Datasets › URLB

URLB (Unsupervised Reinforcement Learning Benchmark)

Introduced by Michael Laskin et al. in URLB: Unsupervised Reinforcement Learning Benchmark28 Oct 2021 archive 2025-07-28

URLB consists of two phases: reward-free pre-training and downstream task adaptation with extrinsic rewards. Building on the DeepMind Control Suite, it provides twelve continuous control tasks from three domains for evaluation.

Benchmarks archive 2025-07-28

No leaderboard in the archive resolves to this dataset.

Papers archive 2025-07-28

No paper in the archive has a leaderboard row on this dataset; the archive counts 30 papers for it but never published that list.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • URLB (states, 5*10^5 frames)
  • URLB (states, 2*10^6 frames)
  • URLB (states, 10^6 frames)
  • URLB (states, 10^5 frames)
  • URLB (pixels, 5*10^5 frames)
  • URLB (pixels, 2*10^6 frames)
  • URLB (pixels, 10^6 frames)
  • URLB (pixels, 10^5 frames)
  • URLB

9 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections