{"url":"/dataset/urlb","name":"URLB","full_name":"Unsupervised Reinforcement Learning Benchmark","description_markdown":"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.","description_withheld":null,"homepage":"https://github.com/rll-research/url_benchmark","introduced_date":"2021-10-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/urlb-unsupervised-reinforcement-learning","title":"URLB: Unsupervised Reinforcement Learning Benchmark","first_author":"Michael Laskin","url":null},"license":null,"modalities":[],"tasks":[{"name":"Unsupervised Reinforcement Learning","url":"/task/unsupervised-reinforcement-learning","datasets_with_task":"/datasets/task/unsupervised-reinforcement-learning"}],"languages":[],"variants":["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"],"data_loaders":[],"num_papers_in_archive":30,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}