"of":[9,95,111,119],"Dreamer,":[10],"leading":[12],"model-based":[13],"reinforcement":[14,156],"learning":[15,113,139,157],"(MBRL)":[16],"method":[17],"from":[18,114,184],"pixels.":[19],"Dreamer":[20,151,162,182],"is":[21,32],"sample-":[23],"and":[24,44,75,89,108,130,152,165],"cost-efficient":[25],"solution":[26],"to":[27,34,45,67,84,137,143,150],"robot":[28],"learning,":[29],"as":[30,142],"it":[31],"used":[33],"train":[35],"latent":[36,50],"state-space":[37],"models":[38],"based":[39,56],"on":[40,174],"variational":[42],"autoencoder":[43,65],"conduct":[46],"policy":[47],"optimization":[48],"by":[49,93],"trajectory":[51],"imagination.":[52],"However,":[53],"this":[54,86,100],"autoencoding":[55],"approach":[57],"often":[58],"causes":[59],"object":[60,185],"vanishing,":[61],"in":[62,180],"which":[63,181],"fails":[66],"perceives":[68],"key":[69],"objects":[70],"for":[71],"solving":[72],"control":[73],"tasks,":[74,179],"thus":[76],"significantly":[77],"limiting":[78],"Dreamer's":[79,87],"potential.":[80],"This":[81],"work":[82],"aims":[83],"relieve":[85],"bottleneck":[88],"enhance":[90],"its":[91],"performance":[92],"means":[94],"removing":[96],"decoder.":[98],"For":[99],"purpose,":[101],"firstly":[103],"derive":[104],"likelihood-":[106],"free":[107],"InfoMax":[109,164],"objective":[110],"contrastive":[112],"evidence":[116],"lower":[117],"bound":[118],"Dreamer.":[120],"Secondly,":[121],"incorporate":[123],"two":[124],"components,":[125],"(i)":[126],"independent":[127],"linear":[128],"dynamics":[129],"(ii)":[131],"random":[133],"crop":[134],"data":[135],"augmentation,":[136],"scheme":[140],"so":[141],"improve":[144],"training":[146],"performance.":[147],"comparison":[149],"other":[153],"recent":[154],"model-free":[155],"methods,":[158],"our":[159],"newly":[160],"devised":[161],"with":[163],"without":[166],"generative":[167],"decoder":[168],"(Dreaming)":[169],"achieves":[170],"best":[172],"scores":[173],"5":[175],"difficult":[176],"simulated":[177],"robotics":[178],"suffers":[183],"vanishing.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}