{"id":"https://openalex.org/W4392427796","doi":"https://doi.org/10.48550/arxiv.2403.00564","title":"EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data","display_name":"EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data","publication_year":2024,"publication_date":"2024-03-01","ids":{"openalex":"https://openalex.org/W4392427796","doi":"https://doi.org/10.48550/arxiv.2403.00564"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.00564","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.00564","pdf_url":"https://arxiv.org/pdf/2403.00564","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.00564","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100696961","display_name":"Shengjie Wang","orcid":"https://orcid.org/0000-0003-3990-5803"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Shengjie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113981679","display_name":"S.C. Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shaohuai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003926322","display_name":"Weirui Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Weirui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101381899","display_name":"Jiacheng You","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You, Jiacheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038207720","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-2150-5986"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Yang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100696961"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.5985000133514404,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.5985000133514404,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5190492272377014},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5035452246665955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14854151010513306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5190492272377014},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5035452246665955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14854151010513306}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.00564","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.00564","pdf_url":"https://arxiv.org/pdf/2403.00564","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.00564","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.00564","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.00564","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.00564","pdf_url":"https://arxiv.org/pdf/2403.00564","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392427796.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Sample":[0],"efficiency":[1],"remains":[2],"a":[3,41,73,87,101],"crucial":[4],"challenge":[5],"in":[6,21,90,113],"applying":[7],"Reinforcement":[8],"Learning":[9],"(RL)":[10],"to":[11,56],"real-world":[12],"tasks.":[13],"While":[14],"recent":[15],"algorithms":[16],"have":[17,26,50],"made":[18],"significant":[19,88],"strides":[20],"improving":[22],"sample":[23],"efficiency,":[24],"none":[25],"achieved":[27],"consistently":[28],"superior":[29,111],"performance":[30,53],"across":[31,119],"diverse":[32,91,120],"domains.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37,77],"introduce":[38],"EfficientZero":[39,55,79,98],"V2,":[40],"general":[42,107],"framework":[43],"designed":[44],"for":[45],"sample-efficient":[46],"RL":[47],"algorithms.":[48],"We":[49],"expanded":[51],"the":[52,82,94,105],"of":[54,75,115],"multiple":[57],"domains,":[58],"encompassing":[59],"both":[60],"continuous":[61],"and":[62,69,128],"discrete":[63],"actions,":[64],"as":[65,67,123],"well":[66],"visual":[68],"low-dimensional":[70],"inputs.":[71],"With":[72],"series":[74],"improvements":[76],"propose,":[78],"V2":[80,99],"outperforms":[81],"current":[83],"state-of-the-art":[84],"(SOTA)":[85],"by":[86],"margin":[89],"tasks":[92,118],"under":[93],"limited":[95],"data":[96],"setting.":[97],"exhibits":[100],"notable":[102],"advancement":[103],"over":[104],"prevailing":[106],"algorithm,":[108],"DreamerV3,":[109],"achieving":[110],"outcomes":[112],"50":[114],"66":[116],"evaluated":[117],"benchmarks,":[121],"such":[122],"Atari":[124],"100k,":[125],"Proprio":[126],"Control,":[127],"Vision":[129],"Control.":[130]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
