{"id":"https://openalex.org/W4312299945","doi":"https://doi.org/10.1109/iros47612.2022.9981405","title":"DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction","display_name":"DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312299945","doi":"https://doi.org/10.1109/iros47612.2022.9981405"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981405","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":["Digital & AI Technology Center,Technology Division, Panasonic Corporation,Japan"],"affiliations":[{"raw_affiliation_string":"Digital & 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":["Digital & AI Technology Center,Technology Division, Panasonic Corporation,Japan","Ritsumeikan University, College of Information Science and Engineering, Japan"],"affiliations":[{"raw_affiliation_string":"Digital & AI Technology Center,Technology Division, Panasonic Corporation,Japan","institution_ids":["https://openalex.org/I1283155146"]},{"raw_affiliation_string":"Ritsumeikan University, College of Information Science and Engineering, Japan","institution_ids":["https://openalex.org/I135768898"]}]}],"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":1.9933,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88732245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"985","last_page":"991"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9990000128746033,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8191866874694824},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.712168276309967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7014303207397461},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.5991042852401733},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.560357928276062},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.544888436794281},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5155272483825684},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49322789907455444},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46496158838272095},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4505411684513092},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.41176003217697144},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4053381681442261}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8191866874694824},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.712168276309967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7014303207397461},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5991042852401733},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.560357928276062},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.544888436794281},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5155272483825684},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49322789907455444},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46496158838272095},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4505411684513092},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.41176003217697144},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4053381681442261},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981405","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W834081922","https://openalex.org/W2110346534","https://openalex.org/W2150468603","https://openalex.org/W2157331557","https://openalex.org/W2242818861","https://openalex.org/W2781585732","https://openalex.org/W2958484796","https://openalex.org/W2963336905","https://openalex.org/W2994849131","https://openalex.org/W2995298643","https://openalex.org/W3005680577","https://openalex.org/W3012514211","https://openalex.org/W3028766998","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3036224891","https://openalex.org/W3047079303","https://openalex.org/W3088304681","https://openalex.org/W3115293622","https://openalex.org/W3118062200","https://openalex.org/W3122690883","https://openalex.org/W3132285497","https://openalex.org/W3134652006","https://openalex.org/W3169216412","https://openalex.org/W3186672455","https://openalex.org/W3190215236","https://openalex.org/W3205091198","https://openalex.org/W3206042616","https://openalex.org/W3210788351","https://openalex.org/W4210659164","https://openalex.org/W4249244053","https://openalex.org/W4287779179","https://openalex.org/W4289294484","https://openalex.org/W4297808394","https://openalex.org/W6623316541","https://openalex.org/W6756256016","https://openalex.org/W6765813175","https://openalex.org/W6771217966","https://openalex.org/W6771810092","https://openalex.org/W6774314701","https://openalex.org/W6775634482","https://openalex.org/W6777656069","https://openalex.org/W6778102432","https://openalex.org/W6779326418","https://openalex.org/W6779997284","https://openalex.org/W6781981342","https://openalex.org/W6783988234","https://openalex.org/W6791742336","https://openalex.org/W6795793241","https://openalex.org/W6799458897"],"related_works":["https://openalex.org/W4386799044","https://openalex.org/W2773208253","https://openalex.org/W2560646951","https://openalex.org/W4297454206","https://openalex.org/W65104662","https://openalex.org/W1871748041","https://openalex.org/W2362286668","https://openalex.org/W4390437797","https://openalex.org/W4312820300","https://openalex.org/W2039892622"],"abstract_inverted_index":{"The":[0,72],"present":[1],"paper":[2],"proposes":[3],"a":[4,13,23,45,67,76,122],"novel":[5,77],"reinforce-ment":[6],"learning":[7,27,49,70,127],"method":[8],"with":[9,39],"world":[10,33,62],"models,":[11],"DreamingV2,":[12],"collaborative":[14],"extension":[15],"of":[16,47,79,85,91],"DreamerV2":[17,95],"and":[18,87,96,138],"Dreaming.":[19,92],"Dream-":[20],"erV2":[21],"is":[22,43,75,132],"cutting-edge":[24],"model-based":[25,99],"reinforcement":[26,48],"from":[28,50],"pixels":[29,51],"that":[30,52,118],"uses":[31],"discrete":[32,83,130],"models":[34],"to":[35,54,94,134],"represent":[36],"latent":[37],"states":[38],"categorical":[40],"variables.":[41],"Dreaming":[42],"also":[44],"form":[46],"attempts":[53],"avoid":[55],"the":[56,82,88,105,139],"auto":[57],"encoding":[58],"process":[59],"in":[60],"general":[61],"model":[63],"training":[64],"by":[65],"involving":[66],"reconstruction-free":[68,89,140],"contrastive":[69],"objective.":[71],"proposed":[73],"DreamingV2":[74,86,103,119],"approach":[78],"adopting":[80],"both":[81],"representation":[84,131],"objective":[90],"Compared":[93],"other":[97],"recent":[98],"methods":[100],"without":[101],"reconstruction,":[102],"achieves":[104],"best":[106],"scores":[107],"on":[108],"five":[109],"simulated":[110],"challenging":[111],"3D":[112],"robot":[113,126],"arm":[114],"tasks.":[115],"We":[116],"believe":[117],"will":[120],"be":[121],"reliable":[123],"solution":[124],"for":[125],"since":[128],"its":[129],"suitable":[133],"describe":[135],"discontinuous":[136],"environments,":[137],"fashion":[141],"well":[142],"manages":[143],"complex":[144],"vision":[145],"observations.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}