TUHH Open Research
Help
  • Log In
    New user? Click here to register.Have you forgotten your password?
  • English
  • Deutsch
  • Communities & Collections
  • Publications
  • Research Data
  • People
  • Institutions
  • Projects
  • Statistics
  1. Home
  2. TUHH
  3. Publications
  4. Meta-world+: an improved, standardized, RL benchmark
 
Options

Meta-world+: an improved, standardized, RL benchmark

Citation Link: https://doi.org/10.15480/882.16723
Publikationstyp
Preprint
Conference Paper
Date Issued
2025-11-21
Sprache
English
Author(s)
McLean, Reginald
Chatzaroulas, Evangelos
McCutcheon, Luc  
Röder, Frank  
Data Science Foundations E-21  
He, Zhanpeng
Yu, Tianhe
Julian, Ryan
Zentner, K. R.
Terry, Jordan  
Woungang, Isaac  
Farsad, Nariman
Castro, Pablo Samuel
TORE-DOI
10.15480/882.16723
TORE-URI
https://hdl.handle.net/11420/61570
Start Page
1
End Page
21
Citation
39th Conference on Neural Information Processing Systems, NeurIPS 2025
Contribution to Conference
39th Conference on Neural Information Processing Systems, NeurIPS 2025  
Publisher DOI
10.48550/arXiv.2505.11289
ArXiv ID
2505.11289
Meta-World is widely used for evaluating multi-task and meta-reinforcement learning agents, which are challenged to master diverse skills simultaneously. Since its introduction however, there have been numerous undocumented changes which inhibit a fair comparison of algorithms. This work strives to disambiguate these results from the literature, while also leveraging the past versions of Meta-World to provide insights into multi-task and meta-reinforcement learning benchmark design. Through this process we release a new open-source version of Meta-World1 that has full reproducibility of past results, is more technically ergonomic, and gives users more control over the tasks that are included in a task set.
DDC Class
005: Computer Programming, Programs, Data and Security
006: Special computer methods
Lizenz
https://creativecommons.org/licenses/by/4.0/
Publication version
submittedVersion
Loading...
Thumbnail Image
Name

2505.11289v2.pdf

Size

4.2 MB

Format

Adobe PDF

TUHH
Weiterführende Links
  • Contact
  • Send Feedback
  • Cookie settings
  • Privacy policy
  • Impress
DSpace Software

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science
Design by effective webwork GmbH

  • Deutsche NationalbibliothekDeutsche Nationalbibliothek
  • ORCiD Member OrganizationORCiD Member Organization
  • DataCiteDataCite
  • Re3DataRe3Data
  • OpenDOAROpenDOAR
  • OpenAireOpenAire
  • BASE Bielefeld Academic Search EngineBASE Bielefeld Academic Search Engine
Feedback