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

D4RL

The D4RL benchmark datasets contain various types of datasets sourced from different policies across multiple environments, designed to evaluate offline reinforcement learning algorithms.

Data and Resources

This dataset has no data

Cite this as

Justin Fu, Aviral Kumar, Ofir Nachum, George Tucker, Sergey Levine (2024). Dataset: D4RL. https://doi.org/10.57702/4cmkf99i

Private DOI This DOI is not yet resolvable.
It is available for use in manuscripts, and will be published when the Dataset is made public.

Additional Info

Field	Value
Created	November 25, 2024
Last update	November 25, 2024
Author	Justin Fu
More Authors	Aviral Kumar Ofir Nachum George Tucker Sergey Levine
Homepage	https://github.com/rail-berkeley/d4rl