You're currently viewing an old version of this dataset. To see the current version, click here.

DMLab-30

DMLab-30 is a benchmark for multitask reinforcement learning in partially observable environments.

Data and Resources

Cite this as

Dennis Diefenbach, Thomas Tanon, Kamal Singh, Pierre Maret (2024). Dataset: DMLab-30. https://doi.org/10.57702/jrz5dpei

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2004.14646
Citation
  • https://doi.org/10.48550/arXiv.1803.03835
Author Dennis Diefenbach
More Authors
Thomas Tanon
Kamal Singh
Pierre Maret
Homepage https://github.com/deepmind/lab